Token | .. |
Token ID | 492 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
Mug | +0.134 |
iron | +0.127 |
imus | +0.120 |
rone | +0.111 |
mia | +0.109 |
Neg logit contributions | |
Animation | -0.179 |
bj | -0.176 |
lections | -0.175 |
DAR | -0.173 |
+= | -0.173 |
Token | *) |
Token ID | 31936 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
Animation | +0.283 |
bj | +0.276 |
lections | +0.273 |
+= | +0.272 |
DAR | +0.270 |
Neg logit contributions | |
Mug | -0.313 |
iron | -0.299 |
imus | -0.287 |
rone | -0.271 |
mia | -0.266 |
Token | graph |
Token ID | 4823 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Animation | +2.562 |
bj | +2.517 |
+= | +2.500 |
lections | +2.485 |
DAR | +2.454 |
Neg logit contributions | |
Mug | -2.577 |
iron | -2.472 |
imus | -2.389 |
rone | -2.240 |
mia | -2.197 |
Token | List |
Token ID | 8053 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
Animation | +2.132 |
bj | +2.072 |
+= | +2.055 |
lections | +2.042 |
DAR | +2.003 |
Neg logit contributions | |
Mug | -3.183 |
iron | -3.059 |
imus | -2.964 |
rone | -2.817 |
mia | -2.772 |
Token | = |
Token ID | 796 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Animation | +2.455 |
+= | +2.382 |
bj | +2.362 |
lections | +2.337 |
DAR | +2.267 |
Neg logit contributions | |
Mug | -4.565 |
iron | -4.397 |
imus | -4.273 |
rone | -4.084 |
mia | -4.037 |
Token | Table |
Token ID | 8655 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Animation | +2.243 |
bj | +2.201 |
+= | +2.181 |
lections | +2.176 |
DAR | +2.154 |
Neg logit contributions | |
Mug | -2.258 |
iron | -2.163 |
imus | -2.082 |
rone | -1.956 |
mia | -1.920 |
Token | [ |
Token ID | 58 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
Animation | +3.901 |
+= | +3.776 |
lections | +3.497 |
bj | +3.471 |
CH | +3.391 |
Neg logit contributions | |
Mug | -12.120 |
iron | -11.615 |
imus | -11.613 |
rone | -11.137 |
mia | -10.957 |
Token | { |
Token ID | 1391 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
Animation | +0.199 |
bj | +0.194 |
lections | +0.192 |
+= | +0.191 |
DAR | +0.189 |
Neg logit contributions | |
Mug | -0.211 |
iron | -0.202 |
imus | -0.194 |
rone | -0.182 |
mia | -0.179 |
Token | Keys |
Token ID | 26363 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
Mug | +0.070 |
iron | +0.067 |
imus | +0.064 |
rone | +0.060 |
mia | +0.059 |
Neg logit contributions | |
Animation | -0.068 |
bj | -0.066 |
lections | -0.066 |
+= | -0.066 |
DAR | -0.065 |
Token | [ |
Token ID | 58 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Animation | +1.904 |
+= | +1.847 |
bj | +1.768 |
lections | +1.753 |
CH | +1.699 |
Neg logit contributions | |
Mug | -6.246 |
iron | -6.046 |
imus | -5.917 |
rone | -5.688 |
mia | -5.630 |
Token | search |
Token ID | 12947 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Mug | +1.339 |
iron | +1.285 |
imus | +1.219 |
rone | +1.133 |
mia | +1.117 |
Neg logit contributions | |
Animation | -1.447 |
bj | -1.400 |
lections | -1.400 |
+= | -1.394 |
DAR | -1.388 |
Token | and |
Token ID | 290 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Mug | +2.476 |
iron | +2.294 |
imus | +2.245 |
mia | +2.067 |
rone | +2.063 |
Neg logit contributions | |
Animation | -1.958 |
bj | -1.913 |
lections | -1.884 |
+= | -1.824 |
awar | -1.793 |
Token | Caribbean |
Token ID | 18020 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Mug | +1.228 |
iron | +1.152 |
imus | +1.119 |
rone | +1.068 |
throat | +1.051 |
Neg logit contributions | |
Animation | -0.745 |
bj | -0.719 |
lections | -0.702 |
+= | -0.683 |
DAR | -0.675 |
Token | States |
Token ID | 1829 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Mug | +1.644 |
iron | +1.514 |
imus | +1.456 |
rone | +1.360 |
omy | +1.354 |
Neg logit contributions | |
Animation | -1.428 |
bj | -1.417 |
lections | -1.383 |
+= | -1.349 |
awar | -1.317 |
Token | ( |
Token ID | 357 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Mug | +1.979 |
iron | +1.868 |
imus | +1.813 |
rone | +1.663 |
mia | +1.660 |
Neg logit contributions | |
Animation | -1.811 |
bj | -1.784 |
lections | -1.749 |
+= | -1.729 |
DAR | -1.711 |
Token | C |
Token ID | 34 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Animation | +0.701 |
bj | +0.692 |
lections | +0.678 |
+= | +0.677 |
DAR | +0.669 |
Neg logit contributions | |
Mug | -1.040 |
iron | -1.008 |
imus | -0.968 |
rone | -0.923 |
mia | -0.904 |
Token | EL |
Token ID | 3698 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Animation | +0.783 |
bj | +0.774 |
lections | +0.759 |
+= | +0.757 |
DAR | +0.754 |
Neg logit contributions | |
Mug | -1.047 |
iron | -1.023 |
imus | -0.981 |
rone | -0.924 |
omy | -0.910 |
Token | AC |
Token ID | 2246 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
Animation | +4.719 |
CH | +4.648 |
DAR | +4.355 |
bj | +4.353 |
+= | +4.320 |
Neg logit contributions | |
Mug | -10.962 |
iron | -10.426 |
imus | -10.345 |
rone | -9.919 |
omy | -9.680 |
Token | ) |
Token ID | 8 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Animation | +3.115 |
bj | +3.028 |
lections | +2.989 |
CH | +2.967 |
+= | +2.963 |
Neg logit contributions | |
Mug | -5.366 |
iron | -5.150 |
imus | -4.974 |
rone | -4.798 |
mia | -4.697 |
Token | held |
Token ID | 2714 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Mug | +1.865 |
iron | +1.760 |
imus | +1.702 |
rone | +1.586 |
isol | +1.581 |
Neg logit contributions | |
Animation | -1.457 |
bj | -1.442 |
lections | -1.421 |
+= | -1.393 |
DAR | -1.384 |
Token | its |
Token ID | 663 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
Mug | +1.896 |
iron | +1.760 |
imus | +1.691 |
rone | +1.568 |
throat | +1.558 |
Neg logit contributions | |
Animation | -1.963 |
bj | -1.924 |
+= | -1.870 |
lections | -1.869 |
DAR | -1.835 |
Token | first |
Token ID | 717 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
Mug | +3.807 |
iron | +3.395 |
imus | +3.349 |
rone | +3.080 |
throat | +3.080 |
Neg logit contributions | |
Animation | -4.650 |
bj | -4.593 |
lections | -4.455 |
+= | -4.412 |
ternity | -4.334 |
Token | OT |
Token ID | 2394 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
Mug | +0.126 |
iron | +0.122 |
imus | +0.116 |
rone | +0.109 |
mia | +0.108 |
Neg logit contributions | |
Animation | -0.116 |
bj | -0.115 |
lections | -0.114 |
+= | -0.114 |
DAR | -0.113 |
Token | TA |
Token ID | 5603 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
Mug | +0.522 |
iron | +0.503 |
imus | +0.485 |
rone | +0.460 |
mia | +0.451 |
Neg logit contributions | |
Animation | -0.368 |
bj | -0.359 |
lections | -0.353 |
+= | -0.349 |
DAR | -0.342 |
Token | WA |
Token ID | 15543 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
lections | +0.039 |
Animation | +0.038 |
bj | +0.037 |
+= | +0.034 |
ternity | +0.034 |
Neg logit contributions | |
Mug | -0.100 |
iron | -0.096 |
imus | -0.091 |
throat | -0.089 |
mia | -0.088 |
Token | ( |
Token ID | 357 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Animation | +1.472 |
bj | +1.443 |
lections | +1.427 |
+= | +1.423 |
DAR | +1.408 |
Neg logit contributions | |
Mug | -1.363 |
iron | -1.298 |
imus | -1.246 |
rone | -1.163 |
mia | -1.140 |
Token | Reuters |
Token ID | 12637 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Animation | +2.473 |
bj | +2.413 |
+= | +2.370 |
lections | +2.362 |
DAR | +2.361 |
Neg logit contributions | |
Mug | -2.249 |
iron | -2.137 |
imus | -2.071 |
rone | -1.920 |
mia | -1.886 |
Token | ) |
Token ID | 8 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Animation | +1.156 |
bj | +1.119 |
+= | +1.104 |
lections | +1.096 |
DAR | +1.086 |
Neg logit contributions | |
Mug | -1.958 |
iron | -1.894 |
imus | -1.840 |
rone | -1.746 |
mia | -1.720 |
Token | - |
Token ID | 532 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
+= | +5.012 |
Women | +4.981 |
Animation | +4.941 |
DAR | +4.681 |
CH | +4.647 |
Neg logit contributions | |
imus | -9.615 |
iron | -9.448 |
Mug | -9.189 |
territ | -9.062 |
mia | -8.915 |
Token | Canada |
Token ID | 3340 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
Women | +5.358 |
DAR | +5.315 |
Animation | +5.302 |
bj | +5.183 |
+= | +5.103 |
Neg logit contributions | |
iron | -6.720 |
Mug | -6.692 |
imus | -6.473 |
rone | -6.123 |
omy | -6.024 |
Token | � |
Token ID | 447 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Mug | +0.193 |
iron | +0.184 |
imus | +0.177 |
rone | +0.167 |
throat | +0.165 |
Neg logit contributions | |
Animation | -0.139 |
bj | -0.138 |
lections | -0.137 |
+= | -0.134 |
DAR | -0.132 |
Token | � |
Token ID | 247 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
Animation | +2.216 |
bj | +2.159 |
lections | +2.129 |
+= | +2.125 |
DAR | +2.092 |
Neg logit contributions | |
Mug | -2.694 |
iron | -2.581 |
imus | -2.490 |
rone | -2.361 |
mia | -2.304 |
Token | s |
Token ID | 82 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
Animation | +1.540 |
bj | +1.503 |
lections | +1.484 |
+= | +1.482 |
DAR | +1.464 |
