Token | Self |
Token ID | 12189 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
Slave | +2.616 |
atts | +2.608 |
Grande | +2.509 |
Warehouse | +2.468 |
Labrador | +2.466 |
Neg logit contributions | |
stroke | -3.016 |
Abstract | -2.808 |
edIn | -2.807 |
sense | -2.772 |
stal | -2.701 |
Token | Dest |
Token ID | 8145 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
stroke | +0.073 |
edIn | +0.068 |
Abstract | +0.067 |
sense | +0.067 |
stal | +0.065 |
Neg logit contributions | |
atts | -0.061 |
Slave | -0.061 |
Grande | -0.059 |
oven | -0.058 |
Labrador | -0.058 |
Token | ruct |
Token ID | 1356 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Slave | +1.603 |
atts | +1.599 |
Grande | +1.547 |
oven | +1.529 |
Warehouse | +1.524 |
Neg logit contributions | |
stroke | -1.283 |
edIn | -1.178 |
Abstract | -1.177 |
sense | -1.162 |
stal | -1.122 |
Token | s |
Token ID | 82 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Slave | +1.276 |
atts | +1.265 |
Grande | +1.207 |
Warehouse | +1.188 |
Labrador | +1.188 |
Neg logit contributions | |
stroke | -1.766 |
Abstract | -1.660 |
edIn | -1.649 |
sense | -1.637 |
stal | -1.598 |
Token | - |
Token ID | 12 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Slave | +0.766 |
atts | +0.766 |
Grande | +0.733 |
oven | +0.723 |
Labrador | +0.718 |
Neg logit contributions | |
stroke | -1.029 |
edIn | -0.964 |
Abstract | -0.962 |
sense | -0.953 |
stal | -0.929 |
Token | Fake |
Token ID | 49233 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
Slave | +0.860 |
atts | +0.857 |
Grande | +0.828 |
oven | +0.818 |
Warehouse | +0.814 |
Neg logit contributions | |
stroke | -0.774 |
edIn | -0.715 |
Abstract | -0.713 |
sense | -0.705 |
stal | -0.683 |
Token | Bon |
Token ID | 7979 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Slave | +6.284 |
atts | +5.999 |
Grande | +5.962 |
Warehouse | +5.841 |
Freak | +5.830 |
Neg logit contributions | |
stroke | -7.658 |
Abstract | -7.245 |
edIn | -7.231 |
sense | -7.100 |
stal | -6.810 |
Token | o |
Token ID | 78 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Slave | +1.979 |
atts | +1.964 |
Grande | +1.899 |
oven | +1.874 |
Warehouse | +1.869 |
Neg logit contributions | |
stroke | -1.859 |
Abstract | -1.735 |
edIn | -1.733 |
sense | -1.704 |
stal | -1.651 |
Token | - |
Token ID | 12 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
atts | +0.224 |
Slave | +0.224 |
Grande | +0.214 |
oven | +0.213 |
Labrador | +0.211 |
Neg logit contributions | |
stroke | -0.279 |
edIn | -0.260 |
Abstract | -0.259 |
sense | -0.258 |
stal | -0.251 |
Token | Animal |
Token ID | 40002 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
Slave | +0.915 |
atts | +0.911 |
Grande | +0.881 |
oven | +0.870 |
Warehouse | +0.866 |
Neg logit contributions | |
stroke | -0.831 |
edIn | -0.769 |
Abstract | -0.766 |
sense | -0.757 |
stal | -0.734 |
Token | Del |
Token ID | 4216 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
stroke | +0.520 |
sense | +0.487 |
edIn | +0.486 |
Abstract | +0.485 |
stal | +0.475 |
Neg logit contributions | |
atts | -0.387 |
Slave | -0.383 |
Grande | -0.370 |
oven | -0.365 |
Labrador | -0.360 |
Token | also |
Token ID | 635 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
stroke | +0.124 |
Abstract | +0.114 |
edIn | +0.114 |
sense | +0.113 |
stal | +0.109 |
Neg logit contributions | |
atts | -0.132 |
Slave | -0.132 |
oven | -0.127 |
Grande | -0.126 |
Warehouse | -0.126 |
Token | calling |
Token ID | 4585 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
Slave | +1.244 |
atts | +1.242 |
Grande | +1.188 |
oven | +1.174 |
Warehouse | +1.167 |
Neg logit contributions | |
stroke | -1.604 |
Abstract | -1.500 |
edIn | -1.497 |
sense | -1.485 |
stal | -1.445 |
Token | CNN |
Token ID | 8100 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
stroke | +0.707 |
edIn | +0.660 |
Abstract | +0.650 |
sense | +0.649 |
stal | +0.627 |
Neg logit contributions | |
atts | -0.741 |
Slave | -0.735 |
oven | -0.709 |
Warehouse | -0.694 |
Grande | -0.690 |
Token | � |
Token ID | 564 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
Slave | +1.329 |
atts | +1.324 |
Grande | +1.277 |
oven | +1.254 |
Labrador | +1.252 |
Neg logit contributions | |
stroke | -1.451 |
edIn | -1.350 |
Abstract | -1.348 |
sense | -1.334 |
stal | -1.296 |
Token | � |
Token ID | 250 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
stroke | +0.107 |
edIn | +0.095 |
Abstract | +0.094 |
sense | +0.092 |
stal | +0.088 |
Neg logit contributions | |
atts | -0.246 |
Slave | -0.245 |
Grande | -0.239 |
Warehouse | -0.238 |
oven | -0.237 |
Token | fake |
Token ID | 30706 |
Feature activation | +9.44e+00 |
Pos logit contributions | |
stroke | +0.240 |
Abstract | +0.223 |
edIn | +0.221 |
sense | +0.220 |
stal | +0.212 |
Neg logit contributions | |
Slave | -0.285 |
atts | -0.283 |
Grande | -0.274 |
Warehouse | -0.272 |
Labrador | -0.272 |
Token | news |
Token ID | 1705 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Slave | +3.762 |
atts | +3.650 |
Grande | +3.586 |
Labrador | +3.471 |
TVs | +3.441 |
Neg logit contributions | |
stroke | -9.630 |
edIn | -9.229 |
Abstract | -9.159 |
sense | -8.921 |
swer | -8.670 |
Token | . |
Token ID | 13 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Slave | +0.304 |
atts | +0.303 |
Grande | +0.292 |
oven | +0.290 |
Warehouse | +0.289 |
Neg logit contributions | |
stroke | -0.295 |
edIn | -0.273 |
Abstract | -0.272 |
sense | -0.271 |
stal | -0.264 |
Token | � |
Token ID | 447 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
Slave | +0.475 |
atts | +0.472 |
Grande | +0.457 |
oven | +0.450 |
Labrador | +0.449 |
Neg logit contributions | |
stroke | -0.467 |
edIn | -0.433 |
Abstract | -0.433 |
sense | -0.428 |
stal | -0.415 |
Token | � |
Token ID | 251 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Slave | +0.746 |
atts | +0.743 |
Grande | +0.719 |
oven | +0.709 |
Labrador | +0.708 |
Neg logit contributions | |
stroke | -0.657 |
Abstract | -0.606 |
edIn | -0.605 |
sense | -0.600 |
stal | -0.579 |
Token | On |
Token ID | 1550 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Slave | +0.314 |
atts | +0.314 |
Grande | +0.302 |
oven | +0.299 |
Warehouse | +0.298 |
Neg logit contributions | |
stroke | -0.298 |
Abstract | -0.275 |
edIn | -0.275 |
sense | -0.272 |
stal | -0.264 |
Token | Washington |
Token ID | 2669 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
atts | +0.404 |
Slave | +0.400 |
oven | +0.385 |
Grande | +0.382 |
Warehouse | +0.376 |
Neg logit contributions | |
stroke | -0.569 |
Abstract | -0.532 |
edIn | -0.531 |
sense | -0.529 |
stal | -0.516 |
Token | status |
Token ID | 3722 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
atts | +0.784 |
Slave | +0.782 |
Grande | +0.748 |
oven | +0.741 |
Warehouse | +0.733 |
Neg logit contributions | |
stroke | -1.051 |
Abstract | -0.982 |
edIn | -0.982 |
sense | -0.973 |
stal | -0.950 |
Token | quo |
Token ID | 18658 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Slave | +1.398 |
atts | +1.393 |
Grande | +1.353 |
oven | +1.337 |
Labrador | +1.333 |
Neg logit contributions | |
stroke | -0.960 |
edIn | -0.876 |
Abstract | -0.874 |
sense | -0.862 |
stal | -0.829 |
Token | , |
Token ID | 11 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
stroke | +1.849 |
Abstract | +1.713 |
edIn | +1.700 |
sense | +1.695 |
stal | +1.678 |
Neg logit contributions | |
atts | -1.574 |
Slave | -1.569 |
Grande | -1.497 |
oven | -1.495 |
Warehouse | -1.485 |
Token | the |
Token ID | 262 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
atts | +0.360 |
Slave | +0.358 |
Grande | +0.342 |
oven | +0.340 |
Warehouse | +0.337 |
Neg logit contributions | |
stroke | -0.507 |
edIn | -0.474 |
Abstract | -0.473 |
sense | -0.469 |
stal | -0.458 |
Token | ga |
Token ID | 31986 |
Feature activation | +9.31e+00 |
Pos logit contributions | |
atts | +0.239 |
Slave | +0.238 |
oven | +0.229 |
Grande | +0.227 |
Warehouse | +0.224 |
Neg logit contributions | |
stroke | -0.309 |
Abstract | -0.287 |
edIn | -0.286 |
sense | -0.285 |
stal | -0.279 |
Token | vel |
Token ID | 626 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
atts | +3.989 |
Slave | +3.887 |
Grande | +3.655 |
oven | +3.582 |
Labrador | +3.468 |
Neg logit contributions | |
stroke | -9.255 |
edIn | -8.966 |
Abstract | -8.827 |
sense | -8.799 |
stal | -8.390 |
Token | may |
Token ID | 743 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Slave | +1.314 |
atts | +1.306 |
Grande | +1.264 |
Labrador | +1.243 |
oven | +1.242 |
Neg logit contributions | |
stroke | -1.348 |
edIn | -1.257 |
Abstract | -1.257 |
sense | -1.241 |
stal | -1.202 |
Token | have |
Token ID | 423 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
Slave | +1.341 |
atts | +1.336 |
Grande | +1.285 |
Labrador | +1.266 |
oven | +1.263 |
Neg logit contributions | |
stroke | -1.625 |
edIn | -1.532 |
Abstract | -1.521 |
sense | -1.507 |
stal | -1.459 |
Token | been |
Token ID | 587 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Slave | +1.861 |
atts | +1.846 |
Grande | +1.791 |
Labrador | +1.758 |
oven | +1.744 |
Neg logit contributions | |
stroke | -2.385 |
edIn | -2.249 |
Abstract | -2.240 |
sense | -2.218 |
stal | -2.154 |
Token | more |
Token ID | 517 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
stroke | +0.189 |
Abstract | +0.174 |
edIn | +0.174 |
sense | +0.173 |
stal | +0.168 |
Neg logit contributions | |
atts | -0.175 |
Slave | -0.174 |
Grande | -0.167 |
oven | -0.166 |
Warehouse | -0.165 |
Token | services |
Token ID | 2594 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
stroke | +0.140 |
edIn | +0.131 |
Abstract | +0.131 |
sense | +0.131 |
stal | +0.127 |
Neg logit contributions | |
atts | -0.107 |
Slave | -0.107 |
Grande | -0.103 |
oven | -0.101 |
Warehouse | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Slave | +1.601 |
atts | +1.582 |
Grande | +1.531 |
Labrador | +1.507 |
oven | +1.501 |
Neg logit contributions | |
stroke | -2.044 |
edIn | -1.942 |
Abstract | -1.914 |
sense | -1.895 |
stal | -1.847 |
Token | Thank |
Token ID | 6952 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
Slave | +0.872 |
atts | +0.861 |
Grande | +0.827 |
Warehouse | +0.810 |
Labrador | +0.810 |
Neg logit contributions | |
stroke | -1.575 |
edIn | -1.489 |
Abstract | -1.484 |
sense | -1.471 |
stal | -1.441 |
Token | you |
Token ID | 345 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
stroke | +1.911 |
Abstract | +1.742 |
edIn | +1.731 |
sense | +1.725 |
stal | +1.673 |
Neg logit contributions | |
atts | -2.129 |
Slave | -2.127 |
Grande | -2.043 |
oven | -2.039 |
Warehouse | -2.017 |
Token | for |
Token ID | 329 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Slave | +1.256 |
atts | +1.248 |
Grande | +1.191 |
oven | +1.173 |
Labrador | +1.164 |
Neg logit contributions | |
stroke | -1.864 |
Abstract | -1.746 |
edIn | -1.744 |
sense | -1.734 |
stal | -1.690 |
Token | subscribing |
Token ID | 18412 |
Feature activation | +9.14e+00 |
Pos logit contributions | |
stroke | +0.469 |
Abstract | +0.441 |
sense | +0.437 |
edIn | +0.436 |
stal | +0.427 |
Neg logit contributions | |
Slave | -0.281 |
atts | -0.279 |
Grande | -0.266 |
oven | -0.259 |
Warehouse | -0.258 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Slave | +4.549 |
atts | +4.432 |
Grande | +4.286 |
Labrador | +4.263 |
TVs | +4.223 |
Neg logit contributions | |
edIn | -8.199 |
stroke | -8.157 |
Abstract | -7.798 |
stal | -7.646 |
sense | -7.609 |
Token | An |
Token ID | 1052 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Slave | +1.520 |
atts | +1.512 |
Grande | +1.444 |
oven | +1.418 |
Warehouse | +1.414 |
Neg logit contributions | |
stroke | -2.351 |
edIn | -2.211 |
Abstract | -2.208 |
sense | -2.188 |
stal | -2.136 |
Token | error |
Token ID | 4049 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
stroke | +0.119 |
Abstract | +0.113 |
sense | +0.112 |
edIn | +0.111 |
stal | +0.109 |
Neg logit contributions | |
Slave | -0.065 |
atts | -0.064 |
Grande | -0.061 |
oven | -0.060 |
Warehouse | -0.060 |
Token | has |
Token ID | 468 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Slave | +3.021 |
atts | +2.997 |
Grande | +2.913 |
oven | +2.887 |
Labrador | +2.861 |
Neg logit contributions | |
stroke | -3.527 |
edIn | -3.453 |
Abstract | -3.356 |
sense | -3.295 |
stal | -3.211 |
Token | occurred |
Token ID | 5091 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
Slave | +2.577 |
atts | +2.557 |
Grande | +2.496 |
oven | +2.488 |
Labrador | +2.466 |
Neg logit contributions | |
stroke | -2.327 |
edIn | -2.203 |
Abstract | -2.146 |
sense | -2.126 |
stal | -2.075 |
Token | services |
Token ID | 2594 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
stroke | +0.083 |
edIn | +0.078 |
Abstract | +0.078 |
sense | +0.078 |
stal | +0.076 |
Neg logit contributions | |
atts | -0.064 |
Slave | -0.064 |
Grande | -0.061 |
oven | -0.061 |
Warehouse | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Slave | +1.708 |
atts | +1.688 |
Grande | +1.634 |
Labrador | +1.609 |
oven | +1.602 |
Neg logit contributions | |
stroke | -2.192 |
edIn | -2.086 |
Abstract | -2.055 |
sense | -2.036 |
stal | -1.981 |
Token | Thank |
Token ID | 6952 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Slave | +0.858 |
atts | +0.849 |
Grande | +0.814 |
Labrador | +0.796 |
Warehouse | +0.796 |
Neg logit contributions | |
stroke | -1.530 |
edIn | -1.446 |
Abstract | -1.441 |
sense | -1.429 |
stal | -1.399 |
Token | you |
Token ID | 345 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
stroke | +2.055 |
Abstract | +1.868 |
edIn | +1.854 |
sense | +1.851 |
stal | +1.798 |
Neg logit contributions | |
atts | -2.323 |
Slave | -2.318 |
oven | -2.225 |
Grande | -2.223 |
Warehouse | -2.200 |
Token | for |
Token ID | 329 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
Slave | +1.216 |
atts | +1.208 |
Grande | +1.153 |
oven | +1.136 |
Warehouse | +1.127 |
Neg logit contributions | |
stroke | -1.803 |
Abstract | -1.689 |
edIn | -1.686 |
sense | -1.677 |
stal | -1.635 |
Token | subscribing |
Token ID | 18412 |
Feature activation | +9.11e+00 |
Pos logit contributions | |
stroke | +0.485 |
Abstract | +0.455 |
sense | +0.451 |
edIn | +0.451 |
stal | +0.441 |
Neg logit contributions | |
Slave | -0.292 |
atts | -0.290 |
Grande | -0.275 |
oven | -0.268 |
Warehouse | -0.268 |
Token | . |
Token ID | 13 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
Slave | +4.525 |
atts | +4.451 |
Grande | +4.295 |
Labrador | +4.270 |
TVs | +4.248 |
Neg logit contributions | |
edIn | -8.119 |
stroke | -8.081 |
Abstract | -7.759 |
stal | -7.587 |
sense | -7.573 |
Token | An |
Token ID | 1052 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Slave | +1.426 |
atts | +1.417 |
Grande | +1.354 |
oven | +1.329 |
Warehouse | +1.326 |
Neg logit contributions | |
stroke | -2.207 |
edIn | -2.076 |
Abstract | -2.073 |
sense | -2.054 |
stal | -2.005 |
Token | error |
Token ID | 4049 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
stroke | +0.121 |
Abstract | +0.114 |
sense | +0.113 |
edIn | +0.112 |
stal | +0.110 |
Neg logit contributions | |
Slave | -0.067 |
atts | -0.066 |
Grande | -0.062 |
oven | -0.061 |
Warehouse | -0.061 |
Token | has |
Token ID | 468 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
Slave | +3.064 |
atts | +3.040 |
Grande | +2.958 |
oven | +2.936 |
Labrador | +2.910 |
Neg logit contributions | |
stroke | -3.573 |
edIn | -3.500 |
Abstract | -3.400 |
sense | -3.339 |
stal | -3.256 |
Token | occurred |
Token ID | 5091 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
Slave | +2.683 |
atts | +2.661 |
Grande | +2.600 |
oven | +2.592 |
Labrador | +2.573 |
Neg logit contributions | |
stroke | -2.411 |
edIn | -2.282 |
Abstract | -2.221 |
sense | -2.200 |
stal | -2.148 |
Token | to |
Token ID | 284 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
stroke | +2.285 |
Abstract | +2.095 |
sense | +2.070 |
edIn | +2.068 |
stal | +2.040 |
Neg logit contributions | |
Slave | -2.204 |
atts | -2.203 |
oven | -2.094 |
Grande | -2.091 |
Warehouse | -2.089 |
Token | stop |
Token ID | 2245 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Slave | +0.439 |
atts | +0.438 |
Grande | +0.421 |
oven | +0.418 |
Warehouse | +0.415 |
Neg logit contributions | |
stroke | -0.423 |
Abstract | -0.389 |
edIn | -0.388 |
sense | -0.384 |
stal | -0.374 |
Token | the |
Token ID | 262 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
stroke | +1.574 |
Abstract | +1.455 |
edIn | +1.450 |
sense | +1.437 |
stal | +1.391 |
Neg logit contributions | |
atts | -1.447 |
Slave | -1.439 |
oven | -1.376 |
Grande | -1.372 |
Labrador | -1.353 |
Token | spread |
Token ID | 4104 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
Slave | +0.959 |
atts | +0.956 |
Grande | +0.917 |
oven | +0.904 |
Warehouse | +0.899 |
Neg logit contributions | |
stroke | -1.190 |
edIn | -1.112 |
Abstract | -1.111 |
sense | -1.100 |
stal | -1.070 |
Token | of |
Token ID | 286 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
stroke | +0.720 |
edIn | +0.675 |
Abstract | +0.675 |
sense | +0.668 |
stal | +0.651 |
Neg logit contributions | |
Slave | -0.517 |
atts | -0.515 |
Grande | -0.494 |
oven | -0.486 |
Labrador | -0.483 |
Token | fake |
Token ID | 8390 |
Feature activation | +9.08e+00 |
Pos logit contributions | |
Slave | +0.858 |
atts | +0.853 |
Grande | +0.821 |
oven | +0.808 |
Labrador | +0.805 |
Neg logit contributions | |
stroke | -1.066 |
edIn | -0.998 |
Abstract | -0.997 |
sense | -0.986 |
stal | -0.961 |
Token | news |
Token ID | 1705 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
Slave | +3.483 |
Grande | +3.418 |
atts | +3.327 |
Labrador | +3.304 |
TVs | +3.285 |
Neg logit contributions | |
stroke | -9.118 |
edIn | -8.836 |
Abstract | -8.806 |
sense | -8.615 |
stal | -8.439 |
Token | . |
Token ID | 13 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
Slave | +0.362 |
atts | +0.361 |
Grande | +0.346 |
oven | +0.342 |
Warehouse | +0.342 |
Neg logit contributions | |
stroke | -0.409 |
Abstract | -0.380 |
edIn | -0.378 |
sense | -0.377 |
stal | -0.367 |
Token |
|
Token ID | 198 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Slave | +0.632 |
atts | +0.628 |
Grande | +0.609 |
Labrador | +0.598 |
oven | +0.598 |
Neg logit contributions | |
stroke | -0.627 |
edIn | -0.582 |
Abstract | -0.580 |
sense | -0.574 |
stal | -0.557 |
Token |
|
Token ID | 198 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
Slave | +0.310 |
atts | +0.309 |
Grande | +0.298 |
oven | +0.295 |
Warehouse | +0.294 |
Neg logit contributions | |
stroke | -0.280 |
Abstract | -0.258 |
edIn | -0.258 |
sense | -0.255 |
stal | -0.247 |
Token | In |
Token ID | 818 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
Slave | +0.503 |
atts | +0.502 |
Grande | +0.486 |
oven | +0.480 |
Labrador | +0.477 |
Neg logit contributions | |
stroke | -0.418 |
edIn | -0.385 |
Abstract | -0.383 |
sense | -0.379 |
stal | -0.367 |
Token | allies |
Token ID | 7681 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
atts | +0.372 |
Slave | +0.369 |
Grande | +0.353 |
oven | +0.352 |
Labrador | +0.348 |
Neg logit contributions | |
stroke | -0.478 |
edIn | -0.448 |
Abstract | -0.447 |
sense | -0.444 |
stal | -0.433 |
Token | ? |
Token ID | 30 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
stroke | +0.813 |
Abstract | +0.749 |
edIn | +0.744 |
sense | +0.743 |
stal | +0.720 |
Neg logit contributions | |
atts | -0.870 |
Slave | -0.869 |
Grande | -0.836 |
oven | -0.830 |
Warehouse | -0.827 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
stroke | +1.237 |
Abstract | +1.159 |
edIn | +1.137 |
sense | +1.136 |
stal | +1.098 |
Neg logit contributions | |
atts | -1.282 |
Slave | -1.246 |
oven | -1.215 |
Grande | -1.200 |
enslaved | -1.188 |
Token |
|
Token ID | 198 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
stroke | +0.262 |
Abstract | +0.242 |
edIn | +0.241 |
sense | +0.239 |
stal | +0.231 |
Neg logit contributions | |
Slave | -0.293 |
atts | -0.293 |
Grande | -0.283 |
oven | -0.280 |
Warehouse | -0.279 |
Token | The |
Token ID | 464 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Slave | +0.032 |
atts | +0.032 |
Grande | +0.031 |
Warehouse | +0.031 |
oven | +0.030 |
Neg logit contributions | |
stroke | -0.025 |
Abstract | -0.023 |
edIn | -0.023 |
sense | -0.022 |
stal | -0.022 |
Token | Web |
Token ID | 5313 |
Feature activation | +9.04e+00 |
Pos logit contributions | |
atts | +0.210 |
Slave | +0.209 |
Grande | +0.200 |
oven | +0.199 |
Labrador | +0.196 |
Neg logit contributions | |
stroke | -0.274 |
Abstract | -0.257 |
edIn | -0.256 |
sense | -0.253 |
stal | -0.247 |
Token | we |
Token ID | 356 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Slave | +6.090 |
atts | +5.872 |
Warehouse | +5.767 |
Grande | +5.736 |
oven | +5.688 |
Neg logit contributions | |
stroke | -6.700 |
edIn | -6.370 |
Abstract | -6.291 |
sense | -6.171 |
stal | -6.029 |
Token | have |
Token ID | 423 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
stroke | +0.125 |
edIn | +0.116 |
Abstract | +0.115 |
sense | +0.114 |
stal | +0.111 |
Neg logit contributions | |
Slave | -0.129 |
atts | -0.129 |
Grande | -0.124 |
oven | -0.123 |
Labrador | -0.122 |
Token | works |
Token ID | 2499 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Slave | +1.742 |
atts | +1.703 |
Grande | +1.673 |
oven | +1.652 |
Labrador | +1.643 |
Neg logit contributions | |
stroke | -1.785 |
edIn | -1.663 |
Abstract | -1.662 |
sense | -1.635 |
stal | -1.576 |
Token | perfectly |
Token ID | 7138 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Slave | +1.347 |
atts | +1.343 |
Grande | +1.291 |
oven | +1.271 |
Labrador | +1.266 |
Neg logit contributions | |
stroke | -1.598 |
edIn | -1.495 |
Abstract | -1.490 |
sense | -1.475 |
stal | -1.434 |
Token | well |
Token ID | 880 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
stroke | +1.676 |
Abstract | +1.558 |
sense | +1.546 |
edIn | +1.542 |
stal | +1.503 |
Neg logit contributions | |
atts | -1.698 |
Slave | -1.677 |
Grande | -1.606 |
oven | -1.604 |
Warehouse | -1.580 |
Token | possession |
Token ID | 7797 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
Slave | +0.898 |
atts | +0.896 |
Grande | +0.861 |
oven | +0.850 |
Warehouse | +0.846 |
Neg logit contributions | |
stroke | -1.039 |
edIn | -0.968 |
Abstract | -0.967 |
sense | -0.957 |
stal | -0.931 |
Token | of |
Token ID | 286 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
Slave | +0.364 |
atts | +0.363 |
Grande | +0.348 |
oven | +0.341 |
Labrador | +0.341 |
Neg logit contributions | |
stroke | -0.500 |
edIn | -0.470 |
Abstract | -0.469 |
sense | -0.464 |
stal | -0.452 |
Token | the |
Token ID | 262 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
atts | +0.665 |
Slave | +0.659 |
oven | +0.635 |
Grande | +0.634 |
Warehouse | +0.628 |
Neg logit contributions | |
stroke | -0.755 |
Abstract | -0.702 |
edIn | -0.698 |
sense | -0.690 |
stal | -0.677 |
Token | Energy |
Token ID | 6682 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
atts | +0.315 |
Slave | +0.306 |
oven | +0.297 |
Grande | +0.294 |
Warehouse | +0.289 |
Neg logit contributions | |
stroke | -0.431 |
Abstract | -0.407 |
edIn | -0.402 |
sense | -0.401 |
stal | -0.393 |
Token | Committee |
Token ID | 4606 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Slave | +0.429 |
atts | +0.427 |
Grande | +0.410 |
oven | +0.403 |
Labrador | +0.401 |
Neg logit contributions | |
stroke | -0.571 |
edIn | -0.535 |
Abstract | -0.534 |
sense | -0.529 |
stal | -0.515 |
Token | ga |
Token ID | 31986 |
Feature activation | +9.00e+00 |
Pos logit contributions | |
stroke | +0.152 |
Abstract | +0.142 |