Neg logit contributions | |
Mug | -1.872 |
iron | -1.794 |
imus | -1.730 |
rone | -1.631 |
mia | -1.604 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Animation | +1.124 |
bj | +1.099 |
lections | +1.090 |
+= | +1.082 |
DAR | +1.071 |
Neg logit contributions | |
Mug | -1.280 |
iron | -1.226 |
imus | -1.179 |
rone | -1.110 |
mia | -1.091 |
Token | � |
Token ID | 447 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
Animation | +0.575 |
bj | +0.562 |
lections | +0.559 |
+= | +0.555 |
DAR | +0.545 |
Neg logit contributions | |
Mug | -0.739 |
iron | -0.710 |
imus | -0.683 |
rone | -0.647 |
mia | -0.638 |
Token | � |
Token ID | 251 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
Animation | +0.148 |
bj | +0.144 |
lections | +0.143 |
+= | +0.141 |
DAR | +0.141 |
Neg logit contributions | |
Mug | -0.144 |
iron | -0.139 |
imus | -0.132 |
rone | -0.123 |
mia | -0.122 |
Token | says |
Token ID | 1139 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
Animation | +0.591 |
bj | +0.578 |
lections | +0.576 |
+= | +0.572 |
DAR | +0.561 |
Neg logit contributions | |
Mug | -0.628 |
iron | -0.599 |
imus | -0.573 |
rone | -0.540 |
mia | -0.531 |
Token | N |
Token ID | 399 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Animation | +2.743 |
bj | +2.694 |
DAR | +2.641 |
+= | +2.640 |
lections | +2.637 |
Neg logit contributions | |
Mug | -3.038 |
iron | -2.938 |
imus | -2.837 |
rone | -2.651 |
mia | -2.607 |
Token | ett |
Token ID | 3087 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Animation | +1.718 |
bj | +1.677 |
lections | +1.648 |
+= | +1.643 |
DAR | +1.608 |
Neg logit contributions | |
Mug | -2.862 |
iron | -2.735 |
imus | -2.656 |
rone | -2.525 |
mia | -2.488 |
Token | les |
Token ID | 829 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
lections | +3.886 |
bj | +3.806 |
Animation | +3.776 |
+= | +3.643 |
CH | +3.510 |
Neg logit contributions | |
Mug | -10.992 |
iron | -10.027 |
imus | -9.875 |
metic | -9.612 |
throat | -9.574 |
Token | . |
Token ID | 13 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
Animation | +1.547 |
bj | +1.511 |
lections | +1.490 |
+= | +1.487 |
DAR | +1.469 |
Neg logit contributions | |
Mug | -1.907 |
iron | -1.827 |
imus | -1.764 |
rone | -1.663 |
mia | -1.634 |
Token | This |
Token ID | 770 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Mug | +0.315 |
iron | +0.295 |
imus | +0.285 |
rone | +0.269 |
mia | +0.263 |
Neg logit contributions | |
Animation | -0.282 |
lections | -0.281 |
bj | -0.279 |
+= | -0.271 |
DAR | -0.267 |
Token | occurs |
Token ID | 8833 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Animation | +1.643 |
bj | +1.607 |
lections | +1.588 |
+= | +1.580 |
DAR | +1.562 |
Neg logit contributions | |
Mug | -1.951 |
iron | -1.866 |
imus | -1.801 |
rone | -1.697 |
mia | -1.668 |
Token | as |
Token ID | 355 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
Animation | +1.089 |
bj | +1.065 |
lections | +1.052 |
+= | +1.047 |
DAR | +1.035 |
Neg logit contributions | |
Mug | -1.311 |
iron | -1.256 |
imus | -1.211 |
rone | -1.142 |
mia | -1.121 |
Token | result |
Token ID | 1255 |
Feature activation | -8.99e-05 |
Pos logit contributions | |
Animation | +1.048 |
bj | +1.024 |
lections | +1.012 |
+= | +1.010 |
DAR | +0.994 |
Neg logit contributions | |
Mug | -0.897 |
iron | -0.844 |
imus | -0.809 |
rone | -0.755 |
throat | -0.740 |
Token | of |
Token ID | 286 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
Mug | +0.001 |
iron | +0.001 |
imus | +0.001 |
rone | +0.001 |
mia | +0.001 |
Neg logit contributions | |
Animation | -0.000 |
bj | -0.000 |
lections | -0.000 |
+= | -0.000 |
DAR | -0.000 |
Token | supply |
Token ID | 5127 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Mug | +0.534 |
iron | +0.501 |
imus | +0.484 |
rone | +0.455 |
throat | +0.448 |
Neg logit contributions | |
Animation | -0.535 |
bj | -0.524 |
+= | -0.515 |
lections | -0.513 |
DAR | -0.502 |
Token | - |
Token ID | 12 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
Mug | +1.812 |
iron | +1.715 |
imus | +1.639 |
rone | +1.558 |
isol | +1.555 |
Neg logit contributions | |
Animation | -1.634 |
bj | -1.605 |
lections | -1.575 |
+= | -1.562 |
DAR | -1.537 |
Token | and |
Token ID | 392 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
Animation | +3.318 |
bj | +3.210 |
+= | +3.204 |
lections | +3.178 |
DAR | +3.145 |
Neg logit contributions | |
Mug | -4.858 |
iron | -4.533 |
imus | -4.464 |
omy | -4.199 |
throat | -4.185 |
Token | - |
Token ID | 12 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Animation | +3.373 |
+= | +3.244 |
DAR | +3.226 |
bj | +3.223 |
Women | +3.193 |
Neg logit contributions | |
Mug | -5.619 |
iron | -5.356 |
imus | -5.211 |
rone | -4.942 |
omy | -4.837 |
Token | demand |
Token ID | 28550 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
weight | +7.091 |
Animation | +7.073 |
bj | +6.931 |
CH | +6.886 |
+= | +6.776 |
Neg logit contributions | |
Mug | -7.557 |
iron | -6.608 |
imus | -6.539 |
throat | -6.345 |
isol | -6.206 |
Token | fundamentals |
Token ID | 33099 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Animation | +0.035 |
bj | +0.035 |
lections | +0.034 |
+= | +0.034 |
DAR | +0.034 |
Neg logit contributions | |
Mug | -0.037 |
iron | -0.035 |
imus | -0.034 |
rone | -0.032 |
mia | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Animation | +2.598 |
bj | +2.541 |
lections | +2.507 |
+= | +2.494 |
DAR | +2.473 |
Neg logit contributions | |
Mug | -3.186 |
iron | -3.057 |
imus | -2.967 |
rone | -2.816 |
omy | -2.736 |
Token | More |
Token ID | 3125 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Animation | +1.518 |
bj | +1.477 |
+= | +1.456 |
lections | +1.452 |
DAR | +1.447 |
Neg logit contributions | |
Mug | -2.061 |
iron | -1.990 |
imus | -1.927 |
rone | -1.821 |
mia | -1.795 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Animation | +1.261 |
bj | +1.238 |
lections | +1.222 |
+= | +1.219 |
DAR | +1.205 |
Neg logit contributions | |
Mug | -1.159 |
iron | -1.102 |
imus | -1.059 |
rone | -0.990 |
mia | -0.968 |
Token | ( |
Token ID | 357 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
Mug | +1.183 |
iron | +1.128 |
imus | +1.081 |
rone | +1.009 |
mia | +0.987 |
Neg logit contributions | |
Animation | -1.248 |
bj | -1.228 |
lections | -1.213 |
+= | -1.205 |
DAR | -1.191 |
Token | 13 |
Token ID | 1485 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Mug | +1.308 |
iron | +1.300 |
imus | +1.203 |
rone | +1.118 |
omy | +1.083 |
Neg logit contributions | |
Animation | -2.006 |
bj | -1.964 |
lections | -1.954 |
+= | -1.943 |
DAR | -1.941 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Mug | +1.071 |
iron | +1.030 |
imus | +0.984 |
rone | +0.930 |
mia | +0.920 |
Neg logit contributions | |
Animation | -0.903 |
lections | -0.883 |
bj | -0.879 |
+= | -0.854 |
DAR | -0.854 |
Token | 5 |
Token ID | 642 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
Animation | +0.749 |
bj | +0.729 |
lections | +0.718 |
+= | +0.711 |
DAR | +0.702 |
Neg logit contributions | |
Mug | -1.243 |
iron | -1.194 |
imus | -1.158 |
rone | -1.101 |
mia | -1.084 |
Token | )) |
Token ID | 4008 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
Mug | +0.242 |
iron | +0.229 |
imus | +0.218 |
rone | +0.202 |
mia | +0.197 |
Neg logit contributions | |
Animation | -0.326 |
bj | -0.320 |
lections | -0.316 |
+= | -0.316 |
DAR | -0.313 |
Token | sq |
Token ID | 19862 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
+= | +4.006 |
Animation | +3.962 |
bj | +3.920 |
lections | +3.867 |
DAR | +3.829 |
Neg logit contributions | |
Mug | -4.597 |
iron | -4.422 |
imus | -4.320 |
rone | -4.044 |
mia | -3.906 |
Token | K |
Token ID | 42 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Animation | +4.776 |
+= | +4.669 |
CH | +4.652 |
bj | +4.366 |
++) | +4.316 |
Neg logit contributions | |
Mug | -9.252 |
imus | -9.041 |
iron | -9.025 |
metic | -8.842 |
throat | -8.659 |
Token | ernel |
Token ID | 7948 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
Animation | +0.723 |
bj | +0.705 |
+= | +0.695 |
lections | +0.695 |
DAR | +0.676 |
Neg logit contributions | |
Mug | -1.203 |
iron | -1.155 |
imus | -1.119 |
rone | -1.058 |
throat | -1.048 |
Token | = |
Token ID | 796 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
+= | +2.033 |
Animation | +1.850 |
bj | +1.720 |
++) | +1.611 |
CH | +1.602 |
Neg logit contributions | |
Mug | -8.971 |
iron | -8.664 |
imus | -8.545 |
rone | -8.361 |
throat | -8.334 |
Token | c |
Token ID | 269 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Animation | +0.475 |
bj | +0.465 |
lections | +0.460 |
+= | +0.459 |
DAR | +0.455 |
Neg logit contributions | |
Mug | -0.454 |
iron | -0.433 |
imus | -0.416 |
rone | -0.389 |
mia | -0.381 |
Token | v |
Token ID | 85 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Animation | +2.016 |
bj | +2.002 |
+= | +1.945 |
lections | +1.938 |
CH | +1.851 |
Neg logit contributions | |