edIn | +0.141 |
sense | +0.141 |
stal | +0.137 |
Neg logit contributions | |
atts | -0.137 |
Slave | -0.137 |
Grande | -0.131 |
oven | -0.130 |
Warehouse | -0.129 |
Token | vel |
Token ID | 626 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
Slave | +4.036 |
atts | +3.995 |
Grande | +3.732 |
oven | +3.629 |
Labrador | +3.593 |
Neg logit contributions | |
stroke | -8.965 |
edIn | -8.496 |
sense | -8.485 |
Abstract | -8.341 |
stal | -8.126 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Slave | +0.638 |
atts | +0.636 |
Grande | +0.611 |
oven | +0.603 |
Warehouse | +0.600 |
Neg logit contributions | |
stroke | -0.751 |
edIn | -0.701 |
Abstract | -0.700 |
sense | -0.693 |
stal | -0.674 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
atts | +0.748 |
Slave | +0.747 |
Grande | +0.718 |
oven | +0.712 |
Warehouse | +0.707 |
Neg logit contributions | |
stroke | -0.733 |
Abstract | -0.679 |
edIn | -0.679 |
sense | -0.671 |
stal | -0.651 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
stroke | +0.161 |
Abstract | +0.149 |
edIn | +0.147 |
sense | +0.147 |
stal | +0.142 |
Neg logit contributions | |
Slave | -0.181 |
atts | -0.181 |
Grande | -0.175 |
oven | -0.173 |
Warehouse | -0.172 |
Token | Now |
Token ID | 3844 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
stroke | +0.016 |
Abstract | +0.015 |
edIn | +0.015 |
sense | +0.015 |
stal | +0.014 |
Neg logit contributions | |
Slave | -0.019 |
atts | -0.018 |
Grande | -0.018 |
Warehouse | -0.018 |
oven | -0.018 |
Token | he |
Token ID | 339 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
stroke | +0.326 |
Abstract | +0.304 |
edIn | +0.301 |
sense | +0.300 |
stal | +0.292 |
Neg logit contributions | |
Slave | -0.273 |
atts | -0.272 |
Grande | -0.260 |
oven | -0.258 |
Warehouse | -0.258 |
Token | says |
Token ID | 1139 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
Slave | +0.264 |
atts | +0.263 |
Grande | +0.253 |
oven | +0.249 |
Warehouse | +0.248 |
Neg logit contributions | |
stroke | -0.313 |
edIn | -0.292 |
Abstract | -0.292 |
sense | -0.289 |
stal | -0.281 |
Token | . |
Token ID | 13 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
Slave | +0.360 |
atts | +0.360 |
Grande | +0.346 |
Labrador | +0.341 |
oven | +0.341 |
Neg logit contributions | |
stroke | -0.476 |
edIn | -0.449 |
Abstract | -0.444 |
sense | -0.442 |
stal | -0.427 |
Token |
|
Token ID | 198 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
Slave | +0.372 |
atts | +0.371 |
Grande | +0.358 |
oven | +0.353 |
Labrador | +0.352 |
Neg logit contributions | |
stroke | -0.368 |
edIn | -0.341 |
Abstract | -0.341 |
sense | -0.337 |
stal | -0.327 |
Token |
|
Token ID | 198 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
stroke | +0.063 |
Abstract | +0.059 |
edIn | +0.058 |
sense | +0.058 |
stal | +0.056 |
Neg logit contributions | |
atts | -0.072 |
Slave | -0.072 |
Grande | -0.069 |
oven | -0.069 |
Warehouse | -0.068 |
Token | Fake |
Token ID | 49233 |
Feature activation | +8.98e+00 |
Pos logit contributions | |
stroke | +0.098 |
Abstract | +0.091 |
edIn | +0.090 |
sense | +0.089 |
stal | +0.086 |
Neg logit contributions | |
Slave | -0.116 |
atts | -0.115 |
Grande | -0.111 |
Warehouse | -0.110 |
oven | -0.110 |
Token | - |
Token ID | 12 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Slave | +6.648 |
atts | +6.533 |
Grande | +6.478 |
TVs | +6.343 |
Labrador | +6.316 |
Neg logit contributions | |
stroke | -6.046 |
edIn | -5.651 |
Abstract | -5.524 |
sense | -5.478 |
stal | -5.310 |
Token | data |
Token ID | 7890 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
Slave | +0.239 |
atts | +0.238 |
Grande | +0.230 |
Warehouse | +0.227 |
Labrador | +0.226 |
Neg logit contributions | |
stroke | -0.209 |
Abstract | -0.193 |
edIn | -0.192 |
sense | -0.191 |
stal | -0.184 |
Token | challenges |
Token ID | 6459 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Slave | +2.258 |
atts | +2.245 |
Grande | +2.167 |
oven | +2.132 |
Labrador | +2.128 |
Neg logit contributions | |
stroke | -2.505 |
edIn | -2.336 |
Abstract | -2.332 |
sense | -2.309 |
stal | -2.244 |
Token | have |
Token ID | 423 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
stroke | +0.120 |
Abstract | +0.111 |
edIn | +0.110 |
sense | +0.109 |
stal | +0.106 |
Neg logit contributions | |
atts | -0.120 |
Slave | -0.120 |
Grande | -0.115 |
oven | -0.114 |
Warehouse | -0.113 |
Token | been |
Token ID | 587 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Slave | +1.821 |
atts | +1.816 |
Grande | +1.740 |
oven | +1.717 |
Warehouse | +1.710 |
Neg logit contributions | |
stroke | -2.270 |
Abstract | -2.119 |
edIn | -2.119 |
sense | -2.097 |
stal | -2.040 |
Token | services |
Token ID | 2594 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
stroke | +0.159 |
edIn | +0.148 |
Abstract | +0.148 |
sense | +0.148 |
stal | +0.144 |
Neg logit contributions | |
atts | -0.122 |
Slave | -0.122 |
Grande | -0.116 |
oven | -0.115 |
Warehouse | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Slave | +1.703 |
atts | +1.682 |
Grande | +1.628 |
Labrador | +1.604 |
oven | +1.595 |
Neg logit contributions | |
stroke | -2.204 |
edIn | -2.100 |
Abstract | -2.065 |
sense | -2.046 |
stal | -1.992 |
Token | Thank |
Token ID | 6952 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
Slave | +0.871 |
atts | +0.862 |
Grande | +0.827 |
Labrador | +0.808 |
Warehouse | +0.808 |
Neg logit contributions | |
stroke | -1.556 |
edIn | -1.471 |
Abstract | -1.466 |
sense | -1.453 |
stal | -1.423 |
Token | you |
Token ID | 345 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
stroke | +2.057 |
Abstract | +1.872 |
edIn | +1.856 |
sense | +1.854 |
stal | +1.801 |
Neg logit contributions | |
atts | -2.306 |
Slave | -2.303 |
Grande | -2.209 |
oven | -2.206 |
Warehouse | -2.185 |
Token | for |
Token ID | 329 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
Slave | +1.282 |
atts | +1.275 |
Grande | +1.217 |
oven | +1.198 |
Warehouse | +1.190 |
Neg logit contributions | |
stroke | -1.920 |
Abstract | -1.800 |
edIn | -1.799 |
sense | -1.787 |
stal | -1.742 |
Token | subscribing |
Token ID | 18412 |
Feature activation | +8.95e+00 |
Pos logit contributions | |
stroke | +0.367 |
Abstract | +0.345 |
sense | +0.342 |
edIn | +0.342 |
stal | +0.334 |
Neg logit contributions | |
Slave | -0.219 |
atts | -0.217 |
Grande | -0.206 |
oven | -0.201 |
Warehouse | -0.201 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Slave | +4.470 |
atts | +4.397 |
Grande | +4.233 |
Labrador | +4.213 |
TVs | +4.195 |
Neg logit contributions | |
edIn | -7.982 |
stroke | -7.918 |
Abstract | -7.610 |
stal | -7.435 |
sense | -7.432 |
Token | An |
Token ID | 1052 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
Slave | +1.410 |
atts | +1.401 |
Grande | +1.339 |
oven | +1.313 |
Warehouse | +1.311 |
Neg logit contributions | |
stroke | -2.189 |
edIn | -2.059 |
Abstract | -2.056 |
sense | -2.037 |
stal | -1.989 |
Token | error |
Token ID | 4049 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
Slave | +0.008 |
atts | +0.008 |
Grande | +0.007 |
oven | +0.007 |
Warehouse | +0.007 |
Neg logit contributions | |
stroke | -0.014 |
Abstract | -0.013 |
sense | -0.013 |
edIn | -0.013 |
stal | -0.013 |
Token | has |
Token ID | 468 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
Slave | +3.104 |
atts | +3.077 |
Grande | +2.999 |
oven | +2.976 |
Labrador | +2.950 |
Neg logit contributions | |
stroke | -3.633 |
edIn | -3.560 |
Abstract | -3.456 |
sense | -3.397 |
stal | -3.305 |
Token | occurred |
Token ID | 5091 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Slave | +2.730 |
atts | +2.707 |
Grande | +2.646 |
oven | +2.638 |
Labrador | +2.617 |
Neg logit contributions | |
stroke | -2.473 |
edIn | -2.338 |
Abstract | -2.279 |
sense | -2.257 |
stal | -2.202 |
Token | & |
Token ID | 5 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Slave | +2.560 |
atts | +2.534 |
Grande | +2.443 |
Labrador | +2.392 |
Warehouse | +2.386 |
Neg logit contributions | |
stroke | -3.256 |
edIn | -3.071 |
Abstract | -3.054 |
sense | -3.026 |
stal | -2.934 |
Token | GF |
Token ID | 21713 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
Slave | +1.357 |
atts | +1.350 |
Grande | +1.305 |
oven | +1.288 |
Labrador | +1.283 |
Neg logit contributions | |
stroke | -1.206 |
edIn | -1.116 |
Abstract | -1.109 |
sense | -1.097 |
stal | -1.064 |
Token | Break |
Token ID | 12243 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
stroke | +0.470 |
sense | +0.436 |
Abstract | +0.435 |
edIn | +0.433 |
stal | +0.418 |
Neg logit contributions | |
atts | -0.423 |
Slave | -0.422 |
Grande | -0.410 |
oven | -0.408 |
Labrador | -0.403 |
Token | Up |
Token ID | 3205 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
stroke | +1.935 |
edIn | +1.786 |
sense | +1.778 |
Abstract | +1.756 |
stal | +1.723 |
Neg logit contributions | |
atts | -1.823 |
Slave | -1.806 |
Grande | -1.746 |
oven | -1.746 |
enslaved | -1.742 |
Token | - |
Token ID | 12 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Slave | +0.435 |
atts | +0.433 |
Grande | +0.415 |
oven | +0.408 |
Warehouse | +0.406 |
Neg logit contributions | |
stroke | -0.616 |
edIn | -0.578 |
Abstract | -0.578 |
sense | -0.572 |
stal | -0.558 |
Token | Fake |
Token ID | 49233 |
Feature activation | +8.86e+00 |
Pos logit contributions | |
Slave | +1.340 |
atts | +1.331 |
Grande | +1.289 |
oven | +1.272 |
Warehouse | +1.267 |
Neg logit contributions | |
stroke | -1.200 |
edIn | -1.110 |
Abstract | -1.101 |
sense | -1.091 |
stal | -1.059 |
Token | Teen |
Token ID | 21432 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Slave | +5.715 |
Grande | +5.458 |
atts | +5.450 |
Freak | +5.320 |
Warehouse | +5.301 |
Neg logit contributions | |
stroke | -7.030 |
edIn | -6.594 |
Abstract | -6.590 |
sense | -6.493 |
stal | -6.241 |
Token | A |
Token ID | 317 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
Slave | +1.698 |
atts | +1.698 |
Grande | +1.624 |
oven | +1.603 |
Labrador | +1.591 |
Neg logit contributions | |
stroke | -2.294 |
edIn | -2.149 |
Abstract | -2.145 |
sense | -2.127 |
stal | -2.073 |
Token | ussie |
Token ID | 43480 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
stroke | +0.491 |
Abstract | +0.452 |
edIn | +0.451 |
sense | +0.451 |
stal | +0.443 |
Neg logit contributions | |
atts | -0.432 |
Slave | -0.427 |
Grande | -0.411 |
enslaved | -0.409 |
oven | -0.408 |
Token | Guy |
Token ID | 13145 |
Feature activation | -2.11e-03 |
Pos logit contributions | |
stroke | +0.266 |
edIn | +0.248 |
Abstract | +0.248 |
sense | +0.246 |
stal | +0.240 |
Neg logit contributions | |
atts | -0.199 |
Slave | -0.195 |
oven | -0.188 |
Grande | -0.188 |
enslaved | -0.185 |
Token | - |
Token ID | 12 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
stroke | +0.002 |
edIn | +0.002 |
Abstract | +0.002 |
sense | +0.002 |
stal | +0.002 |
Neg logit contributions | |
Slave | -0.001 |
atts | -0.001 |
Grande | -0.001 |
oven | -0.001 |
Labrador | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
stroke | +0.288 |
Abstract | +0.269 |
edIn | +0.268 |
sense | +0.266 |
stal | +0.259 |
Neg logit contributions | |
atts | -0.245 |
Slave | -0.242 |
Grande | -0.232 |
oven | -0.231 |
Warehouse | -0.230 |
Token | the |
Token ID | 262 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Slave | +0.693 |
atts | +0.692 |
Grande | +0.663 |
oven | +0.654 |
Warehouse | +0.651 |
Neg logit contributions | |
stroke | -0.856 |
edIn | -0.799 |
Abstract | -0.799 |
sense | -0.791 |
stal | -0.770 |
Token | Moon |
Token ID | 6869 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
atts | +0.164 |
Slave | +0.163 |
Grande | +0.156 |
oven | +0.155 |
Warehouse | +0.153 |
Neg logit contributions | |
stroke | -0.220 |
edIn | -0.206 |
Abstract | -0.206 |
sense | -0.204 |
stal | -0.199 |
Token | landing |
Token ID | 9581 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Slave | +1.327 |
atts | +1.318 |
Grande | +1.259 |
oven | +1.235 |
Labrador | +1.230 |
Neg logit contributions | |
stroke | -2.101 |
Abstract | -1.978 |
edIn | -1.977 |
sense | -1.960 |
stal | -1.911 |
Token | was |
Token ID | 373 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
Slave | +0.765 |
atts | +0.761 |
Grande | +0.736 |
oven | +0.726 |
Labrador | +0.724 |
Neg logit contributions | |
stroke | -0.717 |
Abstract | -0.664 |
edIn | -0.664 |
sense | -0.656 |
stal | -0.635 |
Token | fake |
Token ID | 8390 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
atts | +0.534 |
Slave | +0.531 |
Grande | +0.506 |
oven | +0.500 |
Warehouse | +0.497 |
Neg logit contributions | |
stroke | -0.795 |
Abstract | -0.744 |
edIn | -0.744 |
sense | -0.736 |
stal | -0.719 |
Token | . |
Token ID | 13 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
Slave | +4.818 |
atts | +4.634 |
Grande | +4.613 |
Labrador | +4.582 |
TVs | +4.512 |
Neg logit contributions | |
stroke | -7.502 |
edIn | -7.200 |
sense | -7.124 |
Abstract | -7.117 |
onym | -6.765 |
Token | Flynn |
Token ID | 14654 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
atts | +0.729 |
Slave | +0.726 |
Grande | +0.698 |
oven | +0.694 |
Warehouse | +0.687 |
Neg logit contributions | |
stroke | -0.709 |
Abstract | -0.656 |
edIn | -0.656 |
sense | -0.649 |
stal | -0.628 |
Token | � |
Token ID | 447 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
stroke | +1.059 |
Abstract | +0.980 |
sense | +0.969 |
edIn | +0.968 |
stal | +0.939 |
Neg logit contributions | |
Slave | -1.001 |
atts | -0.995 |
oven | -0.962 |
Warehouse | -0.950 |
Grande | -0.949 |
Token | � |
Token ID | 247 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Slave | +0.108 |
atts | +0.108 |
Grande | +0.104 |
oven | +0.104 |
Warehouse | +0.103 |
Neg logit contributions | |
stroke | -0.086 |
edIn | -0.079 |
Abstract | -0.078 |
sense | -0.077 |
stal | -0.075 |
Token | s |
Token ID | 82 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Slave | +0.218 |
atts | +0.218 |
Grande | +0.212 |
oven | +0.210 |
Warehouse | +0.210 |
Neg logit contributions | |
stroke | -0.099 |
Abstract | -0.087 |
edIn | -0.087 |
sense | -0.086 |
stal | -0.081 |
Token | towards |
Token ID | 3371 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Slave | +1.597 |
atts | +1.591 |
Grande | +1.531 |
oven | +1.508 |
Labrador | +1.503 |
Neg logit contributions | |
stroke | -1.850 |
edIn | -1.731 |
Abstract | -1.725 |
sense | -1.705 |
stal | -1.659 |
Token | what |
Token ID | 644 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
stroke | +0.877 |
edIn | +0.821 |
Abstract | +0.818 |
sense | +0.812 |
stal | +0.792 |
Neg logit contributions | |
atts | -0.663 |
Slave | -0.656 |
oven | -0.626 |
Grande | -0.622 |
Warehouse | -0.619 |
Token | he |
Token ID | 339 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
stroke | +1.674 |
edIn | +1.539 |
Abstract | +1.533 |
sense | +1.516 |
stal | +1.471 |
Neg logit contributions | |
atts | -1.560 |
Slave | -1.548 |
oven | -1.499 |
Warehouse | -1.471 |
Grande | -1.468 |
Token | called |
Token ID | 1444 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
Slave | +0.013 |
atts | +0.013 |
oven | +0.012 |
Grande | +0.012 |
Warehouse | +0.012 |
Neg logit contributions | |
stroke | -0.016 |
Abstract | -0.015 |
edIn | -0.015 |
sense | -0.015 |
stal | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
stroke | +0.352 |
edIn | +0.328 |
Abstract | +0.327 |
sense | +0.325 |
stal | +0.316 |
Neg logit contributions | |
atts | -0.301 |
Slave | -0.299 |
Grande | -0.285 |
oven | -0.285 |
Warehouse | -0.282 |
Token | Beng |
Token ID | 14964 |
Feature activation | +8.63e+00 |
Pos logit contributions | |
atts | +0.200 |
Slave | +0.198 |
Grande | +0.188 |
oven | +0.188 |
Labrador | +0.186 |
Neg logit contributions | |
stroke | -0.295 |
edIn | -0.278 |
Abstract | -0.277 |
sense | -0.275 |
stal | -0.268 |
Token | alis |
Token ID | 27315 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
atts | +3.658 |
Slave | +3.620 |
Grande | +3.423 |
oven | +3.417 |
Labrador | +3.308 |
Neg logit contributions | |
stroke | -8.583 |
edIn | -8.390 |
Abstract | -8.154 |
sense | -8.117 |
stal | -7.820 |
Token | . |
Token ID | 13 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
atts | +0.084 |
Slave | +0.084 |
Grande | +0.080 |
oven | +0.080 |
Warehouse | +0.079 |
Neg logit contributions | |
stroke | -0.092 |
Abstract | -0.086 |
edIn | -0.085 |
sense | -0.084 |
stal | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
atts | +0.300 |
Slave | +0.299 |
Grande | +0.286 |
oven | +0.284 |
Labrador | +0.281 |
Neg logit contributions | |
stroke | -0.357 |
Abstract | -0.333 |
edIn | -0.333 |
sense | -0.330 |
stal | -0.320 |
Token |
|
Token ID | 198 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
stroke | +0.735 |
Abstract | +0.681 |
edIn | +0.678 |
sense | +0.671 |
stal | +0.649 |
Neg logit contributions | |
Slave | -0.817 |
atts | -0.817 |
Grande | -0.787 |
oven | -0.780 |
Warehouse | -0.776 |
Token | The |
Token ID | 464 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
stroke | +0.516 |
Abstract | +0.480 |
edIn | +0.475 |
sense | +0.470 |
stal | +0.453 |
Neg logit contributions | |
Slave | -0.618 |
atts | -0.615 |
Grande | -0.594 |
Labrador | -0.589 |
Warehouse | -0.589 |
Token | also |
Token ID | 635 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Slave | +1.200 |
atts | +1.195 |
Grande | +1.141 |
oven | +1.134 |
Warehouse | +1.130 |
Neg logit contributions | |
stroke | -1.544 |
Abstract | -1.441 |
edIn | -1.435 |
sense | -1.424 |
stal | -1.388 |
Token | been |
Token ID | 587 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Slave | +1.345 |
atts | +1.338 |
Grande | +1.277 |
oven | +1.265 |
Warehouse | +1.259 |
Neg logit contributions | |
stroke | -1.837 |
Abstract | -1.718 |
edIn | -1.713 |
sense | -1.702 |
stal | -1.658 |
Token | guilty |
Token ID | 6717 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
stroke | +0.937 |
Abstract | +0.877 |
sense | +0.865 |
edIn | +0.861 |
stal | +0.841 |
Neg logit contributions | |
Slave | -0.732 |
atts | -0.730 |
Grande | -0.699 |
oven | -0.698 |
Warehouse | -0.691 |
Token | of |
Token ID | 286 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
Slave | +1.817 |
atts | +1.815 |
Grande | +1.729 |
Labrador | +1.697 |
oven | +1.688 |
Neg logit contributions | |
stroke | -2.866 |
Abstract | -2.720 |
edIn | -2.713 |
sense | -2.674 |
stal | -2.603 |
Token | sharing |
Token ID | 7373 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
atts | +0.619 |
Slave | +0.619 |
Grande | +0.593 |
oven | +0.588 |
Warehouse | +0.584 |
Neg logit contributions | |
stroke | -0.716 |
edIn | -0.665 |
Abstract | -0.665 |
sense | -0.658 |
stal | -0.639 |
Token | fake |
Token ID | 8390 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
stroke | +0.823 |
Abstract | +0.767 |
edIn | +0.767 |
sense | +0.762 |
stal | +0.741 |
Neg logit contributions | |
atts | -0.614 |
Slave | -0.609 |
oven | -0.578 |
Grande | -0.576 |
Warehouse | -0.573 |
Token | news |
Token ID | 1705 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
Slave | +3.651 |
atts | +3.597 |
Grande | +3.564 |
Labrador | +3.410 |
Freak | +3.348 |
Neg logit contributions | |
stroke | -8.462 |
edIn | -8.111 |
Abstract | -8.093 |
sense | -7.869 |
stal | -7.694 |
Token | on |
Token ID | 319 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Slave | +0.567 |
atts | +0.564 |
Grande | +0.540 |
oven | +0.536 |
Warehouse | +0.534 |
Neg logit contributions | |
stroke | -0.661 |
Abstract | -0.614 |
edIn | -0.613 |
sense | -0.609 |
stal | -0.592 |
Token | his |
Token ID | 465 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
atts | +0.589 |
Slave | +0.587 |
Grande | +0.557 |
oven | +0.552 |
Warehouse | +0.546 |
Neg logit contributions | |
stroke | -0.945 |
edIn | -0.889 |
Abstract | -0.887 |
sense | -0.879 |
stal | -0.859 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
atts | +0.458 |
Slave | +0.456 |
Grande | +0.432 |
oven | +0.430 |
Warehouse | +0.425 |
Neg logit contributions | |
stroke | -0.693 |
edIn | -0.651 |
Abstract | -0.649 |
sense | -0.645 |
stal | -0.629 |
Token | page |
Token ID | 2443 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Slave | +1.331 |
atts | +1.320 |
Grande | +1.264 |
Warehouse | +1.227 |
Labrador | +1.227 |
Neg logit contributions | |
stroke | -2.274 |
Abstract | -2.143 |
edIn | -2.143 |
sense | -2.122 |
stal | -2.076 |
Token | Ottawa |
Token ID | 14074 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
atts | +0.134 |
Slave | +0.133 |
oven | +0.128 |
Grande | +0.126 |
Warehouse | +0.124 |
Neg logit contributions | |
stroke | -0.174 |
edIn | -0.163 |
Abstract | -0.163 |
sense | -0.162 |
stal | -0.157 |
Token | in |
Token ID | 287 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
stroke | +2.432 |
Abstract | +2.247 |
edIn | +2.227 |
sense | +2.218 |
stal | +2.155 |
Neg logit contributions | |
atts | -2.358 |
Slave | -2.351 |
oven | -2.263 |
Grande | -2.242 |
Labrador | -2.202 |
Token | January |
Token ID | 3269 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
atts | +0.126 |
Slave | +0.124 |
oven | +0.119 |
Grande | +0.118 |
Warehouse | +0.117 |
Neg logit contributions | |
stroke | -0.159 |
Abstract | -0.147 |
sense | -0.147 |
edIn | -0.147 |
stal | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Slave | +0.163 |
atts | +0.163 |
Grande | +0.156 |
oven | +0.155 |
Warehouse | +0.153 |
Neg logit contributions | |
stroke | -0.185 |
Abstract | -0.172 |
edIn | -0.172 |
sense | -0.171 |
stal | -0.166 |
Token | ( |
Token ID | 357 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
atts | +0.351 |
Slave | +0.350 |
Grande | +0.336 |
oven | +0.335 |
Labrador | +0.331 |
Neg logit contributions | |
stroke | -0.351 |
Abstract | -0.324 |
edIn | -0.323 |
sense | -0.320 |
stal | -0.311 |
Token | Wa |
Token ID | 33484 |
Feature activation | +8.47e+00 |
Pos logit contributions | |
Slave | +0.962 |
atts | +0.958 |
Grande | +0.929 |
oven | +0.912 |
Labrador | +0.911 |
Neg logit contributions | |
stroke | -0.901 |
edIn | -0.836 |
Abstract | -0.830 |
sense | -0.824 |
stal | -0.798 |
Token | ub |
Token ID | 549 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
atts | +6.059 |
Slave | +5.889 |
Grande | +5.827 |
oven | +5.652 |
Labrador | +5.612 |
Neg logit contributions | |
stroke | -6.160 |
edIn | -5.655 |
sense | -5.630 |
Abstract | -5.623 |
stal | -5.500 |
Token | ges |
Token ID | 3212 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Slave | +0.346 |
atts | +0.345 |
Grande | +0.333 |
oven | +0.329 |
Warehouse | +0.327 |
Neg logit contributions | |
stroke | -0.349 |
edIn | -0.324 |
Abstract | -0.323 |
sense | -0.320 |
stal | -0.310 |
Token | hig |
Token ID | 25196 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
Slave | +1.127 |
atts | +1.123 |
Grande | +1.084 |
oven | +1.070 |
Warehouse | +1.066 |
Neg logit contributions | |
stroke | -1.094 |
edIn | -1.013 |
Abstract | -1.012 |
sense | -1.001 |
stal | -0.972 |
Token | Rice |
Token ID | 13823 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Slave | +2.775 |
atts | +2.767 |
Grande | +2.660 |
oven | +2.619 |
Labrador | +2.619 |
Neg logit contributions | |
stroke | -3.047 |
Abstract | -2.839 |
edIn | -2.838 |
sense | -2.806 |
stal | -2.721 |
Token | / |
Token ID | 14 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Slave | +0.751 |
atts | +0.748 |
Grande | +0.719 |
oven | +0.712 |
Warehouse | +0.708 |
Neg logit contributions | |
stroke | -0.798 |
Abstract | -0.741 |
edIn | -0.740 |
sense | -0.734 |
stal | -0.715 |
Token | she |
Token ID | 673 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
stroke | +0.014 |
edIn | +0.013 |
Abstract | +0.013 |
sense | +0.013 |
stal | +0.012 |
Neg logit contributions | |
atts | -0.012 |
Slave | -0.012 |
oven | -0.011 |
Grande | -0.011 |
Warehouse | -0.011 |
Token | believed |
Token ID | 4762 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
Slave | +0.983 |
atts | +0.979 |
Grande | +0.939 |
oven | +0.938 |
Warehouse | +0.927 |
Neg logit contributions | |
stroke | -1.008 |
Abstract | -0.935 |
edIn | -0.923 |
sense | -0.922 |
stal | -0.899 |
Token | his |
Token ID | 465 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Slave | +1.950 |
atts | +1.921 |
Grande | +1.874 |
Labrador | +1.832 |
Warehouse | +1.828 |
Neg logit contributions | |
stroke | -2.388 |
Abstract | -2.247 |
edIn | -2.242 |
sense | -2.225 |
stal | -2.159 |
Token | papers |
Token ID | 9473 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
Slave | +0.981 |
atts | +0.981 |
Grande | +0.937 |
oven | +0.932 |
Warehouse | +0.920 |
Neg logit contributions | |
stroke | -1.195 |
edIn | -1.116 |
Abstract | -1.113 |
sense | -1.102 |
stal | -1.073 |
Token | were |
Token ID | 547 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Slave | +0.727 |
atts | +0.726 |
Grande | +0.699 |
oven | +0.693 |
Warehouse | +0.689 |
Neg logit contributions | |
stroke | -0.691 |
Abstract | -0.639 |
edIn | -0.635 |
sense | -0.630 |
stal | -0.612 |
Token | fake |
Token ID | 8390 |
Feature activation | +8.45e+00 |
Pos logit contributions | |
atts | +1.119 |
Slave | +1.118 |
Grande | +1.071 |
oven | +1.058 |
Warehouse | +1.050 |
Neg logit contributions | |
stroke | -1.418 |
Abstract | -1.321 |
edIn | -1.320 |
sense | -1.307 |
stal | -1.274 |
Token | and |
Token ID | 290 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Slave | +4.863 |
atts | +4.810 |
Grande | +4.724 |
Labrador | +4.622 |
Warehouse | +4.561 |
Neg logit contributions | |
stroke | -6.970 |
edIn | -6.761 |
Abstract | -6.633 |
sense | -6.592 |
stal | -6.300 |
Token | that |
Token ID | 326 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
atts | +0.212 |
Slave | +0.211 |
oven | +0.202 |
Grande | +0.200 |
Warehouse | +0.198 |
Neg logit contributions | |
stroke | -0.245 |
Abstract | -0.227 |
edIn | -0.225 |
sense | -0.222 |
stal | -0.218 |
Token | he |
Token ID | 339 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
atts | +0.431 |
Slave | +0.429 |
Grande | +0.410 |
oven | +0.409 |
Warehouse | +0.403 |
Neg logit contributions | |
stroke | -0.513 |
edIn | -0.476 |
Abstract | -0.475 |
sense | -0.470 |
stal | -0.458 |
Token | was |
Token ID | 373 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
Slave | +0.848 |
atts | +0.843 |
Grande | +0.811 |
oven | +0.808 |
Warehouse | +0.800 |
Neg logit contributions | |
stroke | -0.816 |
Abstract | -0.754 |
edIn | -0.744 |
sense | -0.742 |
stal | -0.722 |
Token | an |
Token ID | 281 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
atts | +0.027 |
Slave | +0.027 |
oven | +0.026 |
Grande | +0.026 |
Warehouse | +0.025 |
Neg logit contributions | |
stroke | -0.033 |
Abstract | -0.030 |
edIn | -0.030 |
sense | -0.029 |
stal | -0.029 |
Token | Emails |
Token ID | 39617 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
stroke | +1.362 |
Abstract | +1.274 |
sense | +1.260 |
edIn | +1.255 |
stal | +1.232 |
Neg logit contributions | |
Slave | -1.016 |
atts | -1.013 |
Grande | -0.973 |
Labrador | -0.947 |
oven | -0.942 |
Token | privacy |
Token ID | 6782 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Slave | +1.225 |
atts | +1.220 |
Grande | +1.162 |
oven | +1.139 |
Warehouse | +1.135 |
Neg logit contributions | |
stroke | -2.077 |
edIn | -1.958 |
Abstract | -1.956 |
sense | -1.939 |
stal | -1.894 |
Token | policy |
Token ID | 2450 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
stroke | +0.601 |
Abstract | +0.534 |
edIn | +0.532 |
sense | +0.531 |
stal | +0.504 |
Neg logit contributions | |
Slave | -0.998 |
atts | -0.998 |
Grande | -0.959 |
oven | -0.959 |
Warehouse | -0.951 |
Token | Thanks |
Token ID | 6930 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
stroke | +0.238 |
Abstract | +0.220 |
sense | +0.220 |
edIn | +0.218 |
swer | +0.210 |
Neg logit contributions | |
Slave | -0.255 |
atts | -0.254 |
Labrador | -0.243 |
oven | -0.240 |
Warehouse | -0.240 |
Token | for |
Token ID | 329 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
stroke | +1.305 |
edIn | +1.210 |
Abstract | +1.197 |
sense | +1.197 |
stal | +1.180 |
Neg logit contributions | |
atts | -0.992 |
Slave | -0.988 |
oven | -0.953 |
Grande | -0.944 |
Warehouse | -0.922 |
Token | subscribing |
Token ID | 18412 |
Feature activation | +8.32e+00 |
Pos logit contributions | |
stroke | +0.095 |
Abstract | +0.088 |
edIn | +0.088 |
sense | +0.087 |
stal | +0.087 |
Neg logit contributions | |
atts | -0.061 |
Slave | -0.060 |
Grande | -0.057 |
oven | -0.056 |
Warehouse | -0.055 |
Token | ! |
Token ID | 0 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Slave | +4.379 |
atts | +4.341 |
Grande | +4.148 |
Warehouse | +4.124 |
Labrador | +4.120 |
Neg logit contributions | |
stroke | -7.455 |
edIn | -7.248 |
Abstract | -7.244 |
sense | -7.104 |
stal | -6.962 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.00e+00 |
Pos logit contributions | |
Slave | +0.259 |
atts | +0.258 |
Grande | +0.250 |
oven | +0.247 |
Labrador | +0.246 |
Neg logit contributions | |
stroke | -0.203 |
edIn | -0.186 |
Abstract | -0.186 |
sense | -0.183 |
stal | -0.177 |
Token | Nick |
Token ID | 23609 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
stroke | +5.286 |
Abstract | +5.215 |
sense | +4.873 |
edIn | +4.778 |
stal | +4.630 |
Neg logit contributions | |
Slave | -6.185 |
atts | -6.073 |
Grande | -5.963 |
Warehouse | -5.941 |
Labrador | -5.941 |
Token | Saban |
Token ID | 41618 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
stroke | +0.398 |
Abstract | +0.371 |
edIn | +0.370 |
sense | +0.368 |
stal | +0.357 |
Neg logit contributions | |
atts | -0.321 |
Slave | -0.320 |
Grande | -0.308 |
oven | -0.305 |
Warehouse | -0.302 |
Token | has |
Token ID | 468 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
stroke | +0.383 |
edIn | +0.355 |
Abstract | +0.355 |
sense | +0.351 |
stal | +0.344 |
Neg logit contributions | |
atts | -0.367 |
Slave | -0.367 |
oven | -0.351 |
Grande | -0.351 |
Labrador | -0.346 |
Token | 12 |
Token ID | 1065 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Slave | +0.395 |
atts | +0.394 |
Grande | +0.381 |
oven | +0.377 |
Labrador | +0.375 |
Neg logit contributions | |
stroke | -0.320 |
edIn | -0.294 |
Abstract | -0.294 |
sense | -0.290 |
stal | -0.280 |
Token | Mar |
Token ID | 1526 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
Slave | +1.299 |
atts | +1.294 |
Grande | +1.246 |
oven | +1.228 |
Warehouse | +1.223 |
Neg logit contributions | |
stroke | -1.441 |
edIn | -1.344 |
Abstract | -1.341 |
sense | -1.326 |
stal | -1.289 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Slave | +2.766 |
atts | +2.746 |
Grande | +2.648 |
Labrador | +2.611 |
Warehouse | +2.598 |
Neg logit contributions | |
stroke | -3.387 |
edIn | -3.207 |
Abstract | -3.168 |
sense | -3.139 |
stal | -3.030 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
stroke | +0.125 |
Abstract | +0.117 |
edIn | +0.116 |
sense | +0.115 |
stal | +0.112 |
Neg logit contributions | |
atts | -0.109 |
Slave | -0.108 |
Grande | -0.103 |
oven | -0.103 |
Labrador | -0.101 |
Token | The |
Token ID | 383 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
stroke | +0.736 |
Abstract | +0.686 |
edIn | +0.683 |
sense | +0.675 |
stal | +0.658 |
Neg logit contributions | |
atts | -0.750 |
Slave | -0.746 |
Grande | -0.716 |
oven | -0.708 |
Labrador | -0.704 |
Token | Web |
Token ID | 5313 |
Feature activation | +8.30e+00 |
Pos logit contributions | |
atts | +0.088 |
Slave | +0.088 |
Grande | +0.084 |
oven | +0.083 |
Labrador | +0.082 |
Neg logit contributions | |
stroke | -0.114 |
Abstract | -0.107 |
edIn | -0.107 |
sense | -0.106 |
stal | -0.103 |
Token | we |
Token ID | 356 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Slave | +5.801 |
atts | +5.675 |
Warehouse | +5.565 |
oven | +5.508 |
Grande | +5.483 |
Neg logit contributions | |
stroke | -5.992 |
edIn | -5.631 |
Abstract | -5.550 |
sense | -5.465 |
stal | -5.369 |
Token | have |
Token ID | 423 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
stroke | +0.374 |
edIn | +0.347 |
Abstract | +0.346 |
sense | +0.345 |
stal | +0.335 |
Neg logit contributions | |
Slave | -0.332 |
atts | -0.331 |
Grande | -0.319 |
Labrador | -0.315 |
Warehouse | -0.314 |
Token | is |
Token ID | 318 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
Slave | +1.288 |
atts | +1.282 |
Grande | +1.231 |
oven | +1.212 |
Warehouse | +1.205 |
Neg logit contributions | |
stroke | -1.685 |
edIn | -1.578 |
Abstract | -1.577 |
sense | -1.560 |
stal | -1.519 |
Token | not |
Token ID | 407 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
Slave | +0.662 |
atts | +0.661 |
Grande | +0.635 |
oven | +0.626 |
Warehouse | +0.624 |
Neg logit contributions | |
stroke | -0.764 |
Abstract | -0.712 |
edIn | -0.711 |
sense | -0.704 |
stal | -0.686 |
Token | broken |
Token ID | 5445 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
Slave | +0.679 |
atts | +0.678 |
Grande | +0.653 |
oven | +0.645 |
Warehouse | +0.642 |
Neg logit contributions | |
stroke | -0.705 |
Abstract | -0.654 |
edIn | -0.654 |
sense | -0.647 |
stal | -0.628 |
Token | must |
Token ID | 1276 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
Slave | +1.180 |
atts | +1.177 |
Grande | +1.137 |
oven | +1.127 |
Warehouse | +1.116 |
Neg logit contributions | |
stroke | -1.092 |
Abstract | -1.008 |
edIn | -1.000 |
sense | -0.995 |
stal | -0.970 |
Token | select |
Token ID | 2922 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
atts | +3.539 |
Slave | +3.526 |
Grande | +3.451 |
Labrador | +3.400 |
Warehouse | +3.390 |
Neg logit contributions | |
stroke | -1.913 |
edIn | -1.774 |
Abstract | -1.739 |
sense | -1.718 |
stal | -1.612 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Slave | +0.787 |
atts | +0.784 |
Grande | +0.756 |
oven | +0.745 |
Labrador | +0.743 |
Neg logit contributions | |
stroke | -0.844 |
Abstract | -0.788 |
edIn | -0.780 |
sense | -0.776 |
stal | -0.751 |
Token | newsletter |
Token ID | 13129 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
Slave | +1.008 |
atts | +1.004 |
Grande | +0.961 |
oven | +0.943 |
Warehouse | +0.943 |
Neg logit contributions | |
stroke | -1.464 |
edIn | -1.374 |
Abstract | -1.370 |
sense | -1.359 |
stal | -1.325 |
Token | to |
Token ID | 284 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
atts | +1.756 |
Slave | +1.748 |
Grande | +1.684 |
Labrador | +1.649 |
oven | +1.642 |
Neg logit contributions | |
stroke | -2.216 |
edIn | -2.096 |
Abstract | -2.074 |
sense | -2.063 |
stal | -2.007 |
Token | subscribe |
Token ID | 12383 |
Feature activation | +8.29e+00 |
Pos logit contributions | |
Slave | +0.824 |
atts | +0.820 |
Grande | +0.782 |
oven | +0.762 |
Labrador | +0.761 |
Neg logit contributions | |
stroke | -1.512 |
edIn | -1.431 |
Abstract | -1.427 |
sense | -1.415 |
stal | -1.381 |
Token | to |
Token ID | 284 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
Slave | +4.410 |
atts | +4.352 |
Grande | +4.136 |
TVs | +4.078 |
Labrador | +4.027 |
Neg logit contributions | |
edIn | -7.268 |
stroke | -7.126 |
Abstract | -6.911 |
sense | -6.831 |
swer | -6.701 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Slave | +1.899 |
atts | +1.893 |
Grande | +1.824 |
Labrador | +1.786 |
Warehouse | +1.777 |
Neg logit contributions | |
stroke | -2.436 |
edIn | -2.325 |
Abstract | -2.282 |
sense | -2.261 |
stal | -2.200 |
Token | Sign |
Token ID | 5865 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Slave | +1.816 |
atts | +1.800 |
Grande | +1.755 |
Warehouse | +1.727 |
Labrador | +1.727 |
Neg logit contributions | |
stroke | -1.428 |
edIn | -1.313 |
Abstract | -1.304 |
sense | -1.288 |
stal | -1.246 |
Token | Up |
Token ID | 3205 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Slave | +0.921 |
atts | +0.919 |
Grande | +0.881 |
oven | +0.869 |
Labrador | +0.864 |
Neg logit contributions | |
stroke | -1.159 |
Abstract | -1.082 |
edIn | -1.082 |
sense | -1.071 |
stal | -1.042 |
Token | You |
Token ID | 921 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
Slave | +1.848 |
atts | +1.844 |
Grande | +1.770 |
oven | +1.748 |
Labrador | +1.738 |
Neg logit contributions | |
stroke | -2.162 |
Abstract | -2.015 |
edIn | -2.015 |
sense | -1.994 |
stal | -1.937 |
Token | April |
Token ID | 3035 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Slave | +0.749 |
atts | +0.748 |
Grande | +0.713 |
oven | +0.702 |
Warehouse | +0.697 |
Neg logit contributions | |
stroke | -1.165 |
Abstract | -1.094 |
edIn | -1.094 |
sense | -1.084 |
stal | -1.058 |
Token | . |
Token ID | 13 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Slave | +0.959 |
atts | +0.957 |
Grande | +0.920 |
oven | +0.908 |
Warehouse | +0.903 |
Neg logit contributions | |
stroke | -1.078 |
Abstract | -1.003 |
edIn | -1.002 |
sense | -0.992 |
stal | -0.965 |
Token | Senior |
Token ID | 14017 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
atts | +0.259 |
Slave | +0.256 |
Grande | +0.247 |
oven | +0.247 |
enslaved | +0.242 |
Neg logit contributions | |
stroke | -0.252 |
Abstract | -0.234 |
edIn | -0.232 |
sense | -0.230 |
stal | -0.223 |
Token | management |
Token ID | 4542 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
stroke | +2.416 |
sense | +2.232 |
Abstract | +2.217 |
edIn | +2.195 |
stal | +2.177 |
Neg logit contributions | |
Slave | -1.785 |
atts | -1.775 |
oven | -1.730 |
Grande | -1.723 |
enslaved | -1.658 |
Token | at |
Token ID | 379 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
stroke | +1.226 |
Abstract | +1.130 |
sense | +1.124 |
edIn | +1.107 |
stal | +1.094 |
Neg logit contributions | |
Slave | -1.115 |
atts | -1.097 |
oven | -1.076 |
Grande | -1.062 |
Warehouse | -1.039 |
Token | Eng |
Token ID | 1985 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
stroke | +0.571 |
edIn | +0.529 |
Abstract | +0.526 |
sense | +0.519 |
stal | +0.509 |
Neg logit contributions | |
atts | -0.519 |
Slave | -0.516 |
oven | -0.495 |
Grande | -0.495 |
Warehouse | -0.485 |
Token | ie |
Token ID | 494 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
atts | +5.447 |
Slave | +5.330 |
Grande | +5.145 |
Warehouse | +5.127 |
Labrador | +5.094 |
Neg logit contributions | |
stroke | -6.001 |
Abstract | -5.756 |
edIn | -5.717 |
sense | -5.595 |
stal | -5.329 |
Token | , |
Token ID | 11 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Slave | +0.664 |
atts | +0.660 |
Grande | +0.631 |
oven | +0.624 |
Labrador | +0.617 |
Neg logit contributions | |
stroke | -0.979 |
Abstract | -0.917 |
edIn | -0.916 |
sense | -0.909 |
stal | -0.887 |
Token | the |
Token ID | 262 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
Slave | +0.403 |
atts | +0.403 |
Grande | +0.388 |
oven | +0.384 |
Warehouse | +0.381 |
Neg logit contributions | |
stroke | -0.384 |
edIn | -0.355 |
Abstract | -0.354 |
sense | -0.350 |
stal | -0.339 |
Token | French |
Token ID | 4141 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
stroke | +0.072 |
Abstract | +0.066 |
edIn | +0.066 |
sense | +0.065 |
stal | +0.064 |
Neg logit contributions | |
atts | -0.053 |
Slave | -0.052 |
oven | -0.050 |
Grande | -0.050 |
Warehouse | -0.048 |
Token | company |
Token ID | 1664 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
atts | +0.461 |
Slave | +0.459 |
Grande | +0.436 |
oven | +0.434 |
Warehouse | +0.425 |
Neg logit contributions | |
stroke | -0.662 |
Abstract | -0.618 |
edIn | -0.615 |
sense | -0.608 |
stal | -0.595 |
Token | we |
Token ID | 356 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
stroke | +0.414 |
edIn | +0.384 |
Abstract | +0.382 |
sense | +0.378 |
stal | +0.367 |
Neg logit contributions | |
Slave | -0.438 |
atts | -0.437 |
Grande | -0.423 |
oven | -0.416 |
Labrador | -0.416 |
Token | investigated |
Token ID | 12565 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
stroke | +1.568 |
Abstract | +1.481 |
sense | +1.444 |
edIn | +1.441 |
stal | +1.409 |
Neg logit contributions | |
Slave | -1.499 |
atts | -1.485 |
Grande | -1.440 |
oven | -1.420 |
Warehouse | -1.412 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
stroke | +0.475 |
Abstract | +0.439 |
edIn | +0.438 |
sense | +0.433 |
stal | +0.420 |
Neg logit contributions | |
Slave | -0.511 |
atts | -0.511 |
Grande | -0.493 |
oven | -0.487 |
Warehouse | -0.485 |
Token | in |
Token ID | 287 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
stroke | +0.836 |
Abstract | +0.777 |
edIn | +0.772 |
sense | +0.768 |
stal | +0.742 |
Neg logit contributions | |
atts | -0.815 |
Slave | -0.811 |
Grande | -0.781 |
oven | -0.774 |
Warehouse | -0.770 |
Token | vivo |
Token ID | 34714 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
stroke | +0.620 |
Abstract | +0.585 |
edIn | +0.581 |
sense | +0.581 |
stal | +0.567 |
Neg logit contributions | |
Slave | -0.348 |
atts | -0.344 |
Grande | -0.328 |
oven | -0.321 |
Warehouse | -0.321 |
Token | pharmac |
Token ID | 25702 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
stroke | +1.285 |
Abstract | +1.193 |
sense | +1.182 |
edIn | +1.179 |
stal | +1.144 |
Neg logit contributions | |
atts | -1.300 |
Slave | -1.295 |
Grande | -1.249 |
oven | -1.239 |
Warehouse | -1.232 |
Token | ological |
Token ID | 2770 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
stroke | +7.592 |
Abstract | +7.284 |
sense | +7.095 |
stal | +7.036 |
onym | +6.799 |
Neg logit contributions | |
Slave | -7.302 |
Grande | -7.274 |
TVs | -7.179 |
Warehouse | -7.047 |
atts | -7.019 |
Token | profile |
Token ID | 7034 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
stroke | +2.841 |
Abstract | +2.654 |
sense | +2.629 |
edIn | +2.570 |
stal | +2.530 |
Neg logit contributions | |
atts | -3.035 |
Slave | -3.009 |
oven | -2.947 |
Grande | -2.917 |
Warehouse | -2.902 |
Token | of |
Token ID | 286 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
stroke | +3.553 |
Abstract | +3.341 |
edIn | +3.299 |
sense | +3.297 |
stal | +3.210 |
Neg logit contributions | |
Slave | -2.804 |
atts | -2.789 |
Grande | -2.679 |
Warehouse | -2.646 |
oven | -2.642 |
Token | N |
Token ID | 399 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
stroke | +1.220 |
Abstract | +1.125 |
edIn | +1.120 |
sense | +1.113 |
stal | +1.075 |
Neg logit contributions | |
atts | -1.223 |
Slave | -1.208 |
Grande | -1.163 |
oven | -1.157 |
Warehouse | -1.148 |
Token | - |
Token ID | 12 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
stroke | +3.670 |
Abstract | +3.401 |
sense | +3.379 |
edIn | +3.366 |
stal | +3.244 |
Neg logit contributions | |
Slave | -3.906 |
atts | -3.841 |
Grande | -3.742 |
Warehouse | -3.725 |
Freak | -3.653 |
Token | it |
Token ID | 340 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
stroke | +1.696 |
Abstract | +1.576 |
sense | +1.559 |
edIn | +1.556 |
stal | +1.493 |
Neg logit contributions | |
atts | -1.541 |
Slave | -1.530 |
oven | -1.466 |
Grande | -1.461 |
Warehouse | -1.451 |
Token | is |
Token ID | 318 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
stroke | +1.559 |
Abstract | +1.435 |
edIn | +1.409 |
sense | +1.405 |
stal | +1.354 |
Neg logit contributions | |
Slave | -1.914 |
atts | -1.897 |
Grande | -1.838 |
oven | -1.824 |
Warehouse | -1.819 |
Token | possible |
Token ID | 1744 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
stroke | +1.302 |
Abstract | +1.206 |
sense | +1.170 |
edIn | +1.170 |
stal | +1.132 |
Neg logit contributions | |
Slave | -1.569 |
atts | -1.567 |
Grande | -1.511 |
Warehouse | -1.499 |
oven | -1.496 |
Token | to |
Token ID | 284 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
stroke | +3.380 |
Abstract | +3.135 |
sense | +3.081 |
edIn | +3.078 |
stal | +2.978 |
Neg logit contributions | |
Slave | -3.197 |
atts | -3.170 |
oven | -3.056 |
Grande | -3.048 |
Warehouse | -3.025 |
Token | perform |
Token ID | 1620 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
stroke | +1.060 |
Abstract | +0.974 |
sense | +0.962 |
edIn | +0.948 |
stal | +0.927 |
Neg logit contributions | |
atts | -1.123 |
Slave | -1.116 |
Grande | -1.080 |
oven | -1.074 |
Warehouse | -1.062 |
Token | pharmac |
Token ID | 25702 |
Feature activation | -9.93e+00 |
Pos logit contributions | |
atts | +0.338 |
Slave | +0.337 |
Grande | +0.323 |
oven | +0.320 |
Warehouse | +0.318 |
Neg logit contributions | |
stroke | -0.362 |
Abstract | -0.337 |
edIn | -0.335 |
sense | -0.333 |
stal | -0.323 |
Token | ological |
Token ID | 2770 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
stroke | +5.669 |
Abstract | +5.226 |
sense | +5.015 |
stal | +4.905 |
edIn | +4.833 |
Neg logit contributions | |
Slave | -8.297 |
Grande | -8.269 |
atts | -8.166 |
Warehouse | -8.010 |
TVs | -8.000 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
stroke | +2.447 |
Abstract | +2.257 |
sense | +2.243 |
edIn | +2.229 |
stal | +2.159 |
Neg logit contributions | |
atts | -2.242 |
Slave | -2.203 |
Grande | -2.123 |
oven | -2.116 |
Warehouse | -2.093 |
Token | elect |
Token ID | 1742 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
stroke | +1.279 |
Abstract | +1.190 |
sense | +1.180 |
edIn | +1.176 |
stal | +1.141 |
Neg logit contributions | |
atts | -1.101 |
Slave | -1.089 |
Grande | -1.045 |
oven | -1.029 |
Warehouse | -1.027 |
Token | roph |
Token ID | 10051 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
stroke | +2.022 |
Abstract | +1.845 |
edIn | +1.830 |
sense | +1.823 |
stal | +1.744 |
Neg logit contributions | |
Slave | -2.286 |
atts | -2.268 |
Grande | -2.237 |
Warehouse | -2.183 |
Labrador | -2.163 |
Token | ys |
Token ID | 893 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
stroke | +3.021 |
Abstract | +2.817 |
edIn | +2.763 |
sense | +2.748 |
stal | +2.662 |
Neg logit contributions | |
Slave | -3.735 |
atts | -3.722 |
Grande | -3.690 |
Labrador | -3.611 |
Warehouse | -3.572 |
Token | 111 |
Token ID | 16243 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Slave | +1.353 |
atts | +1.349 |
Grande | +1.305 |
oven | +1.290 |
Labrador | +1.283 |
Neg logit contributions | |
stroke | -1.176 |
edIn | -1.089 |
Abstract | -1.083 |
sense | -1.070 |
stal | -1.037 |
Token | ) |
Token ID | 8 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
Slave | +1.276 |
atts | +1.270 |
Grande | +1.209 |
oven | +1.182 |
Labrador | +1.179 |
Neg logit contributions | |
stroke | -2.409 |
edIn | -2.302 |
Abstract | -2.268 |
sense | -2.254 |
stal | -2.204 |
Token | ( |
Token ID | 357 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
atts | +0.177 |
Slave | +0.176 |
Grande | +0.169 |
oven | +0.168 |
Warehouse | +0.167 |
Neg logit contributions | |
stroke | -0.165 |
Abstract | -0.153 |
edIn | -0.151 |
sense | -0.151 |
stal | -0.146 |
Token | 17 |
Token ID | 1558 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
Slave | +1.298 |
atts | +1.293 |
Grande | +1.249 |
oven | +1.233 |
Labrador | +1.227 |
Neg logit contributions | |
stroke | -1.242 |
edIn | -1.154 |
Abstract | -1.148 |
sense | -1.136 |
stal | -1.102 |
Token | ) |
Token ID | 8 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
Slave | +0.378 |
atts | +0.377 |
Grande | +0.358 |
oven | +0.352 |
Warehouse | +0.350 |
Neg logit contributions | |
stroke | -0.639 |
Abstract | -0.602 |
edIn | -0.599 |
sense | -0.596 |
stal | -0.582 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.71e+00 |
Pos logit contributions | |
Slave | +0.371 |
atts | +0.366 |
Grande | +0.357 |
Labrador | +0.352 |
Warehouse | +0.351 |
Neg logit contributions | |
stroke | -0.369 |
edIn | -0.343 |
Abstract | -0.342 |