Mug | -4.390 |
iron | -4.163 |
imus | -4.081 |
rone | -3.905 |
throat | -3.860 |
Token | HA |
Token ID | 7801 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
Animation | +0.196 |
bj | +0.193 |
lections | +0.191 |
+= | +0.191 |
DAR | +0.189 |
Neg logit contributions | |
Mug | -0.211 |
iron | -0.204 |
imus | -0.195 |
rone | -0.183 |
mia | -0.180 |
Token | V |
Token ID | 53 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Animation | +1.940 |
bj | +1.891 |
+= | +1.859 |
lections | +1.858 |
DAR | +1.841 |
Neg logit contributions | |
Mug | -2.769 |
iron | -2.649 |
imus | -2.589 |
rone | -2.446 |
mia | -2.404 |
Token | ANA |
Token ID | 31574 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Mug | +2.206 |
iron | +2.163 |
imus | +2.057 |
rone | +1.948 |
Rog | +1.940 |
Neg logit contributions | |
Animation | -1.439 |
lections | -1.390 |
bj | -1.379 |
+= | -1.347 |
DAR | -1.327 |
Token | ( |
Token ID | 357 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Animation | +0.767 |
bj | +0.753 |
lections | +0.745 |
+= | +0.738 |
DAR | +0.728 |
Neg logit contributions | |
Mug | -0.833 |
iron | -0.793 |
imus | -0.761 |
rone | -0.719 |
mia | -0.704 |
Token | Reuters |
Token ID | 12637 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Animation | +2.119 |
bj | +2.072 |
+= | +2.041 |
lections | +2.038 |
DAR | +2.021 |
Neg logit contributions | |
Mug | -1.928 |
iron | -1.832 |
imus | -1.770 |
rone | -1.643 |
mia | -1.610 |
Token | ) |
Token ID | 8 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Animation | +0.763 |
bj | +0.741 |
lections | +0.729 |
+= | +0.729 |
DAR | +0.718 |
Neg logit contributions | |
Mug | -1.244 |
iron | -1.199 |
imus | -1.163 |
rone | -1.104 |
mia | -1.087 |
Token | - |
Token ID | 532 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
+= | +4.808 |
Animation | +4.744 |
Women | +4.727 |
DAR | +4.519 |
CH | +4.472 |
Neg logit contributions | |
imus | -8.503 |
iron | -8.405 |
Mug | -8.257 |
territ | -7.950 |
mia | -7.895 |
Token | Latin |
Token ID | 9133 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Animation | +5.283 |
Women | +5.236 |
DAR | +5.207 |
bj | +5.150 |
+= | +5.072 |
Neg logit contributions | |
iron | -6.460 |
Mug | -6.391 |
imus | -6.303 |
omy | -5.846 |
rone | -5.827 |
Token | American |
Token ID | 1605 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
Animation | +1.478 |
bj | +1.453 |
lections | +1.437 |
+= | +1.425 |
DAR | +1.410 |
Neg logit contributions | |
Mug | -1.476 |
iron | -1.397 |
imus | -1.348 |
rone | -1.256 |
mia | -1.244 |
Token | and |
Token ID | 290 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
Animation | +0.339 |
bj | +0.336 |
lections | +0.332 |
+= | +0.329 |
DAR | +0.323 |
Neg logit contributions | |
Mug | -0.263 |
iron | -0.244 |
imus | -0.233 |
rone | -0.216 |
mia | -0.212 |
Token | Caribbean |
Token ID | 18020 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Mug | +0.294 |
iron | +0.274 |
imus | +0.265 |
throat | +0.251 |
rone | +0.251 |
Neg logit contributions | |
Animation | -0.214 |
bj | -0.208 |
lections | -0.206 |
+= | -0.201 |
DAR | -0.195 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Animation | +3.001 |
bj | +2.935 |
+= | +2.919 |
lections | +2.865 |
CH | +2.843 |
Neg logit contributions | |
Mug | -2.505 |
iron | -2.337 |
imus | -2.283 |
rone | -2.112 |
throat | -2.092 |
Token | . |
Token ID | 13 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
Animation | +2.208 |
bj | +2.160 |
+= | +2.153 |
lections | +2.099 |
DAR | +2.082 |
Neg logit contributions | |
Mug | -3.003 |
iron | -2.870 |
imus | -2.801 |
rone | -2.657 |
throat | -2.607 |
Token | get |
Token ID | 1136 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
Animation | +3.773 |
bj | +3.664 |
+= | +3.633 |
CH | +3.613 |
lections | +3.558 |
Neg logit contributions | |
Mug | -3.884 |
iron | -3.598 |
imus | -3.530 |
throat | -3.357 |
rone | -3.356 |
Token | Struct |
Token ID | 44909 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
Animation | +2.928 |
+= | +2.809 |
bj | +2.799 |
lections | +2.749 |
CH | +2.733 |
Neg logit contributions | |
Mug | -2.841 |
iron | -2.738 |
imus | -2.641 |
rone | -2.505 |
throat | -2.469 |
Token | uring |
Token ID | 870 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Mug | +0.068 |
iron | +0.064 |
imus | +0.060 |
rone | +0.053 |
omy | +0.052 |
Neg logit contributions | |
Animation | -0.146 |
bj | -0.144 |
lections | -0.142 |
+= | -0.142 |
DAR | -0.142 |
Token | Element |
Token ID | 20180 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Animation | +0.988 |
bj | +0.965 |
+= | +0.956 |
lections | +0.955 |
DAR | +0.944 |
Neg logit contributions | |
Mug | -0.852 |
iron | -0.809 |
imus | -0.776 |
rone | -0.724 |
mia | -0.708 |
Token | ( |
Token ID | 7 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
Animation | +2.966 |
+= | +2.840 |
bj | +2.738 |
CH | +2.657 |
weight | +2.491 |
Neg logit contributions | |
Mug | -10.641 |
imus | -10.170 |
iron | -10.006 |
metic | -9.896 |
throat | -9.844 |
Token | cv |
Token ID | 33967 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Animation | +2.746 |
bj | +2.719 |
lections | +2.669 |
+= | +2.664 |
DAR | +2.622 |
Neg logit contributions | |
Mug | -2.640 |
iron | -2.472 |
imus | -2.402 |
rone | -2.235 |
throat | -2.201 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Animation | +1.861 |
bj | +1.824 |
+= | +1.806 |
lections | +1.798 |
DAR | +1.780 |
Neg logit contributions | |
Mug | -1.425 |
iron | -1.341 |
imus | -1.289 |
rone | -1.192 |
throat | -1.163 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Animation | +0.779 |
bj | +0.762 |
lections | +0.752 |
+= | +0.749 |
DAR | +0.741 |
Neg logit contributions | |
Mug | -0.926 |
iron | -0.887 |
imus | -0.855 |
rone | -0.805 |
mia | -0.792 |
Token | M |
Token ID | 44 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
Animation | +1.484 |
bj | +1.455 |
lections | +1.439 |
+= | +1.437 |
DAR | +1.424 |
Neg logit contributions | |
Mug | -1.180 |
iron | -1.119 |
imus | -1.071 |
rone | -0.993 |
mia | -0.970 |
Token | ent |
Token ID | 298 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Animation | +0.816 |
bj | +0.799 |
lections | +0.794 |
+= | +0.790 |
DAR | +0.776 |
Neg logit contributions | |
Mug | -1.031 |
iron | -0.983 |
imus | -0.952 |
rone | -0.900 |
mia | -0.882 |
Token | , |
Token ID | 11 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Animation | +0.672 |
bj | +0.656 |
lections | +0.646 |
+= | +0.645 |
DAR | +0.637 |
Neg logit contributions | |
Mug | -0.898 |
iron | -0.861 |
imus | -0.833 |
rone | -0.787 |
mia | -0.774 |
Token | eastern |
Token ID | 10183 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
Mug | +1.314 |
iron | +1.289 |
imus | +1.203 |
rone | +1.143 |
isol | +1.130 |
Neg logit contributions | |
Animation | -1.500 |
bj | -1.480 |
lections | -1.459 |
CH | -1.426 |
+= | -1.423 |
Token | � |
Token ID | 564 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
Animation | +4.216 |
+= | +4.064 |
bj | +4.031 |
lections | +4.026 |
DAR | +3.954 |
Neg logit contributions | |
Mug | -7.476 |
iron | -7.182 |
imus | -6.916 |
rone | -6.646 |
Rog | -6.519 |
Token | � |
Token ID | 246 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
Animation | +0.610 |
bj | +0.598 |
+= | +0.591 |
lections | +0.590 |
DAR | +0.582 |
Neg logit contributions | |
Mug | -0.565 |
iron | -0.534 |
imus | -0.515 |
rone | -0.479 |
mia | -0.470 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
bj | +2.726 |
Animation | +2.660 |
+= | +2.587 |
lections | +2.555 |
CH | +2.511 |
Neg logit contributions | |
Mug | -3.746 |
imus | -3.391 |
iron | -3.388 |
rone | -3.201 |
throat | -3.183 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
bj | +4.754 |
+= | +4.411 |
Animation | +4.358 |
weight | +4.329 |
awar | +4.244 |
Neg logit contributions | |
Mug | -8.924 |
imus | -7.904 |
Lime | -7.721 |
iron | -7.667 |
isol | -7.637 |
Token | ians |
Token ID | 1547 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
Animation | +1.286 |
bj | +1.268 |
lections | +1.255 |
+= | +1.253 |
DAR | +1.242 |
Neg logit contributions | |
Mug | -0.664 |
iron | -0.616 |
imus | -0.581 |
rone | -0.523 |
mia | -0.508 |
Token | � |
Token ID | 447 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Animation | +2.374 |
bj | +2.268 |
lections | +2.247 |
+= | +2.227 |
DAR | +2.174 |
Neg logit contributions | |
Mug | -4.663 |
iron | -4.459 |
imus | -4.326 |
rone | -4.131 |
throat | -4.068 |
Token | � |
Token ID | 247 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
Animation | +0.984 |
bj | +0.961 |
lections | +0.948 |
+= | +0.943 |
DAR | +0.934 |
Neg logit contributions | |
Mug | -1.273 |
iron | -1.223 |
imus | -1.180 |
rone | -1.117 |
mia | -1.097 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Mug | +0.075 |
iron | +0.073 |
imus | +0.070 |
rone | +0.066 |
mia | +0.064 |
Neg logit contributions | |
Animation | -0.067 |
bj | -0.065 |
lections | -0.064 |
+= | -0.064 |