sense | -0.340 |
stal | -0.328 |
Token | United |
Token ID | 17013 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
Abstract | +6.376 |
stroke | +6.366 |
sense | +5.884 |
edIn | +5.742 |
stal | +5.580 |
Neg logit contributions | |
Slave | -7.403 |
atts | -7.253 |
Grande | -7.129 |
Warehouse | -7.129 |
Labrador | -7.118 |
Token | States |
Token ID | 1829 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
stroke | +1.910 |
edIn | +1.774 |
Abstract | +1.772 |
sense | +1.769 |
stal | +1.712 |
Neg logit contributions | |
atts | -1.788 |
Slave | -1.757 |
Grande | -1.700 |
oven | -1.691 |
Labrador | -1.677 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
stroke | +0.570 |
edIn | +0.532 |
Abstract | +0.532 |
sense | +0.526 |
stal | +0.511 |
Neg logit contributions | |
atts | -0.465 |
Slave | -0.463 |
Grande | -0.445 |
oven | -0.441 |
Labrador | -0.435 |
Token | Court |
Token ID | 3078 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
stroke | +0.727 |
Abstract | +0.669 |
edIn | +0.667 |
sense | +0.657 |
stal | +0.642 |
Neg logit contributions | |
atts | -0.723 |
Slave | -0.714 |
Grande | -0.689 |
oven | -0.688 |
Labrador | -0.677 |
Token | case |
Token ID | 1339 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
stroke | +0.209 |
Abstract | +0.194 |
edIn | +0.194 |
sense | +0.191 |
stal | +0.186 |
Neg logit contributions | |
Slave | -0.210 |
atts | -0.210 |
Grande | -0.202 |
oven | -0.200 |
Labrador | -0.199 |
Token | others |
Token ID | 1854 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
stroke | +0.707 |
Abstract | +0.666 |
edIn | +0.663 |
sense | +0.655 |
stal | +0.644 |
Neg logit contributions | |
atts | -0.490 |
Slave | -0.474 |
oven | -0.468 |
Grande | -0.458 |
Warehouse | -0.449 |
Token | heavily |
Token ID | 7272 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
Slave | +1.111 |
atts | +1.109 |
Grande | +1.067 |
oven | +1.056 |
Warehouse | +1.051 |
Neg logit contributions | |
stroke | -1.122 |
edIn | -1.041 |
Abstract | -1.040 |
sense | -1.027 |
stal | -0.999 |
Token | influenced |
Token ID | 12824 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
atts | +0.475 |
Slave | +0.470 |
Grande | +0.445 |
oven | +0.445 |
Warehouse | +0.442 |
Neg logit contributions | |
stroke | -0.674 |
edIn | -0.637 |
Abstract | -0.634 |
sense | -0.620 |
stal | -0.615 |
Token | by |
Token ID | 416 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Slave | +0.182 |
atts | +0.182 |
Grande | +0.174 |
oven | +0.172 |
Warehouse | +0.171 |
Neg logit contributions | |
stroke | -0.241 |
edIn | -0.226 |
Abstract | -0.226 |
sense | -0.223 |
stal | -0.218 |
Token | Buddhism |
Token ID | 25932 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
stroke | +0.354 |
edIn | +0.332 |
Abstract | +0.331 |
sense | +0.327 |
stal | +0.320 |
Neg logit contributions | |
atts | -0.293 |
Slave | -0.289 |
oven | -0.278 |
Grande | -0.276 |
Warehouse | -0.275 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.71e+00 |
Pos logit contributions | |
Slave | +0.104 |
atts | +0.104 |
Grande | +0.100 |
oven | +0.099 |
Warehouse | +0.098 |
Neg logit contributions | |
stroke | -0.105 |
edIn | -0.097 |
Abstract | -0.097 |
sense | -0.096 |
stal | -0.093 |
Token | " |
Token ID | 1 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
Abstract | +6.383 |
stroke | +6.374 |
sense | +5.886 |
edIn | +5.755 |
stal | +5.597 |
Neg logit contributions | |
Slave | -7.375 |
atts | -7.219 |
Warehouse | -7.108 |
Grande | -7.101 |
Labrador | -7.085 |
Token | Sec |
Token ID | 6558 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
stroke | +1.394 |
Abstract | +1.301 |
edIn | +1.271 |
sense | +1.266 |
stal | +1.210 |
Neg logit contributions | |
atts | -1.830 |
Slave | -1.802 |
Grande | -1.748 |
oven | -1.736 |
Warehouse | -1.723 |
Token | rets |
Token ID | 8004 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Slave | +1.487 |
atts | +1.484 |
Grande | +1.412 |
oven | +1.390 |
Warehouse | +1.381 |
Neg logit contributions | |
stroke | -2.408 |
edIn | -2.266 |
Abstract | -2.263 |
sense | -2.244 |
stal | -2.189 |
Token | of |
Token ID | 286 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
stroke | +1.818 |
edIn | +1.664 |
Abstract | +1.662 |
sense | +1.649 |
stal | +1.603 |
Neg logit contributions | |
atts | -1.558 |
Slave | -1.516 |
Grande | -1.464 |
oven | -1.458 |
Labrador | -1.444 |
Token | Season |
Token ID | 7369 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
atts | +0.027 |
Slave | +0.027 |
Grande | +0.026 |
oven | +0.026 |
Warehouse | +0.026 |
Neg logit contributions | |
stroke | -0.030 |
edIn | -0.028 |
Abstract | -0.028 |
sense | -0.027 |
stal | -0.027 |
Token | op |
Token ID | 404 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Slave | +0.067 |
atts | +0.066 |
Grande | +0.063 |
Warehouse | +0.061 |
Labrador | +0.061 |
Neg logit contributions | |
stroke | -0.148 |
Abstract | -0.140 |
sense | -0.139 |
edIn | -0.139 |
stal | -0.136 |
Token | course |
Token ID | 1781 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Slave | +0.861 |
atts | +0.853 |
Grande | +0.832 |
Labrador | +0.812 |
Warehouse | +0.810 |
Neg logit contributions | |
stroke | -1.061 |
edIn | -0.999 |
Abstract | -0.995 |
sense | -0.985 |
stal | -0.952 |
Token | ( |
Token ID | 357 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
stroke | +1.020 |
Abstract | +0.948 |
edIn | +0.948 |
sense | +0.936 |
stal | +0.909 |
Neg logit contributions | |
Slave | -1.002 |
atts | -0.999 |
Grande | -0.963 |
oven | -0.950 |
Warehouse | -0.946 |
Token | 1 |
Token ID | 16 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Slave | +0.899 |
atts | +0.895 |
Grande | +0.865 |
oven | +0.855 |
Labrador | +0.850 |
Neg logit contributions | |
stroke | -0.812 |
edIn | -0.751 |
Abstract | -0.748 |
sense | -0.740 |
stal | -0.716 |
Token | ) |
Token ID | 8 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
stroke | +0.253 |
Abstract | +0.238 |
edIn | +0.235 |
sense | +0.235 |
stal | +0.230 |
Neg logit contributions | |
atts | -0.157 |
Slave | -0.156 |
Grande | -0.148 |
oven | -0.147 |
Warehouse | -0.145 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.69e+00 |
Pos logit contributions | |
stroke | +0.717 |
edIn | +0.666 |
Abstract | +0.665 |
sense | +0.656 |
stal | +0.637 |
Neg logit contributions | |
Slave | -0.746 |
atts | -0.739 |
Grande | -0.717 |
oven | -0.705 |
Warehouse | -0.705 |
Token | The |
Token ID | 464 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Abstract | +6.353 |
stroke | +6.351 |
sense | +5.863 |
edIn | +5.715 |
stal | +5.558 |
Neg logit contributions | |
Slave | -7.386 |
atts | -7.246 |
Grande | -7.124 |
Warehouse | -7.112 |
Labrador | -7.106 |
Token | IRS |
Token ID | 14440 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
stroke | +0.856 |
Abstract | +0.806 |
edIn | +0.801 |
sense | +0.793 |
stal | +0.775 |
Neg logit contributions | |
atts | -0.638 |
Slave | -0.630 |
oven | -0.602 |
Grande | -0.602 |
Labrador | -0.588 |
Token | sent |
Token ID | 1908 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
stroke | +1.112 |
Abstract | +1.035 |
edIn | +1.027 |
sense | +1.015 |
stal | +0.980 |
Neg logit contributions | |
atts | -1.088 |
Slave | -1.073 |
oven | -1.042 |
Grande | -1.033 |
Labrador | -1.019 |
Token | one |
Token ID | 530 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
Slave | +1.263 |
atts | +1.253 |
Grande | +1.212 |
Labrador | +1.191 |
oven | +1.188 |
Neg logit contributions | |
stroke | -1.406 |
edIn | -1.313 |
Abstract | -1.312 |
sense | -1.299 |
stal | -1.263 |
Token | of |
Token ID | 286 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
Slave | +2.224 |
atts | +2.184 |
Grande | +2.126 |
Labrador | +2.094 |
enslaved | +2.066 |
Neg logit contributions | |
stroke | -2.934 |
edIn | -2.775 |
Abstract | -2.775 |
sense | -2.748 |
stal | -2.680 |
Token | a |
Token ID | 257 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
stroke | +0.350 |
Abstract | +0.321 |
sense | +0.317 |
edIn | +0.316 |
stal | +0.307 |
Neg logit contributions | |
Slave | -0.354 |
atts | -0.350 |
Grande | -0.341 |
Warehouse | -0.340 |
Labrador | -0.331 |
Token | friend |
Token ID | 1545 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
stroke | +0.580 |
edIn | +0.538 |
Abstract | +0.538 |
sense | +0.534 |
stal | +0.518 |
Neg logit contributions | |
Slave | -0.539 |
atts | -0.538 |
Grande | -0.517 |
oven | -0.511 |
Warehouse | -0.509 |
Token | Print |
Token ID | 12578 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
stroke | +4.287 |
edIn | +3.951 |
Abstract | +3.941 |
sense | +3.864 |
onym | +3.709 |
Neg logit contributions | |
atts | -4.286 |
ampunk | -3.976 |
proport | -3.923 |
Cosponsors | -3.917 |
lear | -3.912 |
Token | able |
Token ID | 540 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Slave | +1.775 |
Grande | +1.729 |
Labrador | +1.722 |
atts | +1.700 |
Warehouse | +1.691 |
Neg logit contributions | |
stroke | -0.832 |
edIn | -0.732 |
stal | -0.720 |
sense | -0.697 |
Abstract | -0.686 |
Token | version |
Token ID | 2196 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
atts | +0.835 |
Slave | +0.828 |
Grande | +0.777 |
oven | +0.767 |
Labrador | +0.756 |
Neg logit contributions | |
stroke | -1.719 |
Abstract | -1.633 |
sense | -1.620 |
edIn | -1.616 |
stal | -1.579 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.58e+00 |
Pos logit contributions | |
Slave | +1.643 |
atts | +1.608 |
Grande | +1.567 |
Warehouse | +1.550 |
Labrador | +1.538 |
Neg logit contributions | |
stroke | -1.442 |
edIn | -1.341 |
sense | -1.312 |
Abstract | -1.310 |
stal | -1.277 |
Token | A |
Token ID | 32 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
stroke | +6.285 |
Abstract | +6.284 |
sense | +5.802 |
edIn | +5.658 |
stal | +5.505 |
Neg logit contributions | |
Slave | -7.324 |
atts | -7.166 |
Grande | -7.050 |
Warehouse | -7.043 |
Labrador | -7.040 |
Token | university |
Token ID | 6403 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
stroke | +1.892 |
Abstract | +1.770 |
edIn | +1.753 |
sense | +1.748 |
stal | +1.719 |
Neg logit contributions | |
atts | -1.415 |
Slave | -1.398 |
Grande | -1.339 |
oven | -1.333 |
Warehouse | -1.314 |
Token | offered |
Token ID | 4438 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
stroke | +2.213 |
edIn | +2.065 |
Abstract | +2.060 |
sense | +2.033 |
stal | +1.960 |
Neg logit contributions | |
atts | -2.087 |
Slave | -2.057 |
oven | -1.989 |
Grande | -1.957 |
Warehouse | -1.935 |
Token | counselling |
Token ID | 47586 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
stroke | +1.352 |
Abstract | +1.256 |
edIn | +1.248 |
sense | +1.231 |
stal | +1.198 |
Neg logit contributions | |
atts | -1.197 |
Slave | -1.183 |
oven | -1.136 |
Grande | -1.128 |
Warehouse | -1.117 |
Token | to |
Token ID | 284 |
Feature activation | +6.93e-03 |
Pos logit contributions | |
Slave | +0.008 |
atts | +0.008 |
oven | +0.007 |
Grande | +0.007 |
Warehouse | +0.007 |
Neg logit contributions | |
stroke | -0.009 |
Abstract | -0.008 |
sense | -0.008 |
edIn | -0.008 |
stal | -0.008 |
Token | I |
Token ID | 314 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
Slave | +0.274 |
atts | +0.273 |
Grande | +0.263 |
oven | +0.259 |
Labrador | +0.258 |
Neg logit contributions | |
stroke | -0.294 |
edIn | -0.274 |
Abstract | -0.273 |
sense | -0.270 |
stal | -0.263 |
Token | own |
Token ID | 898 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
stroke | +0.573 |
Abstract | +0.529 |
edIn | +0.525 |
sense | +0.522 |
stal | +0.509 |
Neg logit contributions | |
atts | -0.636 |
Slave | -0.633 |
Grande | -0.611 |
oven | -0.610 |
Warehouse | -0.604 |
Token | some |
Token ID | 617 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
stroke | +1.075 |
Abstract | +1.007 |
edIn | +0.996 |
sense | +0.990 |
stal | +0.965 |
Neg logit contributions | |
atts | -0.966 |
Slave | -0.961 |
oven | -0.928 |
Grande | -0.923 |
Warehouse | -0.912 |
Token | bitcoins |
Token ID | 22690 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Slave | +1.051 |
atts | +1.050 |
Grande | +1.005 |
oven | +0.993 |
Warehouse | +0.987 |
Neg logit contributions | |
stroke | -1.324 |
Abstract | -1.237 |
edIn | -1.236 |
sense | -1.224 |
stal | -1.190 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Slave | +0.339 |
atts | +0.338 |
Grande | +0.325 |
oven | +0.321 |
Warehouse | +0.319 |
Neg logit contributions | |
stroke | -0.389 |
edIn | -0.363 |
Abstract | -0.363 |
sense | -0.359 |
stal | -0.349 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.57e+00 |
Pos logit contributions | |
stroke | +0.136 |
edIn | +0.127 |
Abstract | +0.126 |
sense | +0.125 |
stal | +0.121 |
Neg logit contributions | |
Slave | -0.135 |
atts | -0.133 |
Grande | -0.129 |
Labrador | -0.127 |
Warehouse | -0.127 |
Token | Their |
Token ID | 14574 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Abstract | +6.295 |
stroke | +6.283 |
sense | +5.802 |
edIn | +5.660 |
stal | +5.504 |
Neg logit contributions | |
Slave | -7.305 |
atts | -7.155 |
Grande | -7.041 |
Warehouse | -7.037 |
Labrador | -7.028 |
Token | solution |
Token ID | 4610 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
atts | +0.222 |
Slave | +0.221 |
Grande | +0.212 |
oven | +0.209 |
Warehouse | +0.208 |
Neg logit contributions | |
stroke | -0.278 |
Abstract | -0.260 |
edIn | -0.260 |
sense | -0.257 |
stal | -0.250 |
Token | involves |
Token ID | 9018 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
stroke | +1.713 |
Abstract | +1.579 |
edIn | +1.549 |
sense | +1.548 |
stal | +1.505 |
Neg logit contributions | |
atts | -1.768 |
Slave | -1.765 |
Grande | -1.698 |
oven | -1.684 |
Warehouse | -1.667 |
Token | encaps |
Token ID | 32652 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
stroke | +0.567 |
Abstract | +0.529 |
edIn | +0.525 |
sense | +0.519 |
stal | +0.503 |
Neg logit contributions | |
atts | -0.522 |
Slave | -0.519 |
Grande | -0.499 |
oven | -0.496 |
Warehouse | -0.492 |
Token | ulating |
Token ID | 8306 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
stroke | +0.363 |
Abstract | +0.340 |
edIn | +0.338 |
sense | +0.336 |
stal | +0.329 |
Neg logit contributions | |
Slave | -0.320 |
atts | -0.319 |
Grande | -0.307 |
Warehouse | -0.301 |
oven | -0.300 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
atts | +0.002 |
Slave | +0.002 |
oven | +0.002 |
Grande | +0.002 |
enslaved | +0.002 |
Neg logit contributions | |
stroke | -0.002 |
Abstract | -0.002 |
sense | -0.002 |
edIn | -0.002 |
stal | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
Slave | +0.166 |
atts | +0.165 |
Grande | +0.159 |
oven | +0.158 |
Warehouse | +0.157 |
Neg logit contributions | |
stroke | -0.151 |
Abstract | -0.139 |
edIn | -0.139 |
sense | -0.137 |
stal | -0.133 |
Token | * |
Token ID | 9 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
Slave | +0.232 |
atts | +0.231 |
Grande | +0.224 |
oven | +0.221 |
Warehouse | +0.221 |
Neg logit contributions | |
stroke | -0.178 |
Abstract | -0.164 |
edIn | -0.163 |
sense | -0.161 |
stal | -0.155 |
Token | * |
Token ID | 1635 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
stroke | +0.305 |
Abstract | +0.282 |
edIn | +0.279 |
sense | +0.277 |
stal | +0.267 |
Neg logit contributions | |
Slave | -0.360 |
atts | -0.359 |
Grande | -0.347 |
oven | -0.343 |
Warehouse | -0.342 |
Token | * |
Token ID | 1635 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Slave | +1.091 |
atts | +1.085 |
Grande | +1.053 |
oven | +1.039 |
Labrador | +1.037 |
Neg logit contributions | |
stroke | -0.887 |
edIn | -0.821 |
Abstract | -0.813 |
sense | -0.804 |
stal | -0.778 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.56e+00 |
Pos logit contributions | |
Slave | +1.475 |
atts | +1.452 |
Grande | +1.424 |
Labrador | +1.404 |
Warehouse | +1.393 |
Neg logit contributions | |
stroke | -1.471 |
edIn | -1.365 |
Abstract | -1.349 |
sense | -1.338 |
stal | -1.311 |
Token | Despite |
Token ID | 8332 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Abstract | +6.287 |
stroke | +6.287 |
sense | +5.817 |
edIn | +5.680 |
stal | +5.521 |
Neg logit contributions | |
Slave | -7.251 |
atts | -7.116 |
Grande | -6.990 |
Warehouse | -6.973 |
Labrador | -6.961 |
Token | being |
Token ID | 852 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
stroke | +1.267 |
Abstract | +1.177 |
edIn | +1.177 |
sense | +1.160 |
stal | +1.134 |
Neg logit contributions | |
atts | -1.194 |
Slave | -1.185 |
Grande | -1.138 |
oven | -1.137 |
Warehouse | -1.120 |
Token | slightly |
Token ID | 4622 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
stroke | +1.152 |
Abstract | +1.082 |
edIn | +1.065 |
sense | +1.053 |
stal | +1.033 |
Neg logit contributions | |
atts | -0.967 |
Slave | -0.958 |
Grande | -0.919 |
oven | -0.919 |
Warehouse | -0.908 |
Token | broken |
Token ID | 5445 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
stroke | +1.314 |
Abstract | +1.234 |
edIn | +1.209 |
sense | +1.194 |
stal | +1.175 |
Neg logit contributions | |
atts | -1.076 |
Slave | -1.067 |
oven | -1.027 |
Grande | -1.019 |
Warehouse | -1.012 |
Token | on |
Token ID | 319 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
stroke | +1.896 |
edIn | +1.750 |
sense | +1.743 |
Abstract | +1.742 |
stal | +1.684 |
Neg logit contributions | |
atts | -1.860 |
Slave | -1.843 |
Grande | -1.772 |
oven | -1.762 |
Warehouse | -1.742 |
Token | ) |
Token ID | 8 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
stroke | +0.503 |
edIn | +0.469 |
Abstract | +0.466 |
sense | +0.463 |
stal | +0.450 |
Neg logit contributions | |
atts | -0.389 |
Slave | -0.386 |
Grande | -0.371 |
Labrador | -0.366 |
oven | -0.364 |
Token |
|
Token ID | 198 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
stroke | +0.607 |
Abstract | +0.562 |
edIn | +0.562 |
sense | +0.555 |
stal | +0.538 |
Neg logit contributions | |
Slave | -0.647 |
atts | -0.646 |
Grande | -0.623 |
oven | -0.615 |
Labrador | -0.613 |
Token |
|
Token ID | 198 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Slave | +0.319 |
atts | +0.318 |
Grande | +0.307 |
oven | +0.303 |
Warehouse | +0.302 |
Neg logit contributions | |
stroke | -0.293 |
edIn | -0.271 |
Abstract | -0.270 |
sense | -0.267 |
stal | -0.259 |
Token | Order |
Token ID | 18743 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Slave | +0.288 |
atts | +0.287 |
Grande | +0.277 |
oven | +0.274 |
Warehouse | +0.273 |
Neg logit contributions | |
stroke | -0.246 |
edIn | -0.226 |
Abstract | -0.226 |
sense | -0.223 |
stal | -0.216 |
Token | Now |
Token ID | 2735 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Slave | +0.975 |
atts | +0.971 |
Grande | +0.934 |
oven | +0.921 |
Warehouse | +0.917 |
Neg logit contributions | |
stroke | -1.121 |
edIn | -1.045 |
Abstract | -1.044 |
sense | -1.033 |
stal | -1.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.55e+00 |
Pos logit contributions | |
atts | +0.188 |
Slave | +0.188 |
Grande | +0.181 |
oven | +0.179 |
Labrador | +0.178 |
Neg logit contributions | |
stroke | -0.191 |
Abstract | -0.177 |
edIn | -0.177 |
sense | -0.175 |
stal | -0.170 |
Token | After |
Token ID | 3260 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Abstract | +6.260 |
stroke | +6.254 |
sense | +5.778 |
edIn | +5.645 |
stal | +5.486 |
Neg logit contributions | |
Slave | -7.278 |
atts | -7.147 |
Grande | -7.014 |
Warehouse | -7.007 |
Labrador | -7.002 |
Token | much |
Token ID | 881 |
Feature activation | -9.90e-03 |
Pos logit contributions | |
stroke | +0.242 |
Abstract | +0.225 |
edIn | +0.225 |
sense | +0.222 |
stal | +0.217 |
Neg logit contributions | |
atts | -0.216 |
Slave | -0.216 |
Grande | -0.207 |
oven | -0.205 |
Warehouse | -0.203 |
Token | talk |
Token ID | 1561 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
stroke | +0.007 |
Abstract | +0.007 |
edIn | +0.007 |
sense | +0.007 |
stal | +0.006 |
Neg logit contributions | |
Slave | -0.007 |
atts | -0.007 |
Grande | -0.007 |
oven | -0.007 |
Warehouse | -0.007 |
Token | about |
Token ID | 546 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
stroke | +2.048 |
Abstract | +1.901 |
edIn | +1.888 |
sense | +1.887 |
stal | +1.831 |
Neg logit contributions | |
atts | -1.747 |
Slave | -1.741 |
Grande | -1.675 |
oven | -1.648 |
Warehouse | -1.646 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
stroke | +0.374 |
edIn | +0.348 |
Abstract | +0.347 |
sense | +0.343 |
stal | +0.333 |
Neg logit contributions | |
atts | -0.347 |
Slave | -0.345 |
Grande | -0.332 |
oven | -0.330 |
Labrador | -0.326 |
Token | you |
Token ID | 345 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
stroke | +1.585 |
edIn | +1.462 |
Abstract | +1.461 |
sense | +1.450 |
stal | +1.407 |
Neg logit contributions | |
atts | -1.692 |
Slave | -1.675 |
oven | -1.610 |
Grande | -1.604 |
Warehouse | -1.595 |
Token | to |
Token ID | 284 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
stroke | +0.523 |
Abstract | +0.487 |
edIn | +0.486 |
sense | +0.481 |
stal | +0.469 |
Neg logit contributions | |
Slave | -0.454 |
atts | -0.452 |
Grande | -0.433 |
oven | -0.429 |
Warehouse | -0.427 |
Token | vote |
Token ID | 3015 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
stroke | +0.355 |
Abstract | +0.326 |
sense | +0.324 |
edIn | +0.323 |
stal | +0.315 |
Neg logit contributions | |
atts | -0.305 |
Slave | -0.301 |
oven | -0.291 |
Grande | -0.288 |
Warehouse | -0.287 |
Token | accordingly |
Token ID | 16062 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Slave | +0.903 |
atts | +0.898 |
Grande | +0.864 |
oven | +0.848 |
Labrador | +0.846 |
Neg logit contributions | |
stroke | -1.178 |
edIn | -1.103 |
Abstract | -1.103 |
sense | -1.091 |
stal | -1.062 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Slave | +1.768 |
atts | +1.757 |
Grande | +1.704 |
oven | +1.661 |
Labrador | +1.658 |
Neg logit contributions | |
stroke | -2.214 |
edIn | -2.082 |
Abstract | -2.071 |
sense | -2.045 |
stal | -1.986 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.54e+00 |
Pos logit contributions | |
atts | +0.164 |
Slave | +0.163 |
Grande | +0.156 |
oven | +0.156 |
Warehouse | +0.155 |
Neg logit contributions | |
stroke | -0.153 |
Abstract | -0.141 |
edIn | -0.141 |
sense | -0.140 |
stal | -0.135 |
Token | Story |
Token ID | 11605 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Abstract | +6.269 |
stroke | +6.267 |
sense | +5.794 |
edIn | +5.654 |
stal | +5.496 |
Neg logit contributions | |
Slave | -7.271 |
atts | -7.112 |
Grande | -7.005 |
Warehouse | -6.993 |
Labrador | -6.983 |
Token | highlights |
Token ID | 11330 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
stroke | +0.813 |
Abstract | +0.756 |
sense | +0.743 |
edIn | +0.743 |
stal | +0.728 |
Neg logit contributions | |
atts | -1.002 |
Slave | -0.995 |
oven | -0.965 |
Grande | -0.963 |
Warehouse | -0.953 |
Token | Police |
Token ID | 4287 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
stroke | +3.505 |
Abstract | +3.303 |
sense | +3.247 |
edIn | +3.232 |
stal | +3.164 |
Neg logit contributions | |
atts | -2.812 |
oven | -2.655 |
Slave | -2.623 |
enslaved | -2.568 |
Grande | -2.519 |
Token | chief |
Token ID | 4039 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
stroke | +2.887 |
Abstract | +2.648 |
sense | +2.599 |
stal | +2.589 |
edIn | +2.555 |
Neg logit contributions | |
atts | -2.573 |
oven | -2.533 |
Slave | -2.517 |
Grande | -2.412 |
Warehouse | -2.378 |
Token | vows |
Token ID | 36605 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
stroke | +3.197 |
Abstract | +2.951 |
sense | +2.882 |
edIn | +2.861 |
stal | +2.860 |
Neg logit contributions | |
atts | -2.952 |
Slave | -2.933 |
oven | -2.893 |
Grande | -2.767 |
Warehouse | -2.765 |
Token | various |