DAR | -0.064 |
Token | 12 |
Token ID | 1105 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Animation | +3.144 |
+= | +3.108 |
bj | +3.106 |
lections | +3.068 |
DAR | +3.065 |
Neg logit contributions | |
Mug | -3.499 |
iron | -3.311 |
imus | -3.192 |
rone | -3.022 |
mia | -3.017 |
Token | 13 |
Token ID | 1511 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
Animation | +1.208 |
bj | +1.193 |
+= | +1.185 |
lections | +1.179 |
DAR | +1.172 |
Neg logit contributions | |
Mug | -1.078 |
iron | -1.020 |
imus | -0.980 |
rone | -0.919 |
mia | -0.910 |
Token | 14 |
Token ID | 1478 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
Animation | +2.896 |
bj | +2.860 |
+= | +2.843 |
DAR | +2.819 |
lections | +2.806 |
Neg logit contributions | |
Mug | -3.373 |
iron | -3.198 |
imus | -3.087 |
rone | -2.950 |
mia | -2.905 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
Animation | +2.769 |
bj | +2.740 |
+= | +2.712 |
lections | +2.692 |
DAR | +2.672 |
Neg logit contributions | |
Mug | -3.729 |
iron | -3.553 |
imus | -3.449 |
rone | -3.262 |
mia | -3.231 |
Token | 16 |
Token ID | 1467 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
Animation | +4.253 |
DAR | +4.231 |
+= | +4.231 |
bj | +4.229 |
lections | +4.093 |
Neg logit contributions | |
Mug | -5.871 |
iron | -5.554 |
imus | -5.396 |
mia | -5.110 |
rone | -5.095 |
Token | 17 |
Token ID | 1596 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Animation | +3.113 |
+= | +3.093 |
bj | +3.091 |
DAR | +3.065 |
lections | +3.039 |
Neg logit contributions | |
Mug | -5.318 |
iron | -5.136 |
imus | -4.914 |
rone | -4.727 |
mia | -4.722 |
Token | 18 |
Token ID | 1248 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
Animation | +4.771 |
+= | +4.755 |
DAR | +4.740 |
bj | +4.718 |
CH | +4.615 |
Neg logit contributions | |
Mug | -8.375 |
iron | -7.977 |
imus | -7.685 |
rone | -7.506 |
mia | -7.312 |
Token | 19 |
Token ID | 678 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
bj | +3.968 |
Animation | +3.949 |
+= | +3.921 |
CH | +3.879 |
DAR | +3.833 |
Neg logit contributions | |
Mug | -4.017 |
iron | -3.768 |
imus | -3.724 |
mia | -3.454 |
rone | -3.446 |
Token | 20 |
Token ID | 1160 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
Animation | +3.733 |
bj | +3.673 |
+= | +3.654 |
lections | +3.569 |
DAR | +3.556 |
Neg logit contributions | |
Mug | -4.945 |
iron | -4.738 |
imus | -4.656 |
rone | -4.364 |
mia | -4.345 |
Token | 21 |
Token ID | 2310 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Animation | +3.789 |
bj | +3.761 |
+= | +3.759 |
DAR | +3.683 |
lections | +3.656 |
Neg logit contributions | |
Mug | -4.401 |
iron | -4.208 |
imus | -4.100 |
mia | -3.867 |
rone | -3.804 |
Token | 22 |
Token ID | 2534 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Animation | +3.448 |
+= | +3.395 |
bj | +3.376 |
DAR | +3.325 |
lections | +3.316 |
Neg logit contributions | |
Mug | -4.313 |
iron | -4.129 |
imus | -4.010 |
mia | -3.779 |
rone | -3.762 |
Token | BR |
Token ID | 11473 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
Animation | +0.076 |
bj | +0.075 |
lections | +0.075 |
+= | +0.074 |
DAR | +0.074 |
Neg logit contributions | |
Mug | -0.083 |
iron | -0.080 |
imus | -0.076 |
rone | -0.072 |
mia | -0.071 |
Token | USS |
Token ID | 32835 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Animation | +2.633 |
bj | +2.562 |
+= | +2.532 |
lections | +2.514 |
DAR | +2.501 |
Neg logit contributions | |
Mug | -3.424 |
iron | -3.298 |
imus | -3.201 |
rone | -3.024 |
mia | -2.970 |
Token | ELS |
Token ID | 37142 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Animation | +0.626 |
lections | +0.608 |
bj | +0.607 |
+= | +0.589 |
DAR | +0.567 |
Neg logit contributions | |
Mug | -1.383 |
iron | -1.322 |
imus | -1.280 |
rone | -1.221 |
omy | -1.210 |
Token | ( |
Token ID | 357 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Animation | +2.334 |
bj | +2.283 |
+= | +2.261 |
lections | +2.252 |
DAR | +2.239 |
Neg logit contributions | |
Mug | -2.337 |
iron | -2.230 |
imus | -2.155 |
rone | -2.011 |
mia | -1.982 |
Token | Reuters |
Token ID | 12637 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Animation | +2.119 |
bj | +2.072 |
+= | +2.037 |
lections | +2.027 |
DAR | +2.017 |
Neg logit contributions | |
Mug | -1.931 |
iron | -1.836 |
imus | -1.782 |
rone | -1.650 |
mia | -1.625 |
Token | ) |
Token ID | 8 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Animation | +0.616 |
bj | +0.600 |
lections | +0.591 |
+= | +0.588 |
DAR | +0.580 |
Neg logit contributions | |
Mug | -0.992 |
iron | -0.955 |
imus | -0.925 |
rone | -0.879 |
mia | -0.865 |
Token | - |
Token ID | 532 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
+= | +4.763 |
Animation | +4.723 |
Women | +4.668 |
DAR | +4.492 |
CH | +4.450 |
Neg logit contributions | |
imus | -8.372 |
iron | -8.300 |
Mug | -8.170 |
territ | -7.860 |
mia | -7.802 |
Token | The |
Token ID | 383 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Animation | +5.094 |
Women | +5.080 |
DAR | +5.054 |
bj | +5.011 |
+= | +4.889 |
Neg logit contributions | |
iron | -5.705 |
Mug | -5.652 |
imus | -5.529 |
mia | -5.150 |
omy | -5.119 |
Token | world |
Token ID | 995 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
Animation | +2.373 |
bj | +2.324 |
lections | +2.292 |
+= | +2.287 |
DAR | +2.275 |
Neg logit contributions | |
Mug | -2.435 |
iron | -2.341 |
imus | -2.252 |
rone | -2.107 |
mia | -2.073 |
Token | � |
Token ID | 447 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Animation | +0.157 |
lections | +0.153 |
bj | +0.153 |
+= | +0.152 |
DAR | +0.148 |
Neg logit contributions | |
Mug | -0.221 |
iron | -0.211 |
imus | -0.204 |
rone | -0.193 |
throat | -0.191 |
Token | � |
Token ID | 247 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Animation | +1.309 |
bj | +1.280 |
lections | +1.263 |
+= | +1.261 |
DAR | +1.245 |
Neg logit contributions | |
Mug | -1.493 |
iron | -1.428 |
imus | -1.378 |
rone | -1.297 |
mia | -1.272 |
Token | United |
Token ID | 1578 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Mug | +0.141 |
iron | +0.135 |
imus | +0.128 |
rone | +0.121 |
mia | +0.119 |
Neg logit contributions | |
Animation | -0.113 |
bj | -0.111 |
lections | -0.109 |
+= | -0.109 |
DAR | -0.107 |
Token | Supporters |
Token ID | 39995 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
Animation | +0.922 |
bj | +0.902 |
lections | +0.889 |
+= | +0.880 |
DAR | +0.869 |
Neg logit contributions | |
Mug | -1.263 |
iron | -1.208 |
imus | -1.166 |
rone | -1.101 |
mia | -1.086 |
Token | Trust |
Token ID | 9870 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Mug | +0.223 |
iron | +0.211 |
imus | +0.203 |
rone | +0.189 |
omy | +0.185 |
Neg logit contributions | |
Animation | -0.207 |
bj | -0.202 |
lections | -0.198 |
+= | -0.198 |
DAR | -0.195 |
Token | ( |
Token ID | 357 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Animation | +0.663 |
bj | +0.646 |
lections | +0.637 |
+= | +0.636 |
DAR | +0.629 |
Neg logit contributions | |
Mug | -0.795 |
iron | -0.761 |
imus | -0.735 |
rone | -0.691 |
mia | -0.677 |
Token | N |
Token ID | 45 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
Mug | +1.280 |
iron | +1.237 |
imus | +1.178 |
rone | +1.112 |
mia | +1.091 |
Neg logit contributions | |
Animation | -1.117 |
bj | -1.100 |
lections | -1.098 |
+= | -1.093 |
DAR | -1.082 |
Token | UST |
Token ID | 7759 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Animation | +0.350 |
bj | +0.343 |
DAR | +0.337 |
+= | +0.336 |
lections | +0.336 |
Neg logit contributions | |
Mug | -0.382 |
iron | -0.372 |
imus | -0.356 |
rone | -0.329 |
omy | -0.327 |
Token | ), |
Token ID | 828 |
Feature activation | -1.68e-03 |
Pos logit contributions | |
Animation | +5.291 |
lections | +5.242 |
CH | +5.190 |
bj | +5.142 |
Women | +5.091 |
Neg logit contributions | |
Mug | -7.998 |
iron | -7.560 |
imus | -7.443 |
mia | -7.090 |
rone | -6.939 |
Token | N |
Token ID | 399 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
Mug | +0.011 |
iron | +0.010 |
imus | +0.010 |
rone | +0.009 |
mia | +0.009 |
Neg logit contributions | |
Animation | -0.011 |
bj | -0.010 |
lections | -0.010 |
+= | -0.010 |
DAR | -0.010 |
Token | UFC |
Token ID | 44534 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
Mug | +0.579 |
iron | +0.561 |
imus | +0.537 |
rone | +0.506 |
omy | +0.500 |
Neg logit contributions | |
Animation | -0.462 |
bj | -0.454 |
+= | -0.446 |
DAR | -0.444 |
lections | -0.443 |
Token | Fans |
Token ID | 24964 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
Animation | +2.420 |
bj | +2.360 |
lections | +2.334 |
+= | +2.323 |
DAR | +2.294 |
Neg logit contributions | |
Mug | -3.183 |
iron | -3.059 |
imus | -2.960 |
rone | -2.796 |
mia | -2.757 |
Token | United |
Token ID | 1578 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
Animation | +0.154 |
bj | +0.150 |
+= | +0.148 |
lections | +0.147 |
DAR | +0.146 |
Neg logit contributions | |