Token ID | 2972 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
stroke | +1.330 |
Abstract | +1.244 |
edIn | +1.239 |
sense | +1.217 |
stal | +1.185 |
Neg logit contributions | |
atts | -1.255 |
Slave | -1.229 |
oven | -1.190 |
Grande | -1.180 |
Warehouse | -1.166 |
Token | malicious |
Token ID | 17412 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
stroke | +1.700 |
edIn | +1.584 |
Abstract | +1.578 |
sense | +1.559 |
stal | +1.507 |
Neg logit contributions | |
atts | -1.579 |
Slave | -1.526 |
Grande | -1.468 |
oven | -1.467 |
Warehouse | -1.451 |
Token | threat |
Token ID | 2372 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
atts | +0.551 |
Slave | +0.548 |
Grande | +0.525 |
oven | +0.519 |
Warehouse | +0.515 |
Neg logit contributions | |
stroke | -0.678 |
Abstract | -0.632 |
edIn | -0.632 |
sense | -0.626 |
stal | -0.609 |
Token | actors |
Token ID | 10544 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
stroke | +1.224 |
Abstract | +1.155 |
edIn | +1.149 |
sense | +1.149 |
stal | +1.126 |
Neg logit contributions | |
Slave | -0.479 |
atts | -0.472 |
Grande | -0.442 |
oven | -0.435 |
Warehouse | -0.431 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
stroke | +0.255 |
Abstract | +0.238 |
edIn | +0.236 |
sense | +0.235 |
stal | +0.229 |
Neg logit contributions | |
Slave | -0.228 |
atts | -0.228 |
Grande | -0.219 |
oven | -0.217 |
Warehouse | -0.216 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.53e+00 |
Pos logit contributions | |
stroke | +0.157 |
Abstract | +0.147 |
edIn | +0.146 |
sense | +0.145 |
stal | +0.140 |
Neg logit contributions | |
atts | -0.157 |
Slave | -0.155 |
Grande | -0.149 |
oven | -0.148 |
Labrador | -0.147 |
Token | An |
Token ID | 2025 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
stroke | +6.275 |
Abstract | +6.267 |
sense | +5.796 |
edIn | +5.658 |
stal | +5.505 |
Neg logit contributions | |
Slave | -7.261 |
atts | -7.095 |
Warehouse | -7.003 |
Grande | -6.997 |
Labrador | -6.993 |
Token | actor |
Token ID | 8674 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
stroke | +2.024 |
Abstract | +1.933 |
edIn | +1.897 |
sense | +1.857 |
stal | +1.829 |
Neg logit contributions | |
Slave | -1.433 |
atts | -1.421 |
Grande | -1.367 |
oven | -1.341 |
Labrador | -1.336 |
Token | in |
Token ID | 287 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
stroke | +0.270 |
Abstract | +0.252 |
sense | +0.247 |
edIn | +0.247 |
stal | +0.240 |
Neg logit contributions | |
Slave | -0.254 |
atts | -0.254 |
oven | -0.243 |
Grande | -0.243 |
Warehouse | -0.239 |
Token | the |
Token ID | 262 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
stroke | +0.347 |
Abstract | +0.324 |
edIn | +0.324 |
sense | +0.321 |
stal | +0.313 |
Neg logit contributions | |
atts | -0.283 |
Slave | -0.282 |
Grande | -0.270 |
oven | -0.268 |
Labrador | -0.265 |
Token | upcoming |
Token ID | 7865 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
stroke | +0.677 |
edIn | +0.634 |
Abstract | +0.633 |
sense | +0.630 |
stal | +0.612 |
Neg logit contributions | |
atts | -0.484 |
Slave | -0.475 |
Grande | -0.456 |
oven | -0.455 |
Labrador | -0.448 |
Token | possible |
Token ID | 1744 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
Slave | +0.898 |
atts | +0.894 |
Grande | +0.859 |
oven | +0.846 |
Labrador | +0.842 |
Neg logit contributions | |
stroke | -1.130 |
edIn | -1.057 |
Abstract | -1.056 |
sense | -1.045 |
stal | -1.017 |
Token | option |
Token ID | 3038 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
stroke | +3.126 |
sense | +2.831 |
Abstract | +2.824 |
edIn | +2.799 |
stal | +2.752 |
Neg logit contributions | |
atts | -3.146 |
Slave | -3.059 |
oven | -2.977 |
Grande | -2.903 |
enslaved | -2.874 |
Token | among |
Token ID | 1871 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
stroke | +0.755 |
Abstract | +0.701 |
edIn | +0.694 |
sense | +0.691 |
stal | +0.673 |
Neg logit contributions | |
Slave | -0.709 |
atts | -0.708 |
Grande | -0.675 |
oven | -0.675 |
Warehouse | -0.669 |
Token | many |
Token ID | 867 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
stroke | +1.303 |
Abstract | +1.214 |
edIn | +1.209 |
sense | +1.201 |
stal | +1.168 |
Neg logit contributions | |
atts | -1.219 |
Slave | -1.212 |
Grande | -1.161 |
oven | -1.153 |
Warehouse | -1.146 |
Token | . |
Token ID | 13 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
stroke | +1.429 |
Abstract | +1.324 |
sense | +1.308 |
edIn | +1.302 |
stal | +1.274 |
Neg logit contributions | |
atts | -1.372 |
Slave | -1.362 |
oven | -1.295 |
Grande | -1.293 |
Warehouse | -1.286 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.53e+00 |
Pos logit contributions | |
stroke | +0.436 |
Abstract | +0.406 |
edIn | +0.403 |
sense | +0.400 |
stal | +0.386 |
Neg logit contributions | |
atts | -0.459 |
Slave | -0.450 |
oven | -0.435 |
Grande | -0.433 |
enslaved | -0.428 |
Token | B |
Token ID | 33 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
stroke | +6.278 |
Abstract | +6.262 |
sense | +5.800 |
edIn | +5.664 |
stal | +5.514 |
Neg logit contributions | |
Slave | -7.239 |
atts | -7.078 |
Grande | -6.967 |
Warehouse | -6.966 |
Labrador | -6.949 |
Token | ud |
Token ID | 463 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
stroke | +0.070 |
Abstract | +0.065 |
edIn | +0.065 |
sense | +0.064 |
stal | +0.062 |
Neg logit contributions | |
Slave | -0.069 |
atts | -0.068 |
Grande | -0.066 |
Labrador | -0.065 |
Warehouse | -0.065 |
Token | we |
Token ID | 732 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
stroke | +0.207 |
Abstract | +0.192 |
edIn | +0.192 |
sense | +0.192 |
stal | +0.185 |
Neg logit contributions | |
Slave | -0.164 |
atts | -0.163 |
Grande | -0.156 |
oven | -0.155 |
Warehouse | -0.154 |
Token | iser |
Token ID | 5847 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Slave | +0.008 |
atts | +0.008 |
Grande | +0.007 |
Labrador | +0.007 |
oven | +0.006 |
Neg logit contributions | |
stroke | -0.071 |
edIn | -0.068 |
Abstract | -0.068 |
sense | -0.068 |
stal | -0.067 |
Token | Cly |
Token ID | 29133 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Slave | +0.756 |
atts | +0.755 |
Grande | +0.725 |
oven | +0.716 |
Labrador | +0.712 |
Neg logit contributions | |
stroke | -0.837 |
edIn | -0.778 |
Abstract | -0.778 |
sense | -0.770 |
stal | -0.748 |
Token | that |
Token ID | 326 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Slave | +1.391 |
atts | +1.388 |
Grande | +1.331 |
oven | +1.303 |
Labrador | +1.302 |
Neg logit contributions | |
stroke | -2.036 |
edIn | -1.937 |
Abstract | -1.923 |
sense | -1.906 |
stal | -1.852 |
Token | matters |
Token ID | 6067 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
stroke | +0.270 |
Abstract | +0.249 |
edIn | +0.249 |
sense | +0.246 |
stal | +0.239 |
Neg logit contributions | |
Slave | -0.279 |
atts | -0.278 |
Grande | -0.268 |
oven | -0.267 |
Warehouse | -0.265 |
Token | to |
Token ID | 284 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
stroke | +1.272 |
Abstract | +1.170 |
edIn | +1.168 |
sense | +1.163 |
stal | +1.135 |
Neg logit contributions | |
Slave | -1.161 |
atts | -1.157 |
Grande | -1.108 |
Warehouse | -1.106 |
oven | -1.106 |
Token | others |
Token ID | 1854 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
stroke | +0.614 |
Abstract | +0.568 |
edIn | +0.568 |
sense | +0.565 |
stal | +0.545 |
Neg logit contributions | |
atts | -0.621 |
Slave | -0.620 |
Grande | -0.594 |
oven | -0.593 |
Warehouse | -0.592 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Slave | +0.826 |
atts | +0.824 |
Grande | +0.794 |
oven | +0.779 |
Labrador | +0.778 |
Neg logit contributions | |
stroke | -1.004 |
edIn | -0.944 |
Abstract | -0.939 |
sense | -0.928 |
stal | -0.901 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.52e+00 |
Pos logit contributions | |
atts | +0.089 |
Slave | +0.087 |
oven | +0.085 |
Grande | +0.084 |
enslaved | +0.083 |
Neg logit contributions | |
stroke | -0.087 |
Abstract | -0.081 |
edIn | -0.080 |
sense | -0.080 |
stal | -0.077 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Abstract | +6.239 |
stroke | +6.239 |
sense | +5.770 |
edIn | +5.618 |
stal | +5.471 |
Neg logit contributions | |
Slave | -7.284 |
atts | -7.122 |
Warehouse | -7.016 |
Grande | -7.015 |
Labrador | -6.998 |
Token | � |
Token ID | 447 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Slave | +0.965 |
atts | +0.958 |
Grande | +0.929 |
oven | +0.915 |
Labrador | +0.913 |
Neg logit contributions | |
stroke | -0.841 |
edIn | -0.780 |
Abstract | -0.773 |
sense | -0.766 |
stal | -0.739 |
Token | � |
Token ID | 247 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
stroke | +1.288 |
edIn | +1.196 |
Abstract | +1.188 |
sense | +1.173 |
stal | +1.141 |
Neg logit contributions | |
atts | -1.515 |
Slave | -1.504 |
Grande | -1.457 |
oven | -1.452 |
Warehouse | -1.444 |
Token | s |
Token ID | 82 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Slave | +0.059 |
atts | +0.059 |
Grande | +0.056 |
oven | +0.056 |
Warehouse | +0.056 |
Neg logit contributions | |
stroke | -0.053 |
Abstract | -0.049 |
edIn | -0.049 |
sense | -0.048 |
stal | -0.047 |
Token | face |
Token ID | 1986 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
stroke | +0.220 |
Abstract | +0.204 |
edIn | +0.202 |
sense | +0.202 |
stal | +0.196 |
Neg logit contributions | |
atts | -0.202 |
Slave | -0.201 |
Grande | -0.194 |
oven | -0.192 |
Labrador | -0.191 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
stroke | +0.086 |
Abstract | +0.080 |
edIn | +0.079 |
sense | +0.079 |
stal | +0.076 |
Neg logit contributions | |
atts | -0.099 |
Slave | -0.099 |
Grande | -0.095 |
oven | -0.094 |
Warehouse | -0.094 |
Token | References |
Token ID | 19927 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
stroke | +0.081 |
Abstract | +0.075 |
edIn | +0.075 |
sense | +0.074 |
stal | +0.072 |
Neg logit contributions | |
Slave | -0.075 |
atts | -0.075 |
Grande | -0.072 |
oven | -0.071 |
Warehouse | -0.071 |
Token | [ |
Token ID | 685 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
stroke | +0.284 |
edIn | +0.262 |
Abstract | +0.261 |
sense | +0.259 |
stal | +0.250 |
Neg logit contributions | |
Slave | -0.321 |
atts | -0.320 |
Grande | -0.310 |
oven | -0.306 |
Labrador | -0.305 |
Token | edit |
Token ID | 4370 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
stroke | +0.692 |
Abstract | +0.629 |
sense | +0.619 |
edIn | +0.615 |
stal | +0.596 |
Neg logit contributions | |
Slave | -1.003 |
atts | -1.000 |
Grande | -0.970 |
Warehouse | -0.960 |
Labrador | -0.956 |
Token | ] |
Token ID | 2361 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
stroke | +0.128 |
Abstract | +0.117 |
edIn | +0.116 |
sense | +0.115 |
stal | +0.111 |
Neg logit contributions | |
Slave | -0.178 |
atts | -0.178 |
Grande | -0.172 |
oven | -0.170 |
Warehouse | -0.170 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.50e+00 |
Pos logit contributions | |
stroke | +0.735 |
edIn | +0.681 |
Abstract | +0.672 |
sense | +0.666 |
stal | +0.645 |
Neg logit contributions | |
Slave | -0.839 |
atts | -0.832 |
Grande | -0.806 |
Labrador | -0.797 |
oven | -0.794 |
Token | Z |
Token ID | 57 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
stroke | +6.254 |
Abstract | +6.242 |
sense | +5.772 |
edIn | +5.622 |
stal | +5.467 |
Neg logit contributions | |
Slave | -7.251 |
atts | -7.098 |
Grande | -6.984 |
Warehouse | -6.981 |
Labrador | -6.974 |
Token | ombie |
Token ID | 9081 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
stroke | +2.996 |
Abstract | +2.813 |
edIn | +2.779 |
sense | +2.753 |
stal | +2.697 |
Neg logit contributions | |
Slave | -2.860 |
atts | -2.799 |
Grande | -2.718 |
Labrador | -2.696 |
enslaved | -2.687 |
Token | Deep |
Token ID | 10766 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Slave | +2.942 |
atts | +2.899 |
Grande | +2.797 |
Warehouse | +2.757 |
Labrador | +2.742 |
Neg logit contributions | |
stroke | -3.592 |
edIn | -3.373 |
Abstract | -3.357 |
sense | -3.302 |
stal | -3.243 |
Token | State |
Token ID | 1812 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Slave | +1.464 |
atts | +1.460 |
Grande | +1.403 |
oven | +1.383 |
Labrador | +1.377 |
Neg logit contributions | |
stroke | -1.711 |
edIn | -1.595 |
Abstract | -1.594 |
sense | -1.579 |
stal | -1.534 |
Token | Fog |
Token ID | 33381 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
atts | +0.872 |
Slave | +0.864 |
Grande | +0.833 |
oven | +0.827 |
Labrador | +0.817 |
Neg logit contributions | |
stroke | -0.977 |
Abstract | -0.909 |
edIn | -0.908 |
sense | -0.901 |
stal | -0.874 |
Token | are |
Token ID | 389 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
Slave | +1.040 |
atts | +1.036 |
Grande | +0.999 |
oven | +0.984 |
Labrador | +0.981 |
Neg logit contributions | |
stroke | -1.147 |
edIn | -1.069 |
Abstract | -1.067 |
sense | -1.056 |
stal | -1.027 |
Token | worth |
Token ID | 2861 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Slave | +0.544 |
atts | +0.543 |
Grande | +0.522 |
oven | +0.516 |
Warehouse | +0.514 |
Neg logit contributions | |
stroke | -0.583 |
Abstract | -0.541 |
edIn | -0.541 |
sense | -0.535 |
stal | -0.519 |
Token | 1000 |
Token ID | 8576 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
stroke | +1.219 |
edIn | +1.129 |
Abstract | +1.127 |
sense | +1.120 |
stal | +1.085 |
Neg logit contributions | |
Slave | -1.081 |
atts | -1.078 |
Grande | -1.034 |
oven | -1.022 |
Labrador | -1.020 |
Token | , |
Token ID | 11 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
Slave | +0.157 |
atts | +0.157 |
Grande | +0.151 |
oven | +0.149 |
Labrador | +0.148 |
Neg logit contributions | |
stroke | -0.157 |
edIn | -0.146 |
Abstract | -0.146 |
sense | -0.144 |
stal | -0.140 |
Token | 000 |
Token ID | 830 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
stroke | +0.550 |
Abstract | +0.513 |
edIn | +0.513 |
sense | +0.508 |
stal | +0.494 |
Neg logit contributions | |
Slave | -0.457 |
atts | -0.456 |
Grande | -0.437 |
oven | -0.432 |
Warehouse | -0.430 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.50e+00 |
Pos logit contributions | |
stroke | +0.233 |
Abstract | +0.216 |
edIn | +0.216 |
sense | +0.214 |
stal | +0.208 |
Neg logit contributions | |
Slave | -0.220 |
atts | -0.219 |
Grande | -0.211 |
oven | -0.208 |
Warehouse | -0.207 |
Token | T |
Token ID | 51 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
stroke | +6.285 |
Abstract | +6.263 |
sense | +5.799 |
edIn | +5.661 |
stal | +5.504 |
Neg logit contributions | |
Slave | -7.211 |
atts | -7.057 |
Grande | -6.957 |
Warehouse | -6.951 |
Labrador | -6.944 |
Token | oxic |
Token ID | 18047 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
stroke | +1.386 |
Abstract | +1.291 |
sense | +1.273 |
edIn | +1.267 |
stal | +1.236 |
Neg logit contributions | |
Slave | -1.421 |
atts | -1.391 |
Grande | -1.355 |
Labrador | -1.339 |
Warehouse | -1.331 |
Token | waste |
Token ID | 7030 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Slave | +0.457 |
atts | +0.456 |
Grande | +0.440 |
oven | +0.435 |
Warehouse | +0.431 |
Neg logit contributions | |
stroke | -0.541 |
Abstract | -0.504 |
edIn | -0.502 |
sense | -0.499 |
stal | -0.485 |
Token | water |
Token ID | 1660 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
atts | +0.370 |
Slave | +0.369 |
Grande | +0.353 |
oven | +0.351 |
Warehouse | +0.346 |
Neg logit contributions | |
stroke | -0.418 |
Abstract | -0.387 |
edIn | -0.385 |
sense | -0.383 |
stal | -0.375 |
Token | equal |
Token ID | 4961 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
stroke | +1.865 |
Abstract | +1.692 |
sense | +1.691 |
edIn | +1.667 |
stal | +1.644 |
Neg logit contributions | |
atts | -1.699 |
Slave | -1.695 |
Grande | -1.619 |
oven | -1.614 |
Warehouse | -1.581 |
Token | ! |
Token ID | 0 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
stroke | +1.508 |
Abstract | +1.388 |
sense | +1.379 |
edIn | +1.376 |
stal | +1.342 |
Neg logit contributions | |
Slave | -1.263 |
atts | -1.260 |
Grande | -1.205 |
oven | -1.186 |
Warehouse | -1.183 |
Token |
|
Token ID | 198 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
stroke | +1.549 |
Abstract | +1.432 |
edIn | +1.422 |
sense | +1.414 |
stal | +1.364 |
Neg logit contributions | |
atts | -1.794 |
Slave | -1.778 |
Grande | -1.709 |
oven | -1.706 |
Warehouse | -1.690 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
stroke | +0.046 |
Abstract | +0.043 |
edIn | +0.043 |
sense | +0.042 |
stal | +0.041 |
Neg logit contributions | |
Slave | -0.052 |
atts | -0.052 |
Grande | -0.050 |
oven | -0.049 |
Warehouse | -0.049 |
Token | Related |
Token ID | 9819 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Slave | +0.120 |
atts | +0.119 |
Grande | +0.115 |
oven | +0.114 |
Warehouse | +0.114 |
Neg logit contributions | |
stroke | -0.100 |
edIn | -0.092 |
Abstract | -0.092 |
sense | -0.091 |
stal | -0.088 |
Token | articles |
Token ID | 6685 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Slave | +0.890 |
atts | +0.888 |
Grande | +0.851 |
oven | +0.839 |
Warehouse | +0.834 |
Neg logit contributions | |
stroke | -1.165 |
Abstract | -1.089 |
edIn | -1.089 |
sense | -1.078 |
stal | -1.050 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.50e+00 |
Pos logit contributions | |
Slave | +0.847 |
atts | +0.843 |
Grande | +0.813 |
oven | +0.801 |
Labrador | +0.800 |
Neg logit contributions | |
stroke | -0.913 |
edIn | -0.852 |
Abstract | -0.847 |
sense | -0.840 |
stal | -0.814 |
Token | The |
Token ID | 464 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
stroke | +6.266 |
Abstract | +6.249 |
sense | +5.781 |
edIn | +5.646 |
stal | +5.501 |
Neg logit contributions | |
Slave | -7.209 |
atts | -7.070 |
Warehouse | -6.950 |
Grande | -6.946 |
Labrador | -6.921 |
Token | Russian |
Token ID | 3394 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
stroke | +0.819 |
Abstract | +0.771 |
edIn | +0.767 |
sense | +0.759 |
stal | +0.742 |
Neg logit contributions | |
atts | -0.609 |
Slave | -0.602 |
oven | -0.575 |
Grande | -0.575 |
Warehouse | -0.562 |
Token | came |
Token ID | 1625 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
stroke | +1.108 |
Abstract | +1.027 |
edIn | +1.021 |
sense | +1.016 |
stal | +0.992 |
Neg logit contributions | |
atts | -0.869 |
Slave | -0.846 |
oven | -0.819 |
Grande | -0.815 |
Labrador | -0.800 |
Token | over |
Token ID | 625 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Slave | +0.110 |
atts | +0.110 |
Grande | +0.105 |
oven | +0.104 |
Warehouse | +0.104 |
Neg logit contributions | |
stroke | -0.128 |
Abstract | -0.118 |
edIn | -0.118 |
sense | -0.118 |
stal | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Slave | +1.222 |
atts | +1.217 |
Grande | +1.171 |
oven | +1.152 |
Labrador | +1.149 |
Neg logit contributions | |
stroke | -1.441 |
edIn | -1.347 |
Abstract | -1.345 |
sense | -1.331 |
stal | -1.294 |
Token | reported |
Token ID | 2098 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
stroke | +0.421 |
Abstract | +0.394 |
edIn | +0.390 |
sense | +0.386 |
stal | +0.376 |
Neg logit contributions | |
Slave | -0.402 |
atts | -0.400 |
Grande | -0.382 |
oven | -0.380 |
Warehouse | -0.378 |
Token | as |
Token ID | 355 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Slave | +0.054 |
atts | +0.054 |
Grande | +0.052 |
oven | +0.051 |
Warehouse | +0.051 |
Neg logit contributions | |
stroke | -0.062 |
Abstract | -0.058 |
edIn | -0.058 |
sense | -0.057 |
stal | -0.056 |
Token | abstract |
Token ID | 12531 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
Slave | +0.199 |
atts | +0.198 |
Grande | +0.189 |
oven | +0.188 |
Warehouse | +0.188 |
Neg logit contributions | |
stroke | -0.209 |
Abstract | -0.194 |
edIn | -0.193 |
sense | -0.190 |
stal | -0.184 |
Token | s |
Token ID | 82 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
stroke | +2.661 |
Abstract | +2.458 |
edIn | +2.432 |
sense | +2.364 |
stal | +2.260 |
Neg logit contributions | |
Slave | -3.378 |
atts | -3.319 |
Grande | -3.219 |
oven | -3.206 |
Warehouse | -3.205 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
stroke | +0.453 |
Abstract | +0.426 |
edIn | +0.416 |
sense | +0.414 |
stal | +0.405 |
Neg logit contributions | |
Slave | -0.434 |
atts | -0.428 |
Grande | -0.411 |
Warehouse | -0.409 |
oven | -0.408 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.49e+00 |
Pos logit contributions | |
stroke | +0.865 |
Abstract | +0.814 |
edIn | +0.800 |
sense | +0.794 |
stal | +0.765 |
Neg logit contributions | |
atts | -0.799 |
Slave | -0.786 |
oven | -0.757 |
Grande | -0.752 |
enslaved | -0.747 |
Token | A |
Token ID | 32 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
stroke | +6.223 |
Abstract | +6.219 |
sense | +5.738 |
edIn | +5.602 |
stal | +5.438 |
Neg logit contributions | |
Slave | -7.298 |
atts | -7.116 |
Warehouse | -7.036 |
Grande | -7.020 |
Labrador | -7.018 |
Token | group |
Token ID | 1448 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
stroke | +1.848 |
Abstract | +1.728 |
edIn | +1.712 |
sense | +1.707 |
stal | +1.678 |
Neg logit contributions | |
atts | -1.388 |
Slave | -1.372 |
Grande | -1.314 |
oven | -1.308 |
Warehouse | -1.291 |
Token | of |
Token ID | 286 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
Slave | +0.536 |
atts | +0.535 |
Grande | +0.512 |
oven | +0.504 |
Warehouse | +0.502 |
Neg logit contributions | |
stroke | -0.720 |
Abstract | -0.675 |
edIn | -0.674 |
sense | -0.668 |
stal | -0.651 |
Token | Ottawa |
Token ID | 14074 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
stroke | +0.710 |
Abstract | +0.669 |
edIn | +0.663 |
sense | +0.654 |
stal | +0.643 |
Neg logit contributions | |
atts | -0.520 |
Slave | -0.513 |
oven | -0.491 |
Grande | -0.486 |
Warehouse | -0.477 |
Token | fitness |
Token ID | 13547 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
stroke | +3.382 |
Abstract | +3.168 |
edIn | +3.158 |
sense | +3.097 |
stal | +3.082 |
Neg logit contributions | |
atts | -2.693 |
Slave | -2.626 |
oven | -2.544 |
Grande | -2.502 |
Warehouse | -2.447 |
Token | rint |
Token ID | 22272 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
stroke | +0.196 |
Abstract | +0.179 |
edIn | +0.179 |
sense | +0.176 |
stal | +0.170 |
Neg logit contributions | |
Slave | -0.269 |
atts | -0.268 |
Grande | -0.261 |
oven | -0.257 |
Labrador | -0.257 |
Token | ed |
Token ID | 276 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Slave | +1.697 |
atts | +1.693 |
Grande | +1.651 |
oven | +1.636 |
Labrador | +1.631 |
Neg logit contributions | |
stroke | -0.673 |
edIn | -0.587 |
Abstract | -0.586 |
sense | -0.573 |
stal | -0.542 |
Token | with |
Token ID | 351 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Slave | +1.113 |
atts | +1.109 |
Grande | +1.064 |
oven | +1.049 |
Warehouse | +1.044 |
Neg logit contributions | |
stroke | -1.390 |
edIn | -1.299 |
Abstract | -1.298 |
sense | -1.285 |
stal | -1.250 |
Token | permission |
Token ID | 7170 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
stroke | +1.078 |
Abstract | +0.996 |
edIn | +0.996 |
sense | +0.990 |
stal | +0.968 |
Neg logit contributions | |
atts | -0.862 |
Slave | -0.858 |
Grande | -0.824 |
oven | -0.816 |
Warehouse | -0.811 |
Token | . |
Token ID | 13 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
stroke | +0.278 |
Abstract | +0.260 |
edIn | +0.257 |
sense | +0.255 |
stal | +0.248 |
Neg logit contributions | |
Slave | -0.250 |
atts | -0.248 |
Grande | -0.240 |
oven | -0.237 |
Labrador | -0.235 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.49e+00 |
Pos logit contributions | |
Slave | +0.673 |
atts | +0.672 |
Grande | +0.651 |
oven | +0.643 |
Labrador | +0.640 |
Neg logit contributions | |