Mug | -0.188 |
iron | -0.179 |
imus | -0.174 |
rone | -0.162 |
mia | -0.159 |
Token | Story |
Token ID | 8362 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Animation | +0.178 |
bj | +0.175 |
lections | +0.174 |
+= | +0.173 |
DAR | +0.170 |
Neg logit contributions | |
Mug | -0.104 |
iron | -0.095 |
imus | -0.091 |
rone | -0.082 |
mia | -0.080 |
Token | Send |
Token ID | 16290 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
+= | +2.693 |
Animation | +2.666 |
DAR | +2.648 |
Women | +2.624 |
bj | +2.613 |
Neg logit contributions | |
iron | -3.416 |
Mug | -3.372 |
imus | -3.315 |
rone | -3.218 |
mia | -3.109 |
Token | email |
Token ID | 3053 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Women | +2.668 |
DAR | +2.664 |
bj | +2.583 |
+= | +2.503 |
Animation | +2.461 |
Neg logit contributions | |
iron | -7.235 |
Mug | -7.009 |
imus | -6.954 |
rone | -6.907 |
omy | -6.858 |
Token | to |
Token ID | 284 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
+= | +4.360 |
Animation | +4.285 |
bj | +4.216 |
DAR | +4.187 |
lections | +4.184 |
Neg logit contributions | |
Mug | -8.259 |
iron | -8.125 |
imus | -7.809 |
omy | -7.521 |
rone | -7.482 |
Token | this |
Token ID | 428 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Animation | +2.387 |
lections | +2.356 |
bj | +2.318 |
DAR | +2.309 |
Women | +2.279 |
Neg logit contributions | |
Mug | -3.049 |
iron | -2.970 |
imus | -2.775 |
rone | -2.661 |
mia | -2.632 |
Token | address |
Token ID | 2209 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Animation | +0.977 |
bj | +0.973 |
lections | +0.970 |
+= | +0.956 |
DAR | +0.951 |
Neg logit contributions | |
Mug | -1.207 |
iron | -1.162 |
imus | -1.106 |
rone | -1.053 |
ebted | -1.031 |
Token | Enter |
Token ID | 6062 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
DAR | +6.216 |
Women | +6.173 |
+= | +6.162 |
lections | +6.050 |
bj | +6.027 |
Neg logit contributions | |
iron | -6.824 |
Mug | -6.819 |
omy | -6.444 |
imus | -6.427 |
ebted | -6.316 |
Token | Your |
Token ID | 3406 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Animation | +1.693 |
+= | +1.640 |
bj | +1.637 |
lections | +1.633 |
Women | +1.625 |
Neg logit contributions | |
Mug | -1.938 |
iron | -1.894 |
imus | -1.819 |
rone | -1.706 |
omy | -1.659 |
Token | Name |
Token ID | 6530 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Animation | +2.416 |
lections | +2.371 |
+= | +2.357 |
Women | +2.355 |
DAR | +2.338 |
Neg logit contributions | |
Mug | -2.167 |
iron | -2.155 |
imus | -1.989 |
rone | -1.856 |
throat | -1.846 |
Token | Add |
Token ID | 3060 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
+= | +3.864 |
Animation | +3.855 |
Women | +3.848 |
Architects | +3.682 |
bj | +3.680 |
Neg logit contributions | |
iron | -8.526 |
Mug | -8.323 |
imus | -8.068 |
ebted | -7.939 |
rone | -7.893 |
Token | a |
Token ID | 257 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
Animation | +3.344 |
lections | +3.283 |
Women | +3.243 |
DAR | +3.235 |
+= | +3.222 |
Neg logit contributions | |
Mug | -5.491 |
iron | -5.426 |
imus | -5.210 |
rone | -5.068 |
throat | -4.929 |
Token | = |
Token ID | 796 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Animation | +0.726 |
bj | +0.694 |
+= | +0.679 |
lections | +0.672 |
DAR | +0.655 |
Neg logit contributions | |
Mug | -2.362 |
iron | -2.290 |
imus | -2.235 |
rone | -2.146 |
mia | -2.118 |
Token | New |
Token ID | 968 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Animation | +2.205 |
+= | +2.125 |
Women | +2.078 |
bj | +2.044 |
DAR | +2.043 |
Neg logit contributions | |
Mug | -6.493 |
iron | -6.461 |
imus | -6.280 |
rone | -6.038 |
throat | -6.010 |
Token | - |
Token ID | 12 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
Animation | +0.814 |
bj | +0.795 |
lections | +0.784 |
+= | +0.782 |
DAR | +0.772 |
Neg logit contributions | |
Mug | -1.055 |
iron | -1.011 |
imus | -0.977 |
rone | -0.923 |
mia | -0.907 |
Token | Object |
Token ID | 10267 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Animation | +2.579 |
+= | +2.394 |
bj | +2.382 |
CH | +2.356 |
++) | +2.277 |
Neg logit contributions | |
Mug | -4.518 |
imus | -4.268 |
iron | -4.225 |
throat | -4.038 |
rone | -4.001 |
Token | System |
Token ID | 4482 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
Mug | +1.168 |
iron | +1.046 |
imus | +0.987 |
rone | +0.869 |
omy | +0.853 |
Neg logit contributions | |
Animation | -2.310 |
bj | -2.309 |
lections | -2.277 |
+= | -2.249 |
ternity | -2.235 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Animation | +3.085 |
+= | +3.002 |
bj | +2.972 |
CH | +2.876 |
Women | +2.865 |
Neg logit contributions | |
Mug | -4.686 |
iron | -4.457 |
imus | -4.399 |
rone | -4.171 |
throat | -4.129 |
Token | Draw |
Token ID | 25302 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Animation | +3.416 |
+= | +2.892 |
CH | +2.834 |
bj | +2.780 |
Women | +2.711 |
Neg logit contributions | |
Mug | -10.215 |
imus | -9.886 |
iron | -9.700 |
metic | -9.614 |
throat | -9.591 |
Token | ing |
Token ID | 278 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Animation | +0.682 |
bj | +0.664 |
lections | +0.655 |
+= | +0.654 |
DAR | +0.643 |
Neg logit contributions | |
Mug | -0.916 |
iron | -0.876 |
imus | -0.850 |
rone | -0.804 |
mia | -0.789 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Animation | +0.703 |
bj | +0.687 |
lections | +0.677 |
+= | +0.677 |
DAR | +0.668 |
Neg logit contributions | |
Mug | -0.847 |
iron | -0.811 |
imus | -0.783 |
rone | -0.738 |
mia | -0.725 |
Token | Rect |
Token ID | 45474 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
Animation | +1.599 |
bj | +1.520 |
+= | +1.510 |
lections | +1.493 |
DAR | +1.462 |
Neg logit contributions | |
Mug | -2.431 |
iron | -2.325 |
imus | -2.266 |
rone | -2.145 |
mia | -2.122 |
Token | angle |
Token ID | 9248 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Animation | +1.769 |
bj | +1.723 |
+= | +1.713 |
lections | +1.693 |
CH | +1.612 |
Neg logit contributions | |
Mug | -3.267 |
iron | -3.064 |
imus | -3.012 |
throat | -2.843 |
rone | -2.842 |
Token | 2 |
Token ID | 17 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
Animation | +1.896 |
bj | +1.857 |
+= | +1.841 |
lections | +1.824 |
DAR | +1.805 |
Neg logit contributions | |
Mug | -1.493 |
iron | -1.402 |
imus | -1.355 |
rone | -1.253 |
throat | -1.228 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Animation | +0.380 |
bj | +0.372 |
lections | +0.368 |
+= | +0.365 |
DAR | +0.363 |
Neg logit contributions | |
Mug | -0.440 |
iron | -0.422 |
imus | -0.406 |
rone | -0.382 |
mia | -0.376 |
Token | get |
Token ID | 1136 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Animation | +0.979 |
bj | +0.961 |
lections | +0.948 |
+= | +0.947 |
DAR | +0.934 |
Neg logit contributions | |
Mug | -0.861 |
iron | -0.813 |
imus | -0.782 |
rone | -0.730 |
throat | -0.712 |
Token | Struct |
Token ID | 44909 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Animation | +3.033 |
+= | +2.900 |
bj | +2.890 |
lections | +2.832 |
CH | +2.820 |
Neg logit contributions | |
Mug | -3.047 |
iron | -2.928 |
imus | -2.838 |
rone | -2.681 |
throat | -2.664 |
Token | uring |
Token ID | 870 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Mug | +0.757 |
iron | +0.715 |
imus | +0.662 |
rone | +0.580 |
omy | +0.578 |
Neg logit contributions | |
Animation | -1.807 |
bj | -1.792 |
DAR | -1.775 |
+= | -1.758 |
lections | -1.756 |
Token | Element |
Token ID | 20180 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Animation | +1.151 |
bj | +1.121 |
+= | +1.112 |
lections | +1.109 |
DAR | +1.096 |
Neg logit contributions | |
Mug | -1.002 |
iron | -0.950 |
imus | -0.912 |
rone | -0.851 |
mia | -0.833 |
Token | ( |
Token ID | 7 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Animation | +2.832 |
+= | +2.731 |
bj | +2.664 |
CH | +2.527 |
weight | +2.332 |
Neg logit contributions | |
Mug | -10.536 |
imus | -10.006 |
iron | -9.882 |
throat | -9.670 |
metic | -9.636 |
Token | cv |
Token ID | 33967 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Animation | +0.924 |
bj | +0.905 |
lections | +0.896 |
+= | +0.894 |
DAR | +0.886 |
Neg logit contributions | |
Mug | -0.780 |
iron | -0.742 |
imus | -0.710 |
rone | -0.661 |
mia | -0.647 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Animation | +0.806 |
bj | +0.792 |
lections | +0.785 |
+= | +0.782 |
DAR | +0.776 |
Neg logit contributions | |
Mug | -0.582 |
iron | -0.552 |
imus | -0.525 |
rone | -0.485 |
mia | -0.474 |
Token | . |
Token ID | 13 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
Mug | +1.498 |
iron | +1.446 |
imus | +1.364 |
mia | +1.275 |
rone | +1.273 |
Neg logit contributions | |
Animation | -1.491 |
lections | -1.479 |
bj | -1.464 |
DAR | -1.439 |
ternity | -1.431 |
Token | M |
Token ID | 44 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
Mug | +0.408 |
iron | +0.385 |
imus | +0.363 |
mia | +0.332 |
rone | +0.332 |
Neg logit contributions | |
bj | -0.578 |
lections | -0.578 |
Animation | -0.575 |
+= | -0.565 |
DAR | -0.559 |
Token | a |
Token ID | 257 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
Mug | +0.991 |
iron | +0.940 |
imus | +0.898 |
rone | +0.846 |
throat | +0.841 |
Neg logit contributions | |
Animation | -0.938 |
bj | -0.917 |
lections | -0.902 |
+= | -0.893 |
DAR | -0.876 |
Token | Rails |
Token ID | 31493 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
Animation | +0.333 |
bj | +0.326 |
lections | +0.322 |
+= | +0.320 |
DAR | +0.315 |
Neg logit contributions | |
Mug | -0.264 |
iron | -0.248 |
imus | -0.236 |
rone | -0.220 |
throat | -0.216 |
Token | ( |
Token ID | 357 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Animation | +2.731 |
bj | +2.677 |
lections | +2.643 |
+= | +2.640 |
DAR | +2.614 |
Neg logit contributions | |
Mug | -2.547 |
iron | -2.421 |
imus | -2.331 |
rone | -2.176 |
mia | -2.126 |
Token | yes |
Token ID | 8505 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Animation | +0.645 |
bj | +0.631 |
lections | +0.623 |
+= | +0.621 |
DAR | +0.614 |
Neg logit contributions | |
Mug | -0.836 |
iron | -0.809 |
imus | -0.776 |
rone | -0.733 |
mia | -0.722 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Mug | +0.716 |
iron | +0.690 |
imus | +0.658 |
rone | +0.622 |
throat | +0.613 |
Neg logit contributions | |
Animation | -0.596 |
bj | -0.585 |
lections | -0.571 |
+= | -0.570 |
DAR | -0.558 |
Token | Rails |
Token ID | 31493 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Animation | +0.735 |
bj | +0.719 |
lections | +0.708 |
+= | +0.706 |
DAR | +0.696 |
Neg logit contributions | |
Mug | -0.778 |
iron | -0.743 |
imus | -0.712 |
rone | -0.668 |
mia | -0.657 |
Token | ) |
Token ID | 8 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
Animation | +5.072 |
bj | +4.941 |
+= | +4.913 |
DAR | +4.890 |
Women | +4.886 |
Neg logit contributions | |
Mug | -7.854 |
iron | -7.521 |
imus | -7.352 |
rone | -7.050 |
mia | -6.776 |
Token | development |
Token ID | 2478 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Animation | +1.854 |
bj | +1.819 |
lections | +1.800 |
+= | +1.795 |
DAR | +1.778 |
Neg logit contributions | |
Mug | -1.561 |
iron | -1.482 |
imus | -1.419 |
rone | -1.320 |
mia | -1.292 |
Token | team |
Token ID | 1074 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
Animation | +2.293 |
bj | +2.248 |
lections | +2.223 |
+= | +2.223 |
DAR | +2.203 |
Neg logit contributions | |
Mug | -1.930 |
iron | -1.834 |
imus | -1.759 |
rone | -1.634 |
mia | -1.599 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Animation | +0.539 |
bj | +0.527 |
lections | +0.520 |
+= | +0.519 |
DAR | +0.513 |
Neg logit contributions | |
Mug | -0.603 |
iron | -0.576 |
imus | -0.555 |
rone | -0.522 |
mia | -0.513 |
Token | Of |
Token ID | 3226 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
Animation | +0.881 |
bj | +0.862 |
lections | +0.853 |
+= | +0.848 |
DAR | +0.837 |
Neg logit contributions | |
Mug | -0.996 |
iron | -0.950 |
imus | -0.915 |
rone | -0.860 |
mia | -0.844 |
Token | 12 |
Token ID | 1105 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Animation | +2.835 |
+= | +2.798 |
bj | +2.785 |
DAR | +2.769 |
lections | +2.767 |
Neg logit contributions | |
Mug | -3.077 |
iron | -2.918 |
imus | -2.814 |
mia | -2.670 |
rone | -2.656 |
Token | 13 |
Token ID | 1511 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Animation | +1.300 |
bj | +1.279 |
+= | +1.273 |
lections | +1.268 |
DAR | +1.262 |
Neg logit contributions | |
Mug | -1.125 |
iron | -1.066 |
imus | -1.022 |
rone | -0.959 |
mia | -0.952 |
Token | 14 |
Token ID | 1478 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
Animation | +2.803 |
bj | +2.744 |
+= | +2.741 |
DAR | +2.729 |
lections | +2.716 |
Neg logit contributions | |
Mug | -3.117 |
iron | -2.970 |
imus | -2.852 |
rone | -2.733 |
mia | -2.705 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
Animation | +2.781 |
bj | +2.744 |
+= | +2.728 |
lections | +2.709 |
DAR | +2.697 |
Neg logit contributions | |
Mug | -3.753 |
iron | -3.580 |
imus | -3.470 |
rone | -3.295 |
mia | -3.275 |
Token | 16 |
Token ID | 1467 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
DAR | +4.177 |
Animation | +4.176 |
+= | +4.147 |
bj | +4.099 |
Women | +4.022 |
Neg logit contributions | |
Mug | -5.803 |
iron | -5.480 |
imus | -5.307 |
mia | -5.100 |
rone | -5.059 |
Token | 17 |
Token ID | 1596 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
+= | +3.750 |
DAR | +3.733 |
Animation | +3.713 |
bj | +3.652 |
lections | +3.626 |
Neg logit contributions | |
Mug | -7.081 |
iron | -6.857 |
imus | -6.509 |
mia | -6.408 |
rone | -6.370 |
Token | 18 |
Token ID | 1248 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
Animation | +4.695 |
DAR | +4.658 |
+= | +4.620 |
bj | +4.564 |
Women | +4.555 |
Neg logit contributions | |
Mug | -8.134 |
iron | -7.748 |
imus | -7.479 |
rone | -7.339 |
mia | -7.214 |
Token | 19 |
Token ID | 678 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
Animation | +3.648 |
bj | +3.633 |
+= | +3.595 |
CH | +3.558 |
DAR | +3.539 |
Neg logit contributions | |
Mug | -3.558 |
iron | -3.355 |
imus | -3.300 |
mia | -3.079 |
rone | -3.059 |
Token | 20 |
Token ID | 1160 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Animation | +3.684 |
+= | +3.608 |
bj | +3.592 |
DAR | +3.533 |
lections | +3.516 |
Neg logit contributions | |
Mug | -4.924 |
iron | -4.744 |
imus | -4.663 |
mia | -4.387 |
rone | -4.376 |
Token | 21 |
Token ID | 2310 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Animation | +3.973 |
+= | +3.966 |
bj | +3.923 |
DAR | +3.895 |
lections | +3.836 |
Neg logit contributions | |
Mug | -4.755 |
iron | -4.558 |
imus | -4.465 |
mia | -4.270 |
rone | -4.151 |
Token | 22 |
Token ID | 2534 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
Animation | +3.443 |
+= | +3.399 |
DAR | +3.362 |
bj | +3.359 |
lections | +3.306 |
Neg logit contributions | |
Mug | -4.335 |
iron | -4.161 |
imus | -4.050 |
mia | -3.854 |
rone | -3.807 |
Token | . |
Token ID | 13 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
Animation | +3.440 |
+= | +3.366 |
bj | +3.312 |
lections | +3.279 |
++) | +3.222 |
Neg logit contributions | |
Mug | -5.092 |
iron | -4.842 |
imus | -4.767 |
rone | -4.499 |
mia | -4.420 |
Token | Width |
Token ID | 30916 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Animation | +2.688 |
bj | +2.505 |
+= | +2.486 |
lections | +2.437 |
CH | +2.436 |
Neg logit contributions | |
Mug | -5.203 |
iron | -5.019 |
imus | -4.942 |
rone | -4.664 |
throat | -4.613 |
Token | ), |
Token ID | 828 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
Animation | +2.329 |
bj | +2.268 |
+= | +2.262 |
lections | +2.226 |
DAR | +2.207 |
Neg logit contributions | |
Mug | -3.297 |
iron | -3.156 |
imus | -3.066 |
rone | -2.908 |
mia | -2.855 |
Token | ($ |
Token ID | 16763 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Animation | +2.037 |
bj | +1.963 |
+= | +1.934 |
lections | +1.924 |
DAR | +1.895 |
Neg logit contributions | |
Mug | -3.401 |
iron | -3.240 |
imus | -3.184 |
rone | -3.009 |
throat | -2.969 |
Token | SR |
Token ID | 12562 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
Animation | +1.857 |
bj | +1.825 |
lections | +1.805 |
+= | +1.801 |
DAR | +1.784 |
Neg logit contributions | |
Mug | -1.286 |
iron | -1.209 |
imus | -1.154 |
rone | -1.064 |
mia | -1.035 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Animation | +2.509 |
+= | +2.457 |
bj | +2.441 |
CH | +2.368 |
lections | +2.367 |
Neg logit contributions | |
Mug | -3.551 |
iron | -3.385 |
imus | -3.326 |
rone | -3.145 |
throat | -3.095 |
Token | Height |
Token ID | 23106 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Animation | +3.501 |
CH | +3.135 |
+= | +3.032 |
bj | +2.987 |
++) | +2.890 |
Neg logit contributions | |
Mug | -9.745 |
imus | -9.441 |
iron | -9.438 |
rone | -8.961 |
isol | -8.953 |
Token | ))) |
Token ID | 22305 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
Animation | +1.156 |
bj | +1.130 |
lections | +1.115 |
+= | +1.114 |
DAR | +1.100 |
Neg logit contributions | |
Mug | -1.371 |
iron | -1.312 |
imus | -1.267 |
rone | -1.193 |
mia | -1.172 |
Token | ) |
Token ID | 1267 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Animation | +2.558 |
+= | +2.500 |
bj | +2.489 |
lections | +2.464 |
DAR | +2.444 |
Neg logit contributions | |
Mug | -2.995 |
iron | -2.888 |
imus | -2.780 |
rone | -2.629 |
mia | -2.582 |
Token | } |
Token ID | 1782 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Animation | +3.132 |
+= | +3.077 |
bj | +3.045 |
lections | +3.014 |
DAR | +2.998 |
Neg logit contributions | |
Mug | -3.631 |
iron | -3.495 |
imus | -3.374 |
rone | -3.171 |
mia | -3.143 |
Token | } |
Token ID | 1782 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
Animation | +1.422 |
bj | +1.388 |
+= | +1.373 |
lections | +1.368 |
DAR | +1.352 |
Neg logit contributions | |
Mug | -1.834 |