stroke | -0.559 |
Abstract | -0.515 |
edIn | -0.512 |
sense | -0.507 |
stal | -0.490 |
Token | C |
Token ID | 34 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Abstract | +6.221 |
stroke | +6.219 |
sense | +5.740 |
edIn | +5.612 |
stal | +5.450 |
Neg logit contributions | |
Slave | -7.258 |
atts | -7.095 |
Warehouse | -6.985 |
Grande | -6.980 |
Labrador | -6.968 |
Token | ort |
Token ID | 419 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
stroke | +0.901 |
edIn | +0.835 |
Abstract | +0.834 |
sense | +0.829 |
stal | +0.804 |
Neg logit contributions | |
Slave | -0.898 |
atts | -0.887 |
Grande | -0.861 |
Labrador | -0.846 |
Warehouse | -0.845 |
Token | ic |
Token ID | 291 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Slave | +0.319 |
atts | +0.316 |
Grande | +0.305 |
Warehouse | +0.302 |
Labrador | +0.302 |
Neg logit contributions | |
stroke | -0.277 |
Abstract | -0.255 |
edIn | -0.253 |
sense | -0.251 |
stal | -0.244 |
Token | otrop |
Token ID | 34248 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
stroke | +1.173 |
Abstract | +1.099 |
edIn | +1.090 |
sense | +1.088 |
stal | +1.063 |
Neg logit contributions | |
Slave | -0.823 |
atts | -0.820 |
Grande | -0.785 |
Warehouse | -0.766 |
Labrador | -0.765 |
Token | in |
Token ID | 259 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
stroke | +1.342 |
Abstract | +1.229 |
edIn | +1.227 |
sense | +1.224 |
stal | +1.180 |
Neg logit contributions | |
Slave | -1.420 |
atts | -1.412 |
Grande | -1.366 |
Warehouse | -1.349 |
oven | -1.344 |
Token | an |
Token ID | 281 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
stroke | +0.698 |
Abstract | +0.651 |
edIn | +0.645 |
sense | +0.640 |
stal | +0.618 |
Neg logit contributions | |
atts | -0.666 |
Slave | -0.659 |
oven | -0.636 |
Grande | -0.635 |
Labrador | -0.625 |
Token | intro |
Token ID | 18951 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
stroke | +0.750 |
Abstract | +0.716 |
edIn | +0.706 |
sense | +0.693 |
stal | +0.674 |
Neg logit contributions | |
atts | -0.523 |
Slave | -0.518 |
Grande | -0.500 |
Labrador | -0.488 |
oven | -0.488 |
Token | vert |
Token ID | 1851 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
stroke | +2.538 |
Abstract | +2.364 |
sense | +2.325 |
edIn | +2.282 |
stal | +2.271 |
Neg logit contributions | |
atts | -2.027 |
Slave | -2.024 |
Grande | -1.923 |
oven | -1.907 |
Warehouse | -1.903 |
Token | online |
Token ID | 2691 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
stroke | +0.272 |
Abstract | +0.253 |
sense | +0.249 |
edIn | +0.248 |
stal | +0.241 |
Neg logit contributions | |
atts | -0.257 |
Slave | -0.256 |
Grande | -0.248 |
oven | -0.245 |
Warehouse | -0.242 |
Token | ? |
Token ID | 30 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
stroke | +1.181 |
Abstract | +1.095 |
sense | +1.083 |
edIn | +1.080 |
stal | +1.050 |
Neg logit contributions | |
atts | -1.237 |
Slave | -1.228 |
Grande | -1.189 |
oven | -1.176 |
Labrador | -1.165 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.48e+00 |
Pos logit contributions | |
stroke | +1.510 |
Abstract | +1.420 |
edIn | +1.392 |
sense | +1.391 |
stal | +1.342 |
Neg logit contributions | |
atts | -1.441 |
Slave | -1.407 |
oven | -1.369 |
Grande | -1.360 |
enslaved | -1.333 |
Token | Update |
Token ID | 10260 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
stroke | +6.249 |
Abstract | +6.244 |
sense | +5.766 |
edIn | +5.629 |
stal | +5.478 |
Neg logit contributions | |
Slave | -7.224 |
atts | -7.066 |
Grande | -6.960 |
Warehouse | -6.951 |
Labrador | -6.945 |
Token | : |
Token ID | 25 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
stroke | +0.252 |
Abstract | +0.235 |
edIn | +0.232 |
sense | +0.232 |
stal | +0.226 |
Neg logit contributions | |
atts | -0.228 |
Slave | -0.227 |
Grande | -0.217 |
oven | -0.217 |
Labrador | -0.215 |
Token | You |
Token ID | 921 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
stroke | +0.207 |
Abstract | +0.193 |
edIn | +0.191 |
sense | +0.190 |
stal | +0.185 |
Neg logit contributions | |
atts | -0.182 |
Slave | -0.179 |
Grande | -0.172 |
oven | -0.172 |
Labrador | -0.169 |
Token | can |
Token ID | 460 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
stroke | +0.228 |
Abstract | +0.209 |
sense | +0.207 |
edIn | +0.205 |
stal | +0.198 |
Neg logit contributions | |
atts | -0.296 |
Slave | -0.296 |
Grande | -0.286 |
oven | -0.285 |
Warehouse | -0.281 |
Token | find |
Token ID | 1064 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
stroke | +0.978 |
Abstract | +0.900 |
sense | +0.891 |
edIn | +0.882 |
stal | +0.877 |
Neg logit contributions | |
atts | -0.904 |
Slave | -0.901 |
Grande | -0.867 |
oven | -0.866 |
Warehouse | -0.850 |
Token | more |
Token ID | 517 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
stroke | +0.086 |
edIn | +0.080 |
Abstract | +0.079 |
sense | +0.079 |
stal | +0.077 |
Neg logit contributions | |
atts | -0.075 |
Slave | -0.075 |
Grande | -0.072 |
oven | -0.072 |
Warehouse | -0.071 |
Token | in |
Token ID | 287 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Slave | +0.356 |
atts | +0.355 |
Grande | +0.339 |
oven | +0.338 |
Warehouse | +0.335 |
Neg logit contributions | |
stroke | -0.423 |
Abstract | -0.393 |
edIn | -0.393 |
sense | -0.390 |
stal | -0.380 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Slave | +0.143 |
atts | +0.142 |
Grande | +0.136 |
oven | +0.136 |
Warehouse | +0.135 |
Neg logit contributions | |
stroke | -0.141 |
Abstract | -0.130 |
edIn | -0.130 |
sense | -0.128 |
stal | -0.125 |
Token | future |
Token ID | 2003 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
stroke | +0.080 |
Abstract | +0.075 |
edIn | +0.074 |
sense | +0.074 |
stal | +0.072 |
Neg logit contributions | |
atts | -0.067 |
Slave | -0.067 |
Grande | -0.064 |
oven | -0.064 |
Warehouse | -0.063 |
Token | ." |
Token ID | 526 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
stroke | +0.621 |
Abstract | +0.575 |
sense | +0.572 |
edIn | +0.572 |
stal | +0.558 |
Neg logit contributions | |
Slave | -0.529 |
atts | -0.529 |
Grande | -0.505 |
oven | -0.505 |
Warehouse | -0.500 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.45e+00 |
Pos logit contributions | |
stroke | +0.461 |
edIn | +0.429 |
Abstract | +0.427 |
sense | +0.422 |
stal | +0.409 |
Neg logit contributions | |
Slave | -0.499 |
atts | -0.497 |
Grande | -0.482 |
Labrador | -0.473 |
oven | -0.472 |
Token | M |
Token ID | 44 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
stroke | +6.215 |
Abstract | +6.204 |
sense | +5.730 |
edIn | +5.595 |
stal | +5.451 |
Neg logit contributions | |
Slave | -7.233 |
atts | -7.055 |
Warehouse | -6.964 |
Grande | -6.957 |
Labrador | -6.944 |
Token | urd |
Token ID | 2799 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
stroke | +0.239 |
Abstract | +0.221 |
edIn | +0.221 |
sense | +0.219 |
stal | +0.212 |
Neg logit contributions | |
Slave | -0.260 |
atts | -0.258 |
Grande | -0.250 |
Labrador | -0.246 |
Warehouse | -0.245 |
Token | erer |
Token ID | 11882 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
stroke | +0.843 |
edIn | +0.780 |
Abstract | +0.775 |
sense | +0.771 |
stal | +0.755 |
Neg logit contributions | |
Slave | -0.762 |
atts | -0.753 |
Grande | -0.735 |
Labrador | -0.720 |
Warehouse | -0.719 |
Token | identified |
Token ID | 5174 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Slave | +0.566 |
atts | +0.566 |
Grande | +0.543 |
oven | +0.537 |
Warehouse | +0.533 |
Neg logit contributions | |
stroke | -0.663 |
Abstract | -0.618 |
edIn | -0.617 |
sense | -0.610 |
stal | -0.594 |
Token | in |
Token ID | 287 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
stroke | +0.892 |
Abstract | +0.829 |
edIn | +0.826 |
sense | +0.815 |
stal | +0.796 |
Neg logit contributions | |
atts | -0.821 |
Slave | -0.815 |
oven | -0.782 |
Grande | -0.781 |
Warehouse | -0.768 |
Token | . |
Token ID | 13 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Slave | +0.376 |
atts | +0.376 |
Grande | +0.362 |
oven | +0.354 |
Labrador | +0.353 |
Neg logit contributions | |
stroke | -0.462 |
edIn | -0.433 |
Abstract | -0.430 |
sense | -0.426 |
stal | -0.416 |
Token | One |
Token ID | 3198 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Slave | +0.241 |
atts | +0.240 |
Grande | +0.231 |
oven | +0.228 |
Labrador | +0.226 |
Neg logit contributions | |
stroke | -0.263 |
edIn | -0.244 |
Abstract | -0.243 |
sense | -0.241 |
stal | -0.235 |
Token | to |
Token ID | 284 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Slave | +1.275 |
atts | +1.275 |
Grande | +1.230 |
Labrador | +1.199 |
Warehouse | +1.194 |
Neg logit contributions | |
stroke | -1.615 |
edIn | -1.517 |
Abstract | -1.516 |
sense | -1.506 |
stal | -1.448 |
Token | have |
Token ID | 423 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
atts | +0.129 |
Slave | +0.129 |
Grande | +0.124 |
oven | +0.123 |
Warehouse | +0.122 |
Neg logit contributions | |
stroke | -0.139 |
Abstract | -0.128 |
edIn | -0.127 |
sense | -0.126 |
stal | -0.124 |
Token | a |
Token ID | 257 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
atts | +1.254 |
Slave | +1.253 |
Grande | +1.196 |
oven | +1.190 |
Warehouse | +1.182 |
Neg logit contributions | |
stroke | -1.401 |
edIn | -1.302 |
Abstract | -1.300 |
sense | -1.285 |
stal | -1.251 |
Token | crappy |
Token ID | 40805 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
atts | +0.250 |
Slave | +0.247 |
oven | +0.236 |
Grande | +0.235 |
Warehouse | +0.233 |
Neg logit contributions | |
stroke | -0.275 |
Abstract | -0.255 |
edIn | -0.254 |
sense | -0.253 |
stal | -0.247 |
Token | script |
Token ID | 4226 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Slave | +4.079 |
atts | +4.021 |
Grande | +3.901 |
Labrador | +3.819 |
Warehouse | +3.818 |
Neg logit contributions | |
stroke | -5.097 |
Abstract | -4.775 |
edIn | -4.769 |
sense | -4.717 |
stal | -4.588 |
Token | and |
Token ID | 290 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
Slave | +1.497 |
atts | +1.492 |
Grande | +1.435 |
oven | +1.416 |
Warehouse | +1.410 |
Neg logit contributions | |
stroke | -1.705 |
Abstract | -1.584 |
edIn | -1.582 |
sense | -1.568 |
stal | -1.528 |
Token | performances |
Token ID | 13289 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
stroke | +0.299 |
Abstract | +0.277 |
edIn | +0.277 |
sense | +0.273 |
stal | +0.267 |
Neg logit contributions | |
atts | -0.271 |
Slave | -0.268 |
oven | -0.257 |
Grande | -0.256 |
Warehouse | -0.254 |
Token | because |
Token ID | 780 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
atts | +0.318 |
Slave | +0.318 |
Grande | +0.303 |
oven | +0.301 |
Warehouse | +0.300 |
Neg logit contributions | |
stroke | -0.378 |
Abstract | -0.351 |
edIn | -0.349 |
sense | -0.347 |
stal | -0.340 |
Token | they |
Token ID | 484 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
atts | +1.094 |
Slave | +1.093 |
Grande | +1.045 |
oven | +1.040 |
Warehouse | +1.031 |
Neg logit contributions | |
stroke | -1.281 |
edIn | -1.191 |
Abstract | -1.191 |
sense | -1.179 |
stal | -1.148 |
Token | I |
Token ID | 40 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
Slave | +0.281 |
atts | +0.280 |
Grande | +0.271 |
oven | +0.268 |
Warehouse | +0.267 |
Neg logit contributions | |
stroke | -0.212 |
Abstract | -0.195 |
edIn | -0.194 |
sense | -0.192 |
stal | -0.185 |
Token | represent |
Token ID | 2380 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
stroke | +0.264 |
Abstract | +0.243 |
sense | +0.242 |
edIn | +0.239 |
stal | +0.236 |
Neg logit contributions | |
Slave | -0.271 |
atts | -0.270 |
Grande | -0.260 |
Warehouse | -0.259 |
oven | -0.257 |
Token | Vermont |
Token ID | 16033 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Slave | +0.181 |
atts | +0.180 |
Grande | +0.173 |
oven | +0.172 |
Warehouse | +0.170 |
Neg logit contributions | |
stroke | -0.209 |
edIn | -0.195 |
Abstract | -0.195 |
sense | -0.193 |
stal | -0.188 |
Token | , |
Token ID | 11 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
stroke | +1.706 |
Abstract | +1.594 |
edIn | +1.578 |
sense | +1.572 |
stal | +1.543 |
Neg logit contributions | |
atts | -1.659 |
Slave | -1.649 |
Grande | -1.578 |
oven | -1.573 |
Warehouse | -1.546 |
Token | a |
Token ID | 257 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
Slave | +0.212 |
atts | +0.212 |
Grande | +0.204 |
oven | +0.202 |
Warehouse | +0.201 |
Neg logit contributions | |
stroke | -0.208 |
Abstract | -0.193 |
edIn | -0.193 |
sense | -0.190 |
stal | -0.184 |
Token | rural |
Token ID | 10016 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
stroke | +0.612 |
Abstract | +0.570 |
sense | +0.566 |
edIn | +0.565 |
stal | +0.553 |
Neg logit contributions | |
atts | -0.490 |
Slave | -0.486 |
oven | -0.465 |
Grande | -0.465 |
Warehouse | -0.454 |
Token | state |
Token ID | 1181 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
Slave | +3.169 |
atts | +3.117 |
Grande | +3.050 |
Labrador | +3.003 |
Warehouse | +2.977 |
Neg logit contributions | |
stroke | -4.592 |
edIn | -4.369 |
Abstract | -4.334 |
sense | -4.278 |
stal | -4.139 |
Token | where |
Token ID | 810 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
stroke | +0.051 |
Abstract | +0.047 |
edIn | +0.047 |
sense | +0.047 |
stal | +0.046 |
Neg logit contributions | |
atts | -0.045 |
Slave | -0.045 |
Grande | -0.043 |
oven | -0.042 |
Warehouse | -0.042 |
Token | many |
Token ID | 867 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
stroke | +0.403 |
Abstract | +0.374 |
edIn | +0.372 |
sense | +0.370 |
stal | +0.360 |
Neg logit contributions | |
atts | -0.353 |
Slave | -0.351 |
Grande | -0.337 |
oven | -0.336 |
Warehouse | -0.330 |
Token | workers |
Token ID | 3259 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
stroke | +1.264 |
Abstract | +1.176 |
edIn | +1.169 |
sense | +1.165 |
stal | +1.139 |
Neg logit contributions | |
atts | -0.941 |
Slave | -0.935 |
Grande | -0.888 |
oven | -0.887 |
Warehouse | -0.864 |
Token | drive |
Token ID | 3708 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Slave | +1.267 |
atts | +1.263 |
Grande | +1.216 |
oven | +1.199 |
Labrador | +1.194 |
Neg logit contributions | |
stroke | -1.374 |
edIn | -1.279 |
Abstract | -1.278 |
sense | -1.263 |
stal | -1.227 |
Token | . |
Token ID | 13 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Slave | +0.661 |
atts | +0.658 |
Grande | +0.632 |
oven | +0.623 |
Warehouse | +0.620 |
Neg logit contributions | |
stroke | -0.814 |
edIn | -0.759 |
Abstract | -0.759 |
sense | -0.752 |
stal | -0.732 |
Token | Fashion |
Token ID | 30958 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
atts | +0.179 |
Slave | +0.176 |
oven | +0.170 |
Grande | +0.169 |
enslaved | +0.167 |
Neg logit contributions | |
stroke | -0.186 |
Abstract | -0.173 |
edIn | -0.172 |
sense | -0.170 |
stal | -0.164 |
Token | ing |
Token ID | 278 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Slave | +1.502 |
atts | +1.494 |
Grande | +1.451 |
oven | +1.432 |
Warehouse | +1.432 |
Neg logit contributions | |
stroke | -1.105 |
Abstract | -1.010 |
edIn | -1.006 |
sense | -0.994 |
stal | -0.964 |
Token | the |
Token ID | 262 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Slave | +0.105 |
atts | +0.105 |
Grande | +0.101 |
oven | +0.101 |
Warehouse | +0.100 |
Neg logit contributions | |
stroke | -0.112 |
Abstract | -0.104 |
edIn | -0.104 |
sense | -0.103 |
stal | -0.099 |
Token | appropriate |
Token ID | 5035 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
atts | +0.327 |
Slave | +0.325 |
Grande | +0.311 |
oven | +0.310 |
Warehouse | +0.306 |
Neg logit contributions | |
stroke | -0.381 |
Abstract | -0.354 |
edIn | -0.352 |
sense | -0.350 |
stal | -0.339 |
Token | sentence |
Token ID | 6827 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
atts | +0.945 |
Slave | +0.945 |
Grande | +0.903 |
oven | +0.901 |
Warehouse | +0.892 |
Neg logit contributions | |
stroke | -1.027 |
edIn | -0.946 |
Abstract | -0.946 |
sense | -0.941 |
stal | -0.907 |
Token | in |
Token ID | 287 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Slave | +3.306 |
atts | +3.279 |
Grande | +3.189 |
Labrador | +3.155 |
oven | +3.103 |
Neg logit contributions | |
stroke | -3.735 |
edIn | -3.554 |
Abstract | -3.534 |
sense | -3.467 |
stal | -3.362 |
Token | each |
Token ID | 1123 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
stroke | +0.395 |
Abstract | +0.364 |
edIn | +0.363 |
sense | +0.359 |
stal | +0.347 |
Neg logit contributions | |
atts | -0.404 |
Slave | -0.404 |
Grande | -0.389 |
oven | -0.387 |
Warehouse | -0.383 |
Token | individual |
Token ID | 1981 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Slave | +2.502 |
atts | +2.456 |
Grande | +2.389 |
Labrador | +2.344 |
Warehouse | +2.330 |
Neg logit contributions | |
stroke | -3.031 |
Abstract | -2.868 |
edIn | -2.854 |
sense | -2.825 |
stal | -2.773 |
Token | case |
Token ID | 1339 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
stroke | +0.995 |
edIn | +0.920 |
Abstract | +0.917 |
sense | +0.910 |
stal | +0.879 |
Neg logit contributions | |
atts | -0.898 |
Slave | -0.893 |
Grande | -0.858 |
oven | -0.852 |
Warehouse | -0.845 |
Token | is |
Token ID | 318 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
Slave | +0.240 |
atts | +0.240 |
Grande | +0.231 |
oven | +0.228 |
Warehouse | +0.228 |
Neg logit contributions | |
stroke | -0.230 |
Abstract | -0.213 |
edIn | -0.213 |
sense | -0.210 |
stal | -0.204 |
Token | have |
Token ID | 423 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
stroke | +0.399 |
sense | +0.363 |
Abstract | +0.361 |
stal | +0.354 |
edIn | +0.351 |
Neg logit contributions | |
atts | -0.360 |
Slave | -0.358 |
Grande | -0.346 |
oven | -0.345 |
Warehouse | -0.342 |
Token | to |
Token ID | 284 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Slave | +1.026 |
atts | +1.024 |
Grande | +0.983 |
oven | +0.971 |
Warehouse | +0.966 |
Neg logit contributions | |
stroke | -1.203 |
edIn | -1.118 |
Abstract | -1.118 |
sense | -1.107 |
stal | -1.076 |
Token | get |
Token ID | 651 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Slave | +0.309 |
atts | +0.308 |
Grande | +0.298 |
oven | +0.295 |
Warehouse | +0.293 |
Neg logit contributions | |
stroke | -0.348 |
Abstract | -0.321 |
sense | -0.317 |
edIn | -0.315 |
stal | -0.308 |
Token | a |
Token ID | 257 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
stroke | +0.190 |
Abstract | +0.174 |
edIn | +0.172 |
sense | +0.171 |
stal | +0.166 |
Neg logit contributions | |
atts | -0.175 |
Slave | -0.174 |
Grande | -0.167 |
oven | -0.165 |
Warehouse | -0.165 |
Token | prost |
Token ID | 11825 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Slave | +0.954 |
atts | +0.951 |
Grande | +0.913 |
oven | +0.900 |
Warehouse | +0.896 |
Neg logit contributions | |
stroke | -1.167 |
edIn | -1.090 |
Abstract | -1.089 |
sense | -1.078 |
stal | -1.049 |
Token | hetic |
Token ID | 6587 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
Slave | +1.242 |
atts | +1.238 |
Grande | +1.203 |
oven | +1.192 |
Labrador | +1.187 |
Neg logit contributions | |
stroke | -0.747 |
edIn | -0.679 |
Abstract | -0.674 |
sense | -0.668 |
stal | -0.637 |
Token | penis |
Token ID | 16360 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
Slave | +3.350 |
atts | +3.261 |
Grande | +3.184 |
Labrador | +3.139 |
oven | +3.099 |
Neg logit contributions | |
stroke | -4.848 |
edIn | -4.673 |
Abstract | -4.643 |
sense | -4.596 |
stal | -4.437 |
Token | and |
Token ID | 290 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Slave | +2.204 |
atts | +2.189 |
Grande | +2.102 |
oven | +2.082 |
Labrador | +2.071 |
Neg logit contributions | |
stroke | -2.655 |
edIn | -2.525 |
Abstract | -2.504 |
sense | -2.475 |
stal | -2.392 |
Token | God |
Token ID | 1793 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
stroke | +0.137 |
Abstract | +0.125 |
sense | +0.124 |
edIn | +0.124 |
stal | +0.120 |
Neg logit contributions | |
atts | -0.129 |
Slave | -0.128 |
Grande | -0.123 |
oven | -0.122 |
Warehouse | -0.122 |
Token | help |
Token ID | 1037 |
Feature activation | -2.70e-03 |
Pos logit contributions | |
Slave | +2.523 |
atts | +2.509 |
Grande | +2.403 |
oven | +2.364 |
Warehouse | +2.350 |
Neg logit contributions | |
stroke | -3.493 |
edIn | -3.296 |
Abstract | -3.291 |
sense | -3.248 |
stal | -3.169 |
Token | me |
Token ID | 502 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
stroke | +0.002 |
edIn | +0.001 |
Abstract | +0.001 |
sense | +0.001 |
stal | +0.001 |
Neg logit contributions | |
Slave | -0.002 |
atts | -0.002 |
Grande | -0.002 |
oven | -0.002 |
Warehouse | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Slave | +0.108 |
atts | +0.108 |
Grande | +0.104 |
oven | +0.103 |
Warehouse | +0.102 |
Neg logit contributions | |
stroke | -0.096 |
Abstract | -0.089 |
edIn | -0.088 |
sense | -0.088 |
stal | -0.085 |
Token | Miami |
Token ID | 41191 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Slave | +0.137 |
atts | +0.137 |
Grande | +0.132 |
oven | +0.131 |
Warehouse | +0.130 |
Neg logit contributions | |
stroke | -0.116 |
Abstract | -0.107 |
edIn | -0.107 |
sense | -0.106 |
stal | -0.102 |
Token | Dolphins |
Token ID | 21668 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
Slave | +0.618 |
atts | +0.613 |
Grande | +0.573 |
oven | +0.551 |
Warehouse | +0.549 |
Neg logit contributions | |
stroke | -1.881 |
edIn | -1.793 |
Abstract | -1.791 |
sense | -1.778 |
stal | -1.741 |
Token | : |
Token ID | 25 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
Slave | +0.329 |
atts | +0.327 |
Grande | +0.316 |
Warehouse | +0.310 |
Labrador | +0.309 |
Neg logit contributions | |
stroke | -0.436 |
edIn | -0.407 |
Abstract | -0.405 |
sense | -0.403 |
stal | -0.388 |
Token | DE |
Token ID | 5550 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Slave | +0.489 |
atts | +0.487 |
Grande | +0.470 |
oven | +0.464 |
Warehouse | +0.462 |
Neg logit contributions | |
stroke | -0.484 |
edIn | -0.449 |
Abstract | -0.448 |
sense | -0.443 |
stal | -0.430 |
Token | Cameron |
Token ID | 10821 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
Slave | +0.784 |
atts | +0.771 |
Grande | +0.748 |
Labrador | +0.738 |
Warehouse | +0.736 |
Neg logit contributions | |
stroke | -0.946 |
edIn | -0.887 |
Abstract | -0.880 |
sense | -0.869 |
stal | -0.847 |
Token | Wake |
Token ID | 20441 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
Slave | +2.995 |
Grande | +2.854 |
atts | +2.828 |
Warehouse | +2.813 |
Labrador | +2.797 |
Neg logit contributions | |
stroke | -4.432 |
edIn | -4.282 |
Abstract | -4.185 |
sense | -4.166 |
stal | -4.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Slave | +3.711 |
atts | +3.699 |
Grande | +3.626 |
Labrador | +3.538 |
Warehouse | +3.508 |
Neg logit contributions | |
stroke | -4.054 |
Abstract | -3.843 |
edIn | -3.835 |
sense | -3.752 |
stal | -3.585 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Slave | +1.135 |
atts | +1.128 |
Grande | +1.093 |
oven | +1.076 |
Labrador | +1.074 |
Neg logit contributions | |
stroke | -1.090 |
edIn | -1.020 |
Abstract | -1.006 |
sense | -0.997 |
stal | -0.967 |
Token | Contract |
Token ID | 45845 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
atts | +1.051 |
Slave | +1.047 |
Grande | +1.010 |
oven | +1.004 |
Warehouse | +0.996 |
Neg logit contributions | |
stroke | -0.858 |
edIn | -0.785 |
sense | -0.770 |
Abstract | -0.768 |
stal | -0.751 |
Token | : |
Token ID | 25 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Slave | +1.165 |
atts | +1.159 |
Grande | +1.115 |
oven | +1.096 |
Warehouse | +1.093 |
Neg logit contributions | |
stroke | -1.401 |
edIn | -1.310 |
Abstract | -1.307 |