iron | -1.761 |
imus | -1.703 |
rone | -1.610 |
mia | -1.583 |
Token | state |
Token ID | 1181 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Mug | +1.390 |
iron | +1.281 |
imus | +1.256 |
rone | +1.117 |
throat | +1.115 |
Neg logit contributions | |
Animation | -2.456 |
bj | -2.452 |
lections | -2.434 |
+= | -2.387 |
DAR | -2.375 |
Token | ( |
Token ID | 357 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
Animation | +4.278 |
+= | +4.173 |
bj | +4.026 |
Women | +3.958 |
DAR | +3.956 |
Neg logit contributions | |
Mug | -5.314 |
iron | -5.137 |
imus | -4.920 |
rone | -4.703 |
omy | -4.591 |
Token | such |
Token ID | 10508 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
Animation | +0.368 |
bj | +0.355 |
lections | +0.350 |
+= | +0.347 |
DAR | +0.344 |
Neg logit contributions | |
Mug | -0.764 |
iron | -0.745 |
imus | -0.720 |
rone | -0.685 |
mia | -0.678 |
Token | as |
Token ID | 355 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
Animation | +0.211 |
bj | +0.204 |
lections | +0.204 |
+= | +0.198 |
DAR | +0.197 |
Neg logit contributions | |
Mug | -0.361 |
iron | -0.349 |
imus | -0.336 |
rone | -0.318 |
mia | -0.318 |
Token | through |
Token ID | 832 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
Mug | +2.036 |
iron | +1.933 |
imus | +1.850 |
throat | +1.730 |
isol | +1.726 |
Neg logit contributions | |
Animation | -2.531 |
bj | -2.498 |
lections | -2.480 |
+= | -2.412 |
ternity | -2.405 |
Token | a |
Token ID | 257 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Animation | +3.391 |
bj | +3.285 |
+= | +3.242 |
lections | +3.220 |
DAR | +3.194 |
Neg logit contributions | |
Mug | -5.262 |
iron | -5.144 |
imus | -5.024 |
rone | -4.760 |
mia | -4.619 |
Token | or |
Token ID | 393 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
Animation | +4.722 |
bj | +4.558 |
lections | +4.415 |
+= | +4.412 |
DAR | +4.356 |
Neg logit contributions | |
Mug | -8.369 |
iron | -8.153 |
imus | -7.889 |
mia | -7.507 |
rone | -7.504 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Animation | +2.699 |
bj | +2.641 |
lections | +2.606 |
+= | +2.599 |
DAR | +2.571 |
Neg logit contributions | |
Mug | -3.018 |
iron | -2.888 |
imus | -2.785 |
rone | -2.616 |
mia | -2.570 |
Token | must |
Token ID | 1276 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
Animation | +0.835 |
bj | +0.813 |
+= | +0.805 |
lections | +0.801 |
DAR | +0.786 |
Neg logit contributions | |
Mug | -1.256 |
iron | -1.200 |
imus | -1.164 |
rone | -1.105 |
mia | -1.087 |
Token | not |
Token ID | 407 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Animation | +1.248 |
bj | +1.226 |
+= | +1.215 |
lections | +1.206 |
DAR | +1.189 |
Neg logit contributions | |
Mug | -1.342 |
iron | -1.275 |
imus | -1.229 |
rone | -1.153 |
mia | -1.131 |
Token | modify |
Token ID | 13096 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Animation | +0.660 |
bj | +0.645 |
lections | +0.638 |
+= | +0.631 |
DAR | +0.629 |
Neg logit contributions | |
Mug | -0.720 |
iron | -0.689 |
imus | -0.666 |
rone | -0.625 |
mia | -0.614 |
Token | Boston |
Token ID | 6182 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Animation | +0.275 |
bj | +0.267 |
lections | +0.264 |
+= | +0.263 |
DAR | +0.260 |
Neg logit contributions | |
Mug | -0.385 |
iron | -0.370 |
imus | -0.357 |
rone | -0.338 |
omy | -0.332 |
Token | ( |
Token ID | 357 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
Animation | +2.245 |
bj | +2.186 |
+= | +2.175 |
DAR | +2.154 |
lections | +2.133 |
Neg logit contributions | |
Mug | -2.440 |
iron | -2.363 |
imus | -2.282 |
rone | -2.147 |
throat | -2.096 |
Token | pictured |
Token ID | 28852 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Animation | +0.285 |
bj | +0.280 |
lections | +0.278 |
+= | +0.277 |
DAR | +0.274 |
Neg logit contributions | |
Mug | -0.205 |
iron | -0.194 |
imus | -0.185 |
rone | -0.171 |
mia | -0.167 |
Token | ), |
Token ID | 828 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Animation | +0.895 |
bj | +0.876 |
lections | +0.858 |
+= | +0.857 |
DAR | +0.849 |
Neg logit contributions | |
Mug | -1.469 |
iron | -1.413 |
imus | -1.371 |
rone | -1.302 |
mia | -1.284 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Mug | +0.867 |
iron | +0.819 |
imus | +0.783 |
rone | +0.734 |
mia | +0.724 |
Neg logit contributions | |
Animation | -0.880 |
bj | -0.860 |
lections | -0.858 |
+= | -0.845 |
DAR | -0.834 |
Token | Latin |
Token ID | 9133 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Mug | +1.062 |
iron | +1.028 |
imus | +0.981 |
rone | +0.919 |
omy | +0.911 |
Neg logit contributions | |
Animation | -0.896 |
bj | -0.883 |
lections | -0.874 |
+= | -0.873 |
DAR | -0.863 |
Token | Academy |
Token ID | 8581 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
Animation | +4.183 |
DAR | +4.055 |
Women | +3.992 |
Architects | +3.879 |
+= | +3.860 |
Neg logit contributions | |
Mug | -8.836 |
iron | -8.729 |
imus | -8.306 |
rone | -8.152 |
ebted | -7.993 |
Token | , |
Token ID | 11 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Animation | +2.083 |
bj | +2.055 |
+= | +2.017 |
DAR | +2.005 |
Women | +1.972 |
Neg logit contributions | |
Mug | -3.227 |
iron | -3.109 |
imus | -3.047 |
rone | -2.870 |
omy | -2.828 |
Token | some |
Token ID | 617 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
Mug | +2.134 |
iron | +1.940 |
imus | +1.791 |
throat | +1.725 |
rone | +1.709 |
Neg logit contributions | |
Animation | -3.101 |
bj | -3.008 |
lections | -2.969 |
+= | -2.968 |
++) | -2.935 |
Token | areas |
Token ID | 3006 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
Mug | +0.642 |
iron | +0.616 |
imus | +0.598 |
rone | +0.572 |
isol | +0.570 |
Neg logit contributions | |
Animation | -0.394 |
bj | -0.380 |
+= | -0.369 |
lections | -0.363 |
++) | -0.358 |
Token | in |
Token ID | 287 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
Animation | +0.137 |
bj | +0.134 |
lections | +0.132 |
+= | +0.132 |
DAR | +0.130 |
Neg logit contributions | |
Mug | -0.160 |
iron | -0.154 |
imus | -0.148 |
rone | -0.139 |
mia | -0.137 |
Token | — |
Token ID | 851 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Mug | +1.066 |
iron | +1.013 |
imus | +0.977 |
rone | +0.912 |
mia | +0.904 |
Neg logit contributions | |
Animation | -0.967 |
bj | -0.943 |
lections | -0.929 |
+= | -0.918 |
DAR | -0.908 |
Token | Old |
Token ID | 5706 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Mug | +1.848 |
iron | +1.721 |
imus | +1.658 |
rone | +1.538 |
mia | +1.537 |
Neg logit contributions | |
Animation | -1.691 |
bj | -1.634 |
lections | -1.622 |
+= | -1.613 |
++) | -1.573 |
Token | Man |
Token ID | 1869 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Mug | +3.572 |
iron | +3.344 |
imus | +3.163 |
rone | +3.026 |
mia | +2.955 |
Neg logit contributions | |
Animation | -2.862 |
+= | -2.796 |
bj | -2.780 |
lections | -2.757 |
++) | -2.718 |
Token | Car |
Token ID | 1879 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
Mug | +1.522 |
iron | +1.424 |
imus | +1.371 |
rone | +1.288 |
mia | +1.266 |
Neg logit contributions | |
Animation | -1.346 |
bj | -1.307 |
lections | -1.299 |
+= | -1.284 |
DAR | -1.257 |
Token | rick |
Token ID | 5557 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
Mug | +2.498 |
iron | +2.426 |
imus | +2.324 |
rone | +2.254 |
omy | +2.189 |
Neg logit contributions | |
Animation | -2.012 |
bj | -1.931 |
lections | -1.922 |
+= | -1.902 |
DAR | -1.897 |
Token | (@ |
Token ID | 4275 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Mug | +3.226 |
iron | +3.072 |
imus | +2.960 |
rone | +2.734 |
omy | +2.692 |
Neg logit contributions | |
Animation | -2.986 |
lections | -2.884 |
bj | -2.865 |
+= | -2.862 |
DAR | -2.803 |
Token | andy |
Token ID | 10757 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
iron | +7.447 |
Mug | +7.045 |
imus | +6.860 |
rone | +6.401 |
mia | +6.354 |
Neg logit contributions | |
DAR | -7.108 |
lections | -6.972 |
+= | -6.938 |
Animation | -6.781 |
Women | -6.743 |
Token | f |
Token ID | 69 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
Mug | +2.278 |
iron | +2.247 |
imus | +2.143 |
rone | +2.013 |
mia | +1.969 |
Neg logit contributions | |
Animation | -2.405 |
lections | -2.327 |
DAR | -2.327 |
bj | -2.321 |
+= | -2.320 |
Token | erv |
Token ID | 712 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
iron | +5.045 |
Mug | +4.886 |
imus | +4.734 |
rone | +4.507 |
omy | +4.372 |
Neg logit contributions | |
Animation | -4.370 |
DAR | -4.165 |
+= | -4.084 |
Women | -4.055 |
bj | -4.041 |
Token | s |
Token ID | 82 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Animation | +0.033 |
bj | +0.032 |
+= | +0.032 |
lections | +0.032 |
DAR | +0.032 |
Neg logit contributions | |
Mug | -0.048 |
iron | -0.047 |
imus | -0.046 |
rone | -0.043 |
omy | -0.042 |
Token | ) |
Token ID | 8 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
Mug | +1.323 |
iron | +1.294 |
imus | +1.250 |
rone | +1.176 |