sense | -1.294 |
stal | -1.258 |
Token | and |
Token ID | 290 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
stroke | +0.208 |
Abstract | +0.193 |
edIn | +0.192 |
sense | +0.191 |
stal | +0.186 |
Neg logit contributions | |
Slave | -0.180 |
atts | -0.179 |
Grande | -0.172 |
oven | -0.170 |
Warehouse | -0.169 |
Token | dra |
Token ID | 28841 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
stroke | +0.783 |
Abstract | +0.726 |
sense | +0.720 |
edIn | +0.719 |
stal | +0.699 |
Neg logit contributions | |
atts | -0.616 |
Slave | -0.614 |
Grande | -0.584 |
oven | -0.580 |
Warehouse | -0.578 |
Token | per |
Token ID | 525 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
atts | +0.723 |
Slave | +0.722 |
Grande | +0.696 |
oven | +0.688 |
Labrador | +0.683 |
Neg logit contributions | |
stroke | -0.725 |
edIn | -0.675 |
Abstract | -0.674 |
sense | -0.666 |
stal | -0.644 |
Token | y |
Token ID | 88 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
Slave | +1.220 |
atts | +1.220 |
Grande | +1.184 |
oven | +1.174 |
Labrador | +1.171 |
Neg logit contributions | |
stroke | -0.752 |
edIn | -0.685 |
Abstract | -0.681 |
sense | -0.669 |
stal | -0.641 |
Token | , |
Token ID | 11 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
stroke | +0.655 |
Abstract | +0.605 |
sense | +0.602 |
edIn | +0.600 |
stal | +0.588 |
Neg logit contributions | |
Slave | -0.544 |
atts | -0.540 |
Grande | -0.519 |
Warehouse | -0.512 |
oven | -0.511 |
Token | he |
Token ID | 339 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
stroke | +0.483 |
Abstract | +0.445 |
edIn | +0.443 |
sense | +0.442 |
stal | +0.428 |
Neg logit contributions | |
atts | -0.453 |
Slave | -0.452 |
Grande | -0.433 |
oven | -0.430 |
Warehouse | -0.428 |
Token | should |
Token ID | 815 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
stroke | +0.066 |
Abstract | +0.060 |
edIn | +0.059 |
sense | +0.059 |
stal | +0.057 |
Neg logit contributions | |
Slave | -0.082 |
atts | -0.082 |
Grande | -0.079 |
Warehouse | -0.078 |
oven | -0.078 |
Token | proceed |
Token ID | 5120 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
Slave | +1.194 |
atts | +1.191 |
Grande | +1.145 |
oven | +1.129 |
Warehouse | +1.124 |
Neg logit contributions | |
stroke | -1.370 |
edIn | -1.276 |
Abstract | -1.276 |
sense | -1.262 |
stal | -1.227 |
Token | most |
Token ID | 749 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
stroke | +0.689 |
Abstract | +0.635 |
sense | +0.630 |
edIn | +0.626 |
stal | +0.614 |
Neg logit contributions | |
atts | -0.644 |
Slave | -0.640 |
Grande | -0.616 |
oven | -0.611 |
Warehouse | -0.610 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
stroke | +2.240 |
Abstract | +2.050 |
sense | +2.048 |
edIn | +2.012 |
stal | +1.989 |
Neg logit contributions | |
atts | -2.102 |
Slave | -2.053 |
Grande | -1.984 |
Warehouse | -1.968 |
oven | -1.967 |
Token | — |
Token ID | 960 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
Slave | +0.741 |
atts | +0.739 |
Grande | +0.710 |
oven | +0.700 |
Warehouse | +0.697 |
Neg logit contributions | |
stroke | -0.863 |
edIn | -0.805 |
Abstract | -0.804 |
sense | -0.796 |
stal | -0.774 |
Token | and |
Token ID | 290 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
stroke | +0.634 |
Abstract | +0.580 |
edIn | +0.575 |
sense | +0.575 |
stal | +0.555 |
Neg logit contributions | |
atts | -0.759 |
Slave | -0.758 |
Grande | -0.730 |
oven | -0.725 |
Warehouse | -0.723 |
Token | were |
Token ID | 547 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
stroke | +0.811 |
Abstract | +0.743 |
edIn | +0.741 |
sense | +0.739 |
stal | +0.719 |
Neg logit contributions | |
atts | -0.843 |
Slave | -0.838 |
Grande | -0.802 |
oven | -0.795 |
Labrador | -0.793 |
Token | lovely |
Token ID | 14081 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
atts | +0.612 |
Slave | +0.612 |
Grande | +0.587 |
Warehouse | +0.580 |
oven | +0.580 |
Neg logit contributions | |
stroke | -0.631 |
Abstract | -0.585 |
edIn | -0.581 |
sense | -0.579 |
stal | -0.564 |
Token | and |
Token ID | 290 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
stroke | +0.256 |
Abstract | +0.237 |
edIn | +0.236 |
sense | +0.235 |
stal | +0.229 |
Neg logit contributions | |
Slave | -0.226 |
atts | -0.226 |
Grande | -0.217 |
oven | -0.214 |
Warehouse | -0.214 |
Token | golden |
Token ID | 10861 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
stroke | +0.059 |
Abstract | +0.055 |
edIn | +0.054 |
sense | +0.054 |
stal | +0.053 |
Neg logit contributions | |
atts | -0.052 |
Slave | -0.052 |
Grande | -0.050 |
oven | -0.049 |
Warehouse | -0.049 |
Token | on |
Token ID | 319 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
stroke | +0.528 |
Abstract | +0.489 |
edIn | +0.487 |
sense | +0.485 |
stal | +0.473 |
Neg logit contributions | |
Slave | -0.456 |
atts | -0.456 |
Grande | -0.437 |
Warehouse | -0.432 |
oven | -0.431 |
Token | the |
Token ID | 262 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
Slave | +0.317 |
atts | +0.316 |
Grande | +0.305 |
oven | +0.301 |
Warehouse | +0.300 |
Neg logit contributions | |
stroke | -0.281 |
edIn | -0.259 |
Abstract | -0.258 |
sense | -0.255 |
stal | -0.247 |
Token | bott |
Token ID | 3005 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
stroke | +0.386 |
edIn | +0.358 |
Abstract | +0.357 |
sense | +0.356 |
stal | +0.348 |
Neg logit contributions | |
atts | -0.273 |
Slave | -0.270 |
Warehouse | -0.255 |
Grande | -0.255 |
oven | -0.254 |
Token | oms |
Token ID | 3150 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Slave | +0.749 |
atts | +0.743 |
Grande | +0.717 |
Labrador | +0.704 |
oven | +0.704 |
Neg logit contributions | |
stroke | -0.914 |
edIn | -0.852 |
Abstract | -0.851 |
sense | -0.845 |
stal | -0.823 |
Token | . |
Token ID | 13 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
atts | +1.140 |
Slave | +1.139 |
Grande | +1.092 |
oven | +1.079 |
Labrador | +1.070 |
Neg logit contributions | |
stroke | -1.408 |
edIn | -1.335 |
Abstract | -1.320 |
sense | -1.306 |
stal | -1.269 |
Token | The |
Token ID | 383 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
stroke | +0.047 |
Abstract | +0.043 |
edIn | +0.043 |
sense | +0.043 |
stal | +0.042 |
Neg logit contributions | |
atts | -0.046 |
Slave | -0.046 |
Grande | -0.044 |
oven | -0.044 |
Labrador | -0.043 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
stroke | +0.694 |
Abstract | +0.646 |
edIn | +0.640 |
sense | +0.636 |
stal | +0.622 |
Neg logit contributions | |
atts | -0.553 |
Slave | -0.535 |
oven | -0.514 |
Grande | -0.513 |
Labrador | -0.508 |
Token | final |
Token ID | 2457 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
atts | +0.323 |
Slave | +0.318 |
Grande | +0.304 |
oven | +0.303 |
Labrador | +0.301 |
Neg logit contributions | |
stroke | -0.405 |
Abstract | -0.377 |
edIn | -0.375 |
sense | -0.373 |
stal | -0.363 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
stroke | +1.160 |
edIn | +1.075 |
Abstract | +1.069 |
sense | +1.053 |
stal | +1.031 |
Neg logit contributions | |
atts | -0.957 |
Slave | -0.946 |
Grande | -0.902 |
oven | -0.901 |
Labrador | -0.891 |
Token |
|
Token ID | 198 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
atts | +0.123 |
Slave | +0.123 |
Grande | +0.118 |
oven | +0.117 |
Labrador | +0.116 |
Neg logit contributions | |
stroke | -0.135 |
Abstract | -0.126 |
edIn | -0.125 |
sense | -0.124 |
stal | -0.120 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
stroke | +0.288 |
Abstract | +0.267 |
edIn | +0.264 |
sense | +0.263 |
stal | +0.254 |
Neg logit contributions | |
atts | -0.325 |
Slave | -0.325 |
Grande | -0.313 |
oven | -0.309 |
Warehouse | -0.308 |
Token | TV |
Token ID | 6849 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
stroke | +0.085 |
Abstract | +0.079 |
edIn | +0.078 |
sense | +0.077 |
stal | +0.074 |
Neg logit contributions | |
Slave | -0.105 |
atts | -0.104 |
Grande | -0.101 |
Labrador | -0.100 |
Warehouse | -0.100 |
Token | 3 |
Token ID | 18 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Slave | +2.049 |
atts | +2.035 |
Grande | +1.961 |
Warehouse | +1.930 |
oven | +1.919 |
Neg logit contributions | |
stroke | -2.464 |
edIn | -2.302 |
Abstract | -2.289 |
sense | -2.263 |
stal | -2.217 |
Token | has |
Token ID | 468 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
stroke | +1.181 |
Abstract | +1.105 |
edIn | +1.096 |
sense | +1.091 |
stal | +1.061 |
Neg logit contributions | |
atts | -1.079 |
Slave | -1.076 |
Grande | -1.032 |
oven | -1.022 |
Labrador | -1.018 |
Token | dumped |
Token ID | 24105 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Slave | +1.271 |
atts | +1.266 |
Grande | +1.217 |
oven | +1.198 |
Labrador | +1.194 |
Neg logit contributions | |
stroke | -1.526 |
edIn | -1.425 |
Abstract | -1.424 |
sense | -1.409 |
stal | -1.371 |
Token | reality |
Token ID | 3950 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
stroke | +0.587 |
Abstract | +0.546 |
edIn | +0.544 |
sense | +0.540 |
stal | +0.526 |
Neg logit contributions | |
atts | -0.534 |
Slave | -0.527 |
Grande | -0.507 |
oven | -0.503 |
Labrador | -0.500 |
Token | shows |
Token ID | 2523 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
Slave | +1.703 |
atts | +1.692 |
Grande | +1.600 |
oven | +1.565 |
Warehouse | +1.557 |
Neg logit contributions | |
stroke | -3.610 |
edIn | -3.418 |
Abstract | -3.416 |
sense | -3.387 |
stal | -3.314 |
Token | the |
Token ID | 262 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Slave | +0.138 |
atts | +0.138 |
oven | +0.132 |
Grande | +0.132 |
Warehouse | +0.131 |
Neg logit contributions | |
stroke | -0.144 |
Abstract | -0.134 |
edIn | -0.134 |
sense | -0.132 |
stal | -0.130 |
Token | field |
Token ID | 2214 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
stroke | +0.276 |
Abstract | +0.258 |
edIn | +0.258 |
sense | +0.257 |
stal | +0.251 |
Neg logit contributions | |
atts | -0.234 |
Slave | -0.234 |
oven | -0.222 |
Grande | -0.221 |
Warehouse | -0.219 |
Token | on |
Token ID | 319 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
Slave | +0.743 |
atts | +0.740 |
Grande | +0.712 |
oven | +0.704 |
Warehouse | +0.701 |
Neg logit contributions | |
stroke | -0.781 |
Abstract | -0.724 |
edIn | -0.723 |
sense | -0.717 |
stal | -0.698 |
Token | military |
Token ID | 2422 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
atts | +0.342 |
Slave | +0.341 |
Grande | +0.326 |
oven | +0.325 |
Warehouse | +0.322 |
Neg logit contributions | |
stroke | -0.380 |
edIn | -0.354 |
Abstract | -0.353 |
sense | -0.350 |
stal | -0.341 |
Token | operations |
Token ID | 4560 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
stroke | +0.405 |
edIn | +0.379 |
Abstract | +0.376 |
sense | +0.376 |
stal | +0.366 |
Neg logit contributions | |
atts | -0.313 |
Slave | -0.313 |
Grande | -0.298 |
oven | -0.297 |
Warehouse | -0.294 |
Token | ad |
Token ID | 512 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
Slave | +0.065 |
atts | +0.065 |
Grande | +0.062 |
oven | +0.061 |
Warehouse | +0.061 |
Neg logit contributions | |
stroke | -0.067 |
Abstract | -0.062 |
edIn | -0.062 |
sense | -0.062 |
stal | -0.060 |
Token | inf |
Token ID | 1167 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
Slave | +0.422 |
atts | +0.421 |
Grande | +0.402 |
oven | +0.396 |
Warehouse | +0.394 |
Neg logit contributions | |
stroke | -0.519 |
edIn | -0.483 |
Abstract | -0.481 |
sense | -0.480 |
stal | -0.467 |
Token | init |
Token ID | 15003 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
stroke | +0.442 |
Abstract | +0.394 |
edIn | +0.394 |
sense | +0.388 |
stal | +0.371 |
Neg logit contributions | |
Slave | -0.870 |
atts | -0.866 |
Grande | -0.844 |
Warehouse | -0.833 |
Labrador | -0.833 |
Token | um |
Token ID | 388 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Slave | +2.802 |
atts | +2.799 |
Grande | +2.695 |
oven | +2.686 |
Labrador | +2.667 |
Neg logit contributions | |
stroke | -2.535 |
edIn | -2.358 |
Abstract | -2.295 |
sense | -2.289 |
stal | -2.174 |
Token | . |
Token ID | 13 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
stroke | +0.172 |
Abstract | +0.159 |
edIn | +0.159 |
sense | +0.158 |
stal | +0.154 |
Neg logit contributions | |
Slave | -0.155 |
atts | -0.155 |
Grande | -0.149 |
oven | -0.147 |
Warehouse | -0.147 |
Token | � |
Token ID | 447 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
Slave | +0.370 |
atts | +0.369 |
Grande | +0.356 |
oven | +0.351 |
Warehouse | +0.350 |
Neg logit contributions | |
stroke | -0.357 |
edIn | -0.331 |
Abstract | -0.330 |
sense | -0.327 |
stal | -0.317 |
Token | wil |
Token ID | 39716 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
Slave | +0.071 |
atts | +0.071 |
Grande | +0.068 |
oven | +0.067 |
Labrador | +0.067 |
Neg logit contributions | |
stroke | -0.079 |
edIn | -0.074 |
Abstract | -0.074 |
sense | -0.073 |
stal | -0.071 |
Token | kins |
Token ID | 5331 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
stroke | +0.783 |
sense | +0.730 |
Abstract | +0.724 |
edIn | +0.717 |
stal | +0.714 |
Neg logit contributions | |
Slave | -0.450 |
atts | -0.428 |
Grande | -0.424 |
Warehouse | -0.418 |
Labrador | -0.414 |
Token | i |
Token ID | 72 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Slave | +0.304 |
atts | +0.304 |
Grande | +0.294 |
Labrador | +0.291 |
oven | +0.291 |
Neg logit contributions | |
stroke | -0.250 |
edIn | -0.232 |
Abstract | -0.230 |
sense | -0.228 |
stal | -0.218 |
Token | is |
Token ID | 318 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
Slave | +0.307 |
atts | +0.306 |
Grande | +0.296 |
oven | +0.292 |
Labrador | +0.291 |
Neg logit contributions | |
stroke | -0.288 |
edIn | -0.267 |
Abstract | -0.266 |
sense | -0.263 |
stal | -0.255 |
Token | the |
Token ID | 262 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
stroke | +0.013 |
Abstract | +0.012 |
edIn | +0.012 |
sense | +0.012 |
stal | +0.011 |
Neg logit contributions | |
atts | -0.011 |
Slave | -0.011 |
Grande | -0.011 |
oven | -0.011 |
Warehouse | -0.011 |
Token | eastern |
Token ID | 10183 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
atts | +0.170 |
Slave | +0.169 |
Grande | +0.162 |
oven | +0.161 |
Warehouse | +0.159 |
Neg logit contributions | |
stroke | -0.226 |
Abstract | -0.212 |
edIn | -0.211 |
sense | -0.209 |
stal | -0.204 |
Token | short |
Token ID | 1790 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Slave | +1.497 |
atts | +1.486 |
Grande | +1.427 |
Labrador | +1.400 |
oven | +1.399 |
Neg logit contributions | |
stroke | -2.114 |
edIn | -1.988 |
Abstract | -1.983 |
sense | -1.965 |
stal | -1.914 |
Token | - |
Token ID | 12 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
stroke | +0.263 |
Abstract | +0.243 |
edIn | +0.243 |
sense | +0.242 |
stal | +0.235 |
Neg logit contributions | |
atts | -0.228 |
Slave | -0.228 |
Grande | -0.219 |
oven | -0.216 |
Warehouse | -0.215 |
Token | eared |
Token ID | 3380 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Slave | +0.235 |
atts | +0.234 |
Grande | +0.225 |
oven | +0.222 |
Labrador | +0.220 |
Neg logit contributions | |
stroke | -0.281 |
edIn | -0.263 |
Abstract | -0.263 |
sense | -0.260 |
stal | -0.253 |
Token | rock |
Token ID | 3881 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
Slave | +1.106 |
atts | +1.088 |
Grande | +1.054 |
Labrador | +1.041 |
Warehouse | +1.028 |
Neg logit contributions | |
stroke | -1.599 |
edIn | -1.513 |
Abstract | -1.502 |
sense | -1.492 |
stal | -1.447 |
Token | - |
Token ID | 12 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Slave | +0.435 |
atts | +0.426 |
Grande | +0.414 |
Labrador | +0.412 |
oven | +0.407 |
Neg logit contributions | |
stroke | -0.563 |
edIn | -0.537 |
Abstract | -0.531 |
sense | -0.527 |
stal | -0.507 |
Token | necessary |
Token ID | 3306 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
Slave | +0.274 |
atts | +0.273 |
Grande | +0.261 |
oven | +0.257 |
Labrador | +0.256 |
Neg logit contributions | |
stroke | -0.379 |
edIn | -0.355 |
Abstract | -0.354 |
sense | -0.351 |
stal | -0.342 |
Token | repairs |
Token ID | 20097 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Slave | +0.363 |
atts | +0.362 |
Grande | +0.346 |
oven | +0.342 |
Warehouse | +0.340 |
Neg logit contributions | |
stroke | -0.451 |
edIn | -0.420 |
Abstract | -0.419 |
sense | -0.416 |
stal | -0.405 |
Token | throughout |
Token ID | 3690 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Slave | +0.684 |
atts | +0.681 |
Grande | +0.654 |
oven | +0.646 |
Warehouse | +0.643 |
Neg logit contributions | |
stroke | -0.791 |
Abstract | -0.737 |
edIn | -0.737 |
sense | -0.729 |
stal | -0.709 |
Token | the |
Token ID | 262 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
stroke | +0.983 |
edIn | +0.907 |
Abstract | +0.906 |
sense | +0.895 |
stal | +0.868 |
Neg logit contributions | |
Slave | -1.088 |
atts | -1.085 |
Grande | -1.046 |
oven | -1.036 |
Labrador | -1.030 |
Token | city |
Token ID | 1748 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
stroke | +0.699 |
Abstract | +0.652 |
edIn | +0.651 |
sense | +0.644 |
stal | +0.627 |
Neg logit contributions | |
atts | -0.578 |
Slave | -0.576 |
Grande | -0.548 |
oven | -0.545 |
Labrador | -0.542 |
Token | � |
Token ID | 447 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
stroke | +1.161 |
Abstract | +1.082 |
edIn | +1.074 |
sense | +1.069 |
stal | +1.041 |
Neg logit contributions | |
Slave | -1.032 |
atts | -1.028 |
Grande | -0.986 |
oven | -0.975 |
Warehouse | -0.971 |
Token | � |
Token ID | 247 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
stroke | +0.671 |
edIn | +0.620 |
Abstract | +0.618 |
sense | +0.610 |
stal | +0.594 |
Neg logit contributions | |
atts | -0.698 |
Slave | -0.697 |
Grande | -0.673 |
oven | -0.666 |
Warehouse | -0.664 |
Token | s |
Token ID | 82 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
stroke | +0.105 |
edIn | +0.092 |
Abstract | +0.092 |
sense | +0.089 |
stal | +0.084 |
Neg logit contributions | |
Slave | -0.266 |
atts | -0.265 |
Grande | -0.258 |
oven | -0.257 |
Warehouse | -0.255 |
Token | various |
Token ID | 2972 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
stroke | +0.455 |
edIn | +0.425 |
Abstract | +0.424 |
sense | +0.419 |
stal | +0.409 |
Neg logit contributions | |
Slave | -0.366 |
atts | -0.366 |
Grande | -0.349 |
oven | -0.346 |
Labrador | -0.344 |
Token | neighborhoods |
Token ID | 14287 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
stroke | +2.251 |
edIn | +2.112 |
Abstract | +2.101 |
sense | +2.083 |
stal | +2.029 |
Neg logit contributions | |
atts | -1.768 |
Slave | -1.749 |
Grande | -1.665 |
oven | -1.655 |
Labrador | -1.654 |
Token | . |
Token ID | 13 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
stroke | +1.314 |
Abstract | +1.225 |
edIn | +1.216 |
sense | +1.210 |
stal | +1.179 |
Neg logit contributions | |
Slave | -1.177 |
atts | -1.172 |
Grande | -1.122 |
oven | -1.111 |
Warehouse | -1.108 |
Token | states |
Token ID | 2585 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Slave | +0.579 |
atts | +0.577 |
Grande | +0.549 |
oven | +0.542 |
Warehouse | +0.538 |
Neg logit contributions | |
stroke | -0.874 |
Abstract | -0.821 |
edIn | -0.820 |
sense | -0.812 |
stal | -0.794 |
Token | , |
Token ID | 11 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
stroke | +0.095 |
Abstract | +0.088 |
edIn | +0.088 |
sense | +0.087 |
stal | +0.085 |
Neg logit contributions | |
atts | -0.079 |
Slave | -0.079 |
Grande | -0.075 |
oven | -0.075 |
Warehouse | -0.074 |
Token | � |
Token ID | 564 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Slave | +0.465 |
atts | +0.462 |
Grande | +0.444 |
oven | +0.437 |
Labrador | +0.436 |
Neg logit contributions | |
stroke | -0.582 |
edIn | -0.544 |
Abstract | -0.543 |
sense | -0.538 |
stal | -0.524 |
Token | � |
Token ID | 250 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
Slave | +0.134 |
atts | +0.133 |
Grande | +0.129 |
oven | +0.128 |
Labrador | +0.127 |
Neg logit contributions | |
stroke | -0.083 |
Abstract | -0.075 |
edIn | -0.075 |
sense | -0.074 |
stal | -0.071 |
Token | Sometimes |
Token ID | 15468 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
stroke | +0.436 |
Abstract | +0.402 |
edIn | +0.399 |
sense | +0.398 |
stal | +0.383 |
Neg logit contributions | |
Slave | -0.524 |
atts | -0.523 |
Grande | -0.505 |
Warehouse | -0.499 |
oven | -0.498 |
Token | it |
Token ID | 340 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Slave | +1.881 |
atts | +1.861 |
Grande | +1.800 |
Labrador | +1.769 |
oven | +1.766 |
Neg logit contributions | |
stroke | -2.160 |
edIn | -2.029 |
Abstract | -2.020 |
sense | -1.993 |
stal | -1.940 |
Token | grounds |
Token ID | 9384 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
stroke | +0.760 |
Abstract | +0.697 |
sense | +0.692 |
edIn | +0.687 |
stal | +0.670 |
Neg logit contributions | |
Slave | -0.851 |
atts | -0.851 |
Grande | -0.820 |
oven | -0.816 |
Warehouse | -0.811 |
Token | me |
Token ID | 502 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
stroke | +1.114 |
sense | +1.029 |
edIn | +1.024 |
Abstract | +1.015 |
stal | +0.978 |
Neg logit contributions | |
atts | -1.230 |
Slave | -1.227 |
Grande | -1.183 |
oven | -1.180 |
Warehouse | -1.168 |
Token | and |
Token ID | 290 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
stroke | +0.570 |
Abstract | +0.529 |
sense | +0.524 |
edIn | +0.523 |
stal | +0.512 |
Neg logit contributions | |
atts | -0.515 |
Slave | -0.514 |
Grande | -0.494 |
Warehouse | -0.491 |
oven | -0.490 |
Token | gives |
Token ID | 3607 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
stroke | +0.626 |
edIn | +0.576 |
Abstract | +0.576 |
sense | +0.573 |
stal | +0.556 |
Neg logit contributions | |
atts | -0.633 |
Slave | -0.629 |
Grande | -0.605 |
oven | -0.601 |
Warehouse | -0.597 |
Token | me |
Token ID | 502 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
stroke | +0.275 |
Abstract | +0.248 |
edIn | +0.248 |
sense | +0.248 |
stal | +0.236 |
Neg logit contributions | |
atts | -0.397 |
Slave | -0.397 |
Grande | -0.384 |
oven | -0.382 |
Warehouse | -0.380 |
Token | 6 |
Token ID | 718 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
stroke | +0.404 |
Abstract | +0.378 |
edIn | +0.376 |
sense | +0.375 |
stal | +0.365 |
Neg logit contributions | |
atts | -0.293 |
Slave | -0.290 |
Grande | -0.277 |
oven | -0.276 |
Labrador | -0.272 |
Token | percent |
Token ID | 1411 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
Slave | +0.314 |
atts | +0.314 |
Grande | +0.300 |
oven | +0.298 |
Labrador | +0.297 |
Neg logit contributions | |
stroke | -0.322 |
Abstract | -0.298 |
edIn | -0.297 |
sense | -0.295 |
stal | -0.286 |
Token | wheat |
Token ID | 17135 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
stroke | +0.682 |
edIn | +0.632 |
sense | +0.629 |
Abstract | +0.628 |
stal | +0.607 |
Neg logit contributions | |
Slave | -0.541 |
atts | -0.541 |
Grande | -0.515 |
oven | -0.513 |
Labrador | -0.507 |
Token | IPA |
Token ID | 27966 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Slave | +1.354 |
atts | +1.347 |
Grande | +1.295 |
oven | +1.275 |
Labrador | +1.270 |
Neg logit contributions | |
stroke | -1.738 |
edIn | -1.628 |
Abstract | -1.627 |
sense | -1.609 |
stal | -1.566 |
Token | made |
Token ID | 925 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
stroke | +1.306 |
Abstract | +1.220 |
edIn | +1.209 |
sense | +1.207 |
stal | +1.172 |
Neg logit contributions | |
atts | -1.190 |
Slave | -1.178 |
oven | -1.112 |
Grande | -1.111 |
Warehouse | -1.105 |
Token | with |
Token ID | 351 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Slave | +0.136 |
atts | +0.136 |
Grande | +0.130 |
oven | +0.128 |
Warehouse | +0.128 |
Neg logit contributions | |
stroke | -0.167 |
Abstract | -0.156 |
edIn | -0.156 |
sense | -0.154 |
stal | -0.150 |
Token | Chin |
Token ID | 22604 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
stroke | +1.323 |
Abstract | +1.243 |
edIn | +1.236 |
sense | +1.224 |
stal | +1.192 |
Neg logit contributions | |
atts | -1.033 |
Slave | -1.017 |
oven | -0.973 |
Grande | -0.957 |
Warehouse | -0.952 |
Token | ook |
Token ID | 566 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Slave | +2.939 |
atts | +2.930 |
Grande | +2.842 |
oven | +2.812 |
Labrador | +2.798 |
Neg logit contributions | |
stroke | -2.192 |
edIn | -2.015 |
Abstract | -2.000 |
sense | -1.974 |
stal | -1.898 |
Token | and |
Token ID | 290 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
Slave | +1.489 |
atts | +1.480 |
Grande | +1.435 |
oven | +1.409 |
Labrador | +1.407 |
Neg logit contributions | |
stroke | -1.488 |
edIn | -1.378 |
Abstract | -1.377 |
sense | -1.362 |
stal | -1.320 |
Token | Cit |
Token ID | 15792 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
stroke | +0.033 |
Abstract | +0.031 |
edIn | +0.031 |
sense | +0.031 |
stal | +0.030 |
Neg logit contributions | |
atts | -0.025 |
Slave | -0.024 |
oven | -0.023 |
Grande | -0.023 |
Warehouse | -0.023 |
Token | ra |
Token ID | 430 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
stroke | +0.812 |
Abstract | +0.770 |
edIn | +0.761 |
sense | +0.760 |
stal | +0.748 |
Neg logit contributions | |
Slave | -0.441 |
atts | -0.438 |
Grande | -0.411 |
oven | -0.405 |
Warehouse | -0.405 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.83e+00 |
Pos logit contributions | |
stroke | +1.871 |
Abstract | +1.744 |
sense | +1.708 |
edIn | +1.699 |
stal | +1.644 |
Neg logit contributions | |
atts | -2.720 |
Slave | -2.697 |
Grande | -2.620 |
oven | -2.602 |
Labrador | -2.582 |
Token | Republican |
Token ID | 25777 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
stroke | +5.810 |
Abstract | +5.769 |
sense | +5.369 |
edIn | +5.240 |
stal | +5.090 |
Neg logit contributions | |
Slave | -6.776 |
atts | -6.657 |
Grande | -6.533 |
Labrador | -6.515 |
Warehouse | -6.512 |
Token | Sen |
Token ID | 2311 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Slave | +0.961 |
atts | +0.960 |
Grande | +0.922 |
oven | +0.912 |
Warehouse | +0.905 |
Neg logit contributions | |
stroke | -1.073 |
Abstract | -0.999 |
edIn | -0.999 |
sense | -0.987 |
stal | -0.960 |
Token | . |
Token ID | 13 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
stroke | +1.350 |
edIn | +1.243 |
sense | +1.241 |
Abstract | +1.240 |
stal | +1.215 |
Neg logit contributions | |
Slave | -1.278 |
atts | -1.267 |
Grande | -1.219 |
oven | -1.210 |
enslaved | -1.206 |
Token | Rand |
Token ID | 8790 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
stroke | +0.247 |
Abstract | +0.232 |
edIn | +0.230 |
sense | +0.229 |
stal | +0.223 |
Neg logit contributions | |
atts | -0.189 |
Slave | -0.187 |
oven | -0.179 |
Grande | -0.177 |
Warehouse | -0.175 |
Token | Paul |
Token ID | 3362 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
atts | +1.412 |
Slave | +1.408 |
Grande | +1.349 |
Warehouse | +1.333 |
oven | +1.332 |
Neg logit contributions | |
stroke | -1.435 |
Abstract | -1.336 |
edIn | -1.326 |
sense | -1.318 |
stal | -1.274 |
Token | is |
Token ID | 318 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
stroke | +2.903 |
Abstract | +2.689 |
edIn | +2.659 |
sense | +2.651 |
stal | +2.612 |
Neg logit contributions | |
Slave | -2.794 |
atts | -2.775 |
oven | -2.669 |
Warehouse | -2.657 |
Grande | -2.629 |
Token | " |
Token ID | 366 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
Slave | +0.632 |
atts | +0.630 |
Grande | +0.607 |
oven | +0.599 |
Warehouse | +0.596 |
Neg logit contributions | |
stroke | -0.727 |
Abstract | -0.677 |
edIn | -0.669 |
sense | -0.667 |
stal | -0.649 |
Token | bas |
Token ID | 12093 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
stroke | +0.506 |
Abstract | +0.464 |
sense | +0.461 |
edIn | +0.461 |
stal | +0.446 |
Neg logit contributions | |
Slave | -0.597 |
atts | -0.592 |
Grande | -0.577 |
Warehouse | -0.570 |
Labrador | -0.566 |
Token | ically |
Token ID | 1146 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
stroke | +0.360 |
edIn | +0.330 |
Abstract | +0.329 |
sense | +0.326 |
stal | +0.317 |
Neg logit contributions | |
atts | -0.444 |
Slave | -0.444 |
Grande | -0.430 |
Warehouse | -0.423 |
oven | -0.422 |
Token | an |
Token ID | 281 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
atts | +0.992 |
Slave | +0.991 |
Grande | +0.952 |
oven | +0.940 |
Warehouse | +0.936 |
Neg logit contributions | |
stroke | -1.136 |
Abstract | -1.059 |
edIn | -1.055 |
sense | -1.047 |
stal | -1.020 |
Token | it |
Token ID | 340 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
stroke | +0.527 |
edIn | +0.489 |
Abstract | +0.485 |
sense | +0.482 |
stal | +0.470 |
Neg logit contributions | |
atts | -0.504 |
Slave | -0.498 |
Grande | -0.478 |
oven | -0.477 |
Warehouse | -0.472 |
Token | � |
Token ID | 447 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
stroke | +0.313 |
Abstract | +0.289 |
edIn | +0.289 |
sense | +0.286 |
stal | +0.279 |
Neg logit contributions | |
Slave | -0.340 |
atts | -0.338 |
Grande | -0.326 |
oven | -0.323 |
Warehouse | -0.322 |
Token | � |
Token ID | 247 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
stroke | +0.380 |
edIn | +0.351 |
Abstract | +0.349 |
sense | +0.346 |
stal | +0.337 |
Neg logit contributions | |
Slave | -0.383 |
atts | -0.382 |
Grande | -0.370 |
oven | -0.364 |
Warehouse | -0.364 |
Token | s |
Token ID | 82 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Slave | +0.048 |
atts | +0.048 |
Grande | +0.046 |
oven | +0.046 |
Warehouse | +0.046 |
Neg logit contributions | |
stroke | -0.018 |
edIn | -0.016 |
Abstract | -0.016 |
sense | -0.015 |
stal | -0.014 |
Token | unsurprisingly |
Token ID | 49619 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
stroke | +0.820 |
Abstract | +0.764 |
edIn | +0.752 |
sense | +0.750 |
stal | +0.735 |
Neg logit contributions | |
Slave | -0.764 |
atts | -0.762 |
Grande | -0.726 |
oven | -0.724 |
Warehouse | -0.722 |
Token | difficult |
Token ID | 2408 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
stroke | +0.577 |
Abstract | +0.538 |
sense | +0.531 |
edIn | +0.530 |
stal | +0.520 |
Neg logit contributions | |
Slave | -0.514 |
atts | -0.513 |
Grande | -0.491 |
oven | -0.488 |
Warehouse | -0.486 |
Token | for |
Token ID | 329 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
stroke | +1.492 |
Abstract | +1.385 |
edIn | +1.385 |
sense | +1.374 |
stal | +1.339 |
Neg logit contributions | |
Slave | -1.267 |
atts | -1.260 |
Grande | -1.213 |
oven | -1.196 |
Warehouse | -1.191 |
Token | bio |
Token ID | 13401 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
stroke | +1.433 |
Abstract | +1.331 |
edIn | +1.330 |
sense | +1.327 |
stal | +1.290 |
Neg logit contributions | |
atts | -1.303 |
Slave | -1.281 |
Grande | -1.237 |
oven | -1.237 |
Warehouse | -1.207 |
Token | h |
Token ID | 71 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
stroke | +2.081 |
sense | +1.932 |
Abstract | +1.921 |
edIn | +1.897 |
stal | +1.860 |
Neg logit contributions | |
Slave | -2.121 |
atts | -2.081 |
Grande | -2.033 |
Labrador | -1.989 |
oven | -1.982 |
Token | ackers |
Token ID | 28874 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
stroke | +0.245 |
edIn | +0.228 |
Abstract | +0.228 |
sense | +0.226 |
stal | +0.221 |
Neg logit contributions | |
Slave | -0.237 |
atts | -0.231 |
Grande | -0.226 |
Labrador | -0.223 |
Warehouse | -0.222 |
Token | like |
Token ID | 588 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
atts | +0.308 |
Slave | +0.308 |
Grande | +0.296 |
oven | +0.291 |
Labrador | +0.290 |
Neg logit contributions | |
stroke | -0.371 |
edIn | -0.348 |
Abstract | -0.346 |
sense | -0.343 |
stal | -0.333 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Slave | +0.155 |
atts | +0.154 |
Grande | +0.149 |
oven | +0.147 |
Warehouse | +0.147 |
Neg logit contributions | |
stroke | -0.140 |
Abstract | -0.129 |
edIn | -0.129 |
sense | -0.128 |
stal | -0.124 |
Token | On |
Token ID | 2202 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
Slave | +0.126 |
atts | +0.125 |
Grande | +0.122 |
oven | +0.120 |
Labrador | +0.120 |
Neg logit contributions | |
stroke | -0.091 |
edIn | -0.083 |
Abstract | -0.083 |
sense | -0.082 |
stal | -0.079 |
Token | 6 |
Token ID | 718 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
atts | +0.455 |
Slave | +0.451 |
Grande | +0.429 |
oven | +0.429 |
Warehouse | +0.422 |
Neg logit contributions | |
stroke | -0.592 |
Abstract | -0.553 |
edIn | -0.549 |
sense | -0.547 |
stal | -0.534 |
Token | October |
Token ID | 3267 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
stroke | +0.623 |
Abstract | +0.581 |
edIn | +0.574 |
sense | +0.573 |
stal | +0.559 |
Neg logit contributions | |
atts | -0.587 |
Slave | -0.586 |
Grande | -0.562 |
oven | -0.558 |
Labrador | -0.551 |
Token | 1941 |
Token ID | 23234 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
stroke | +0.081 |
edIn | +0.076 |
Abstract | +0.076 |
sense | +0.075 |
stal | +0.073 |
Neg logit contributions | |
Slave | -0.055 |
atts | -0.055 |
Grande | -0.053 |
oven | -0.052 |
Warehouse | -0.052 |
Token | Zh |
Token ID | 10511 |
Feature activation | -6.87e+00 |
Pos logit contributions | |
stroke | +1.634 |
Abstract | +1.501 |
edIn | +1.499 |
sense | +1.479 |
stal | +1.443 |
Neg logit contributions | |
atts | -1.842 |
Slave | -1.833 |
Grande | -1.764 |
oven | -1.756 |
Labrador | -1.740 |
Token | uk |
Token ID | 2724 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
stroke | +4.152 |
sense | +3.704 |
Abstract | +3.682 |
stal | +3.662 |
onym | +3.455 |
Neg logit contributions | |
Slave | -5.826 |
Warehouse | -5.656 |
proport | -5.592 |
Grande | -5.576 |
enslaved | -5.532 |
Token | ov |
Token ID | 709 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
stroke | +0.755 |
Abstract | +0.679 |
sense | +0.673 |
edIn | +0.670 |
stal | +0.656 |
Neg logit contributions | |
Slave | -0.993 |
atts | -0.981 |
Grande | -0.959 |
Warehouse | -0.951 |
Labrador | -0.942 |
Token | was |
Token ID | 373 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
stroke | +2.028 |
Abstract | +1.869 |
edIn | +1.842 |
sense | +1.839 |
stal | +1.824 |
Neg logit contributions | |
Slave | -2.040 |
atts | -2.025 |
oven | -1.942 |
Warehouse | -1.927 |
Grande | -1.919 |
Token | appointed |
Token ID | 9899 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
stroke | +0.384 |
Abstract | +0.357 |
edIn | +0.357 |
sense | +0.353 |
stal | +0.347 |
Neg logit contributions | |
Slave | -0.287 |
atts | -0.285 |
Grande | -0.271 |
oven | -0.270 |
Warehouse | -0.268 |
Token | the |
Token ID | 262 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Slave | +0.235 |
atts | +0.235 |
Grande | +0.226 |
oven | +0.223 |
Warehouse | +0.222 |
Neg logit contributions | |
stroke | -0.250 |
edIn | -0.232 |
Abstract | -0.232 |
sense | -0.230 |
stal | -0.223 |
Token | has |
Token ID | 468 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
stroke | +0.150 |
Abstract | +0.140 |
edIn | +0.139 |
sense | +0.138 |
stal | +0.134 |
Neg logit contributions | |
Slave | -0.123 |
atts | -0.123 |
Grande | -0.118 |
oven | -0.117 |
Labrador | -0.116 |
Token | the |
Token ID | 262 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
Slave | +1.630 |
atts | +1.623 |
Grande | +1.559 |
oven | +1.530 |
Labrador | +1.528 |
Neg logit contributions | |
stroke | -2.015 |
edIn | -1.886 |
Abstract | -1.883 |
sense | -1.865 |
stal | -1.818 |
Token | full |
Token ID | 1336 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Slave | +0.517 |
atts | +0.515 |
Grande | +0.497 |
oven | +0.491 |
Warehouse | +0.487 |
Neg logit contributions | |
stroke | -0.588 |
Abstract | -0.548 |
edIn | -0.547 |
sense | -0.542 |
stal | -0.525 |
Token | list |
Token ID | 1351 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
stroke | +0.210 |
Abstract | +0.195 |
edIn | +0.193 |
sense | +0.193 |
stal | +0.186 |
Neg logit contributions | |
Slave | -0.188 |
atts | -0.188 |
Grande | -0.182 |
oven | -0.180 |
Labrador | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Slave | +0.111 |
atts | +0.111 |
Grande | +0.106 |
oven | +0.105 |
Warehouse | +0.104 |
Neg logit contributions | |
stroke | -0.143 |
Abstract | -0.134 |
edIn | -0.134 |
sense | -0.132 |
stal | -0.129 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.18e+00 |
Pos logit contributions | |
Slave | +0.957 |
atts | +0.953 |
Grande | +0.919 |
oven | +0.907 |
Warehouse | +0.904 |
Neg logit contributions | |
stroke | -0.962 |
edIn | -0.893 |
Abstract | -0.892 |
sense | -0.882 |
stal | -0.856 |
Token | Last |
Token ID | 5956 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
stroke | +5.394 |
Abstract | +5.334 |
sense | +4.968 |
edIn | +4.863 |
stal | +4.714 |
Neg logit contributions | |
Slave | -6.331 |
atts | -6.216 |
Grande | -6.104 |
Warehouse | -6.085 |
Labrador | -6.080 |
Token | weekend |
Token ID | 5041 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
stroke | +2.344 |
Abstract | +2.205 |
sense | +2.185 |
edIn | +2.174 |
stal | +2.098 |
Neg logit contributions | |
atts | -1.737 |
Slave | -1.703 |
oven | -1.640 |
Grande | -1.624 |
Labrador | -1.603 |
Token | in |
Token ID | 287 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
stroke | +1.888 |
Abstract | +1.760 |
edIn | +1.742 |
sense | +1.729 |
stal | +1.683 |
Neg logit contributions | |
atts | -1.667 |
Slave | -1.650 |
Grande | -1.579 |
oven | -1.577 |
Warehouse | -1.555 |
Token | the |
Token ID | 262 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
stroke | +0.417 |
Abstract | +0.389 |
edIn | +0.387 |
sense | +0.385 |
stal | +0.374 |
Neg logit contributions | |
atts | -0.334 |
Slave | -0.333 |
oven | -0.319 |
Grande | -0.319 |
Warehouse | -0.313 |
Token | largest |
Token ID | 4387 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
stroke | +0.370 |
Abstract | +0.347 |
edIn | +0.344 |
sense | +0.342 |
stal | +0.334 |
Neg logit contributions | |
atts | -0.273 |
Slave | -0.269 |
oven | -0.258 |
Grande | -0.256 |
Labrador | -0.251 |
Token | solution |
Token ID | 4610 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
stroke | +0.229 |
Abstract | +0.212 |
edIn | +0.212 |
sense | +0.210 |
stal | +0.204 |
Neg logit contributions | |
Slave | -0.219 |
atts | -0.219 |
Grande | -0.210 |
oven | -0.207 |
Labrador | -0.207 |
Token | to |
Token ID | 284 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
stroke | +2.485 |
Abstract | +2.317 |
edIn | +2.291 |
sense | +2.289 |
stal | +2.228 |
Neg logit contributions | |
Slave | -2.320 |
atts | -2.297 |
Grande | -2.203 |
oven | -2.181 |
Warehouse | -2.172 |
Token | apply |
Token ID | 4174 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
stroke | +0.506 |
Abstract | +0.467 |
edIn | +0.467 |
sense | +0.461 |
stal | +0.450 |
Neg logit contributions | |
atts | -0.488 |
Slave | -0.488 |
Grande | -0.466 |
oven | -0.462 |
Labrador | -0.460 |
Token | to |
Token ID | 284 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
stroke | +1.635 |
Abstract | +1.505 |
edIn | +1.504 |
sense | +1.499 |
stal | +1.447 |
Neg logit contributions | |
Slave | -1.539 |
atts | -1.531 |
Grande | -1.461 |
oven | -1.448 |
Warehouse | -1.447 |
Token | national |
Token ID | 2260 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
atts | +0.039 |
Slave | +0.039 |
Grande | +0.037 |
oven | +0.037 |
Labrador | +0.037 |
Neg logit contributions | |
stroke | -0.040 |
Abstract | -0.037 |
edIn | -0.037 |
sense | -0.036 |
stal | -0.035 |
Token | pharmac |
Token ID | 25702 |
Feature activation | -8.82e+00 |
Pos logit contributions | |
stroke | +0.793 |
edIn | +0.735 |
Abstract | +0.735 |
sense | +0.731 |
stal | +0.714 |
Neg logit contributions | |
atts | -0.681 |
Slave | -0.681 |
Grande | -0.653 |
oven | -0.645 |
Warehouse | -0.641 |
Token | are |
Token ID | 533 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
stroke | +6.365 |
sense | +5.898 |
Abstract | +5.831 |
stal | +5.822 |
edIn | +5.715 |
Neg logit contributions | |
Slave | -6.123 |
Grande | -5.968 |
atts | -5.805 |
Labrador | -5.792 |
TVs | -5.741 |
Token | , |
Token ID | 11 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
stroke | +0.022 |
Abstract | +0.020 |
edIn | +0.020 |
sense | +0.020 |
stal | +0.020 |
Neg logit contributions | |
Slave | -0.020 |
atts | -0.020 |
Grande | -0.019 |
oven | -0.019 |
Labrador | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
stroke | +0.482 |
edIn | +0.448 |
Abstract | +0.448 |
sense | +0.443 |
stal | +0.430 |
Neg logit contributions | |
Slave | -0.454 |
atts | -0.452 |
Grande | -0.435 |
oven | -0.430 |
Warehouse | -0.428 |
Token | part |
Token ID | 636 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
stroke | +0.907 |
Abstract | +0.839 |
edIn | +0.832 |
sense | +0.832 |
stal | +0.807 |
Neg logit contributions | |
Slave | -0.977 |
atts | -0.971 |
Grande | -0.934 |
oven | -0.928 |
Warehouse | -0.922 |
Token | or |
Token ID | 393 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Slave | +1.411 |
atts | +1.411 |
Grande | +1.361 |
oven | +1.341 |
Labrador | +1.337 |
Neg logit contributions | |
stroke | -1.647 |
edIn | -1.546 |
Abstract | -1.536 |
sense | -1.524 |
stal | -1.476 |
Token | on |
Token ID | 319 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
stroke | +2.945 |
edIn | +2.703 |
Abstract | +2.702 |
sense | +2.672 |
stal | +2.609 |
Neg logit contributions | |
atts | -2.896 |
Slave | -2.858 |
oven | -2.749 |
Grande | -2.747 |
Warehouse | -2.710 |
Token | to |
Token ID | 284 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Slave | +0.800 |
atts | +0.794 |
Grande | +0.765 |
Labrador | +0.751 |
oven | +0.749 |
Neg logit contributions | |
stroke | -1.012 |
edIn | -0.951 |
Abstract | -0.948 |
sense | -0.938 |
stal | -0.911 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
stroke | +0.090 |
Abstract | +0.083 |
edIn | +0.083 |
sense | +0.082 |
stal | +0.080 |
Neg logit contributions | |
atts | -0.093 |
Slave | -0.092 |
Grande | -0.089 |
oven | -0.089 |
Labrador | -0.088 |
Token | other |
Token ID | 584 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
stroke | +0.085 |
Abstract | +0.079 |
edIn | +0.079 |
sense | +0.078 |
stal | +0.076 |
Neg logit contributions | |
atts | -0.075 |
Slave | -0.074 |
Grande | -0.071 |
oven | -0.071 |
Labrador | -0.070 |
Token | Reno |
Token ID | 33817 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
atts | +0.696 |
Slave | +0.694 |
Grande | +0.665 |
oven | +0.657 |
Labrador | +0.652 |
Neg logit contributions | |
stroke | -0.874 |
Abstract | -0.816 |
edIn | -0.815 |
sense | -0.810 |
stal | -0.787 |
Token | cards |
Token ID | 4116 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
stroke | +2.426 |
Abstract | +2.227 |
sense | +2.220 |
edIn | +2.184 |
stal | +2.182 |
Neg logit contributions | |
Slave | -2.070 |
atts | -2.068 |
oven | -2.006 |
Labrador | -1.980 |
Warehouse | -1.950 |
Token | , |
Token ID | 11 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
stroke | +4.250 |
Abstract | +3.893 |
sense | +3.856 |
edIn | +3.797 |
stal | +3.785 |
Neg logit contributions | |
Slave | -3.988 |
atts | -3.925 |
Grande | -3.742 |
oven | -3.729 |
Warehouse | -3.711 |
Token | how |
Token ID | 703 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
stroke | +0.510 |
Abstract | +0.469 |
edIn | +0.469 |
sense | +0.466 |
stal | +0.452 |
Neg logit contributions | |
atts | -0.517 |
Slave | -0.513 |
Grande | -0.493 |
oven | -0.492 |
Warehouse | -0.486 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
stroke | +2.082 |
Abstract | +1.930 |
sense | +1.886 |
edIn | +1.883 |
stal | +1.844 |
Neg logit contributions | |
atts | -2.426 |
Slave | -2.396 |
Grande | -2.311 |
oven | -2.305 |
Warehouse | -2.282 |
Token | are |
Token ID | 389 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
stroke | +0.970 |
Abstract | +0.890 |
edIn | +0.890 |
sense | +0.883 |
stal | +0.856 |
Neg logit contributions | |
atts | -1.091 |
Slave | -1.089 |
Grande | -1.049 |
oven | -1.039 |
Warehouse | -1.034 |
Token | you |
Token ID | 345 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
Slave | +0.534 |
atts | +0.530 |
Grande | +0.512 |
oven | +0.504 |
Warehouse | +0.503 |
Neg logit contributions | |
stroke | -0.559 |
edIn | -0.520 |
Abstract | -0.520 |
sense | -0.513 |
stal | -0.499 |
Token | right |
Token ID | 826 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
stroke | +0.128 |
edIn | +0.119 |
Abstract | +0.119 |
sense | +0.118 |
stal | +0.115 |
Neg logit contributions | |
Slave | -0.110 |
atts | -0.109 |
Grande | -0.105 |
oven | -0.104 |
Warehouse | -0.103 |
Token | through |
Token ID | 832 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
stroke | +1.563 |
Abstract | +1.434 |
edIn | +1.432 |
sense | +1.412 |
stal | +1.366 |
Neg logit contributions | |
atts | -1.797 |
Slave | -1.796 |
Grande | -1.730 |
oven | -1.719 |
Warehouse | -1.706 |
Token | to |
Token ID | 284 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
stroke | +1.555 |
edIn | +1.445 |
Abstract | +1.442 |
sense | +1.429 |
stal | +1.390 |
Neg logit contributions | |
atts | -1.397 |
Slave | -1.396 |
Grande | -1.338 |
oven | -1.329 |
Labrador | -1.316 |
Token | its |
Token ID | 663 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
stroke | +0.552 |
edIn | +0.508 |
Abstract | +0.507 |
sense | +0.501 |
stal | +0.487 |
Neg logit contributions | |
atts | -0.629 |
Slave | -0.626 |
Grande | -0.603 |
oven | -0.600 |
Labrador | -0.595 |
Token | character |
Token ID | 2095 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
stroke | +1.517 |
edIn | +1.414 |
Abstract | +1.413 |
sense | +1.398 |
stal | +1.370 |
Neg logit contributions | |
atts | -1.237 |
Slave | -1.207 |
oven | -1.166 |
Grande | -1.154 |
Labrador | -1.129 |
Token | swapping |
Token ID | 38869 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
stroke | +0.135 |
Abstract | +0.125 |
edIn | +0.125 |
sense | +0.124 |
stal | +0.121 |
Neg logit contributions | |
Slave | -0.118 |
atts | -0.118 |
Grande | -0.113 |
oven | -0.112 |
Labrador | -0.111 |
Token | conclusion |
Token ID | 7664 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
stroke | +4.409 |
sense | +4.012 |
Abstract | +3.997 |
edIn | +3.967 |
stal | +3.900 |
Neg logit contributions | |
atts | -3.952 |
Slave | -3.811 |
oven | -3.761 |
Grande | -3.696 |
Warehouse | -3.636 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
Slave | +0.129 |
atts | +0.128 |
Grande | +0.123 |
oven | +0.122 |
Warehouse | +0.121 |
Neg logit contributions | |
stroke | -0.151 |
Abstract | -0.140 |
edIn | -0.140 |
sense | -0.139 |
stal | -0.135 |
Token | While |
Token ID | 2893 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
atts | +0.009 |
Slave | +0.009 |
oven | +0.009 |
Grande | +0.009 |
enslaved | +0.008 |
Neg logit contributions | |
stroke | -0.009 |
Abstract | -0.009 |
edIn | -0.009 |
sense | -0.009 |
stal | -0.008 |
Token | all |
Token ID | 477 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
stroke | +1.108 |
edIn | +1.028 |
Abstract | +1.025 |
sense | +1.015 |
stal | +0.990 |
Neg logit contributions | |
atts | -1.078 |
Slave | -1.058 |
oven | -1.023 |
Grande | -1.022 |
Labrador | -1.005 |
Token | three |
Token ID | 1115 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
stroke | +2.347 |
edIn | +2.181 |
Abstract | +2.170 |
sense | +2.148 |
stal | +2.093 |
Neg logit contributions | |
atts | -1.758 |
Slave | -1.750 |
oven | -1.671 |
Grande | -1.667 |
Labrador | -1.638 |