mia | +1.156 |
Neg logit contributions | |
Animation | -1.046 |
bj | -1.010 |
+= | -1.008 |
lections | -1.006 |
DAR | -1.004 |
Token | < |
Token ID | 1279 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
Mug | +2.145 |
iron | +2.061 |
imus | +1.974 |
rone | +1.856 |
omy | +1.822 |
Neg logit contributions | |
Animation | -1.771 |
bj | -1.731 |
lections | -1.723 |
DAR | -1.696 |
+= | -1.683 |
Token | li |
Token ID | 4528 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
Mug | +1.875 |
iron | +1.852 |
imus | +1.688 |
rone | +1.514 |
omy | +1.434 |
Neg logit contributions | |
Animation | -4.481 |
DAR | -4.438 |
bj | -4.403 |
lections | -4.373 |
+= | -4.363 |
Token | ng |
Token ID | 23370 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
Animation | +3.030 |
+= | +2.976 |
bj | +2.920 |
lections | +2.883 |
DAR | +2.817 |
Neg logit contributions | |
Mug | -5.507 |
iron | -5.315 |
imus | -5.180 |
mia | -4.922 |
rone | -4.887 |
Token | - |
Token ID | 12 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Mug | +0.101 |
iron | +0.097 |
imus | +0.094 |
rone | +0.088 |
mia | +0.087 |
Neg logit contributions | |
Animation | -0.083 |
bj | -0.082 |
lections | -0.081 |
DAR | -0.080 |
+= | -0.080 |
Token | repeat |
Token ID | 44754 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Animation | +2.361 |
bj | +2.328 |
lections | +2.295 |
+= | +2.295 |
DAR | +2.250 |
Neg logit contributions | |
Mug | -1.930 |
iron | -1.800 |
imus | -1.728 |
rone | -1.599 |
mia | -1.578 |
Token | =" |
Token ID | 2625 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Mug | +1.655 |
iron | +1.602 |
imus | +1.552 |
rone | +1.474 |
mia | +1.463 |
Neg logit contributions | |
Animation | -0.760 |
lections | -0.754 |
bj | -0.747 |
DAR | -0.726 |
Women | -0.698 |
Token | phone |
Token ID | 4862 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
iron | +5.226 |
Mug | +5.001 |
imus | +4.702 |
rone | +4.437 |
mia | +4.417 |
Neg logit contributions | |
DAR | -8.574 |
Animation | -8.376 |
Architects | -8.366 |
龍喚士 | -8.294 |
lections | -8.209 |
Token | in |
Token ID | 287 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Mug | +1.893 |
iron | +1.813 |
imus | +1.734 |
rone | +1.631 |
throat | +1.607 |
Neg logit contributions | |
Animation | -1.765 |
bj | -1.729 |
lections | -1.714 |
DAR | -1.711 |
+= | -1.685 |
Token | phones |
Token ID | 9512 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Mug | +1.037 |
iron | +0.970 |
imus | +0.918 |
rone | +0.857 |
isol | +0.840 |
Neg logit contributions | |
Animation | -1.588 |
bj | -1.545 |
DAR | -1.529 |
lections | -1.528 |
+= | -1.524 |
Token | "> |
Token ID | 5320 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Mug | +0.927 |
iron | +0.883 |
imus | +0.843 |
rone | +0.783 |
mia | +0.770 |
Neg logit contributions | |
Animation | -1.077 |
bj | -1.061 |
lections | -1.047 |
DAR | -1.043 |
+= | -1.038 |
Token | < |
Token ID | 1279 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
Mug | +1.402 |
iron | +1.364 |
imus | +1.324 |
rone | +1.272 |
mia | +1.255 |
Neg logit contributions | |
Animation | -0.455 |
bj | -0.438 |
lections | -0.431 |
DAR | -0.423 |
+= | -0.421 |
Token | . |
Token ID | 13 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
Mug | +3.626 |
iron | +3.473 |
imus | +3.278 |
mia | +3.032 |
rone | +3.016 |
Neg logit contributions | |
Animation | -3.940 |
lections | -3.938 |
bj | -3.875 |
DAR | -3.795 |
ternity | -3.793 |
Token | Old |
Token ID | 5706 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Mug | +0.651 |
iron | +0.604 |
imus | +0.585 |
rone | +0.545 |
mia | +0.534 |
Neg logit contributions | |
Animation | -0.567 |
bj | -0.558 |
lections | -0.556 |
+= | -0.546 |
DAR | -0.532 |
Token | gift |
Token ID | 6979 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
Mug | +1.453 |
iron | +1.348 |
imus | +1.290 |
rone | +1.201 |
throat | +1.177 |
Neg logit contributions | |
Animation | -1.942 |
bj | -1.911 |
lections | -1.885 |
+= | -1.865 |
DAR | -1.863 |
Token | – |
Token ID | 1906 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
Animation | +0.584 |
bj | +0.573 |
lections | +0.566 |
+= | +0.562 |
DAR | +0.557 |
Neg logit contributions | |
Mug | -0.666 |
iron | -0.637 |
imus | -0.614 |
rone | -0.576 |
mia | -0.566 |
Token | be |
Token ID | 1350 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Animation | +0.032 |
bj | +0.030 |
lections | +0.030 |
+= | +0.030 |
DAR | +0.029 |
Neg logit contributions | |
Mug | -0.069 |
iron | -0.067 |
imus | -0.065 |
rone | -0.062 |
mia | -0.062 |
Token | arer |
Token ID | 11258 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Mug | +0.577 |
iron | +0.551 |
imus | +0.520 |
rone | +0.470 |
omy | +0.451 |
Neg logit contributions | |
Animation | -1.122 |
bj | -1.099 |
DAR | -1.087 |
+= | -1.086 |
lections | -1.086 |
Token | setting |
Token ID | 4634 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Mug | +4.808 |
iron | +4.531 |
isol | +4.092 |
imus | +4.087 |
throat | +3.983 |
Neg logit contributions | |
lections | -9.377 |
bj | -9.265 |
Animation | -8.940 |
ternity | -8.927 |
++) | -8.919 |
Token | box |
Token ID | 3091 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
Mug | +2.486 |
iron | +2.375 |
imus | +2.220 |
rone | +2.136 |
throat | +2.125 |
Neg logit contributions | |
Animation | -2.362 |
lections | -2.316 |
bj | -2.279 |
ternity | -2.224 |
DAR | -2.217 |
Token | underneath |
Token ID | 14638 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Mug | +0.699 |
iron | +0.671 |
imus | +0.650 |
rone | +0.608 |
throat | +0.602 |
Neg logit contributions | |
Animation | -0.479 |
lections | -0.467 |
bj | -0.467 |
DAR | -0.452 |
+= | -0.449 |
Token | roughly |
Token ID | 7323 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Mug | +4.417 |
imus | +4.043 |
iron | +3.969 |
throat | +3.456 |
rone | +3.408 |
Neg logit contributions | |
Animation | -8.572 |
bj | -8.331 |
lections | -8.320 |
DAR | -8.143 |
ternity | -7.962 |
Token | ( |
Token ID | 357 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Animation | +2.024 |
bj | +1.978 |
+= | +1.959 |
lections | +1.953 |
DAR | +1.930 |
Neg logit contributions | |
Mug | -2.048 |
iron | -1.951 |
imus | -1.878 |
rone | -1.763 |
mia | -1.724 |
Token | the |
Token ID | 262 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
Mug | +4.767 |
iron | +4.424 |
imus | +4.079 |
rone | +3.891 |
throat | +3.878 |
Neg logit contributions | |
Animation | -5.657 |
+= | -5.608 |
bj | -5.587 |
lections | -5.524 |
++) | -5.322 |
Token | iceberg |
Token ID | 34849 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
Mug | +4.635 |
iron | +4.196 |
imus | +3.754 |
throat | +3.733 |
rone | +3.572 |
Neg logit contributions | |
Animation | -7.242 |
lections | -7.159 |
bj | -7.127 |
+= | -7.090 |
awar | -6.795 |
Token | ," |
Token ID | 553 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
Mug | +2.675 |
iron | +2.520 |
imus | +2.425 |
isol | +2.262 |
throat | +2.234 |
Neg logit contributions | |
Animation | -2.764 |
bj | -2.746 |
+= | -2.704 |
lections | -2.671 |
DAR | -2.621 |
Token | he |
Token ID | 339 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
Animation | +0.092 |
bj | +0.089 |
lections | +0.089 |
+= | +0.088 |
DAR | +0.087 |
Neg logit contributions | |
Mug | -0.123 |
iron | -0.117 |
imus | -0.113 |
rone | -0.107 |
throat | -0.105 |
Token | told |
Token ID | 1297 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Animation | +0.113 |
bj | +0.110 |
lections | +0.109 |
+= | +0.108 |
DAR | +0.107 |
Neg logit contributions | |
Mug | -0.161 |
iron | -0.155 |
imus | -0.150 |
rone | -0.141 |
mia | -0.139 |
Token | The |
Token ID | 383 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Mug | +2.557 |
iron | +2.403 |
imus | +2.275 |
rone | +2.146 |
omy | +2.108 |
Neg logit contributions | |
Animation | -2.777 |
lections | -2.724 |
+= | -2.719 |
bj | -2.685 |
++) | -2.676 |
Token | Associated |
Token ID | 10575 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
Mug | +6.829 |
iron | +6.270 |
imus | +5.743 |
rone | +5.609 |
rio | +5.487 |
Neg logit contributions | |
lections | -6.397 |
ternity | -6.286 |
Animation | -6.206 |
bj | -6.176 |
+= | -6.160 |
Token | Press |
Token ID | 4332 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
Mug | +2.657 |
iron | +2.378 |
imus | +2.156 |
rone | +1.991 |
omy | +1.966 |
Neg logit contributions | |
bj | -4.662 |
lections | -4.650 |
Animation | -4.609 |
ternity | -4.551 |
DAR | -4.524 |
Token | in |
Token ID | 287 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Mug | +5.242 |
iron | +5.240 |
imus | +4.770 |
rone | +4.568 |
throat | +4.446 |
Neg logit contributions | |
bj | -5.643 |
Animation | -5.589 |
++) | -5.572 |
DAR | -5.483 |
lections | -5.433 |
Token | an |
Token ID | 281 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Mug | +2.071 |
iron | +1.923 |
imus | +1.825 |
throat | +1.740 |
rone | +1.736 |
Neg logit contributions | |
Animation | -2.010 |
bj | -1.927 |
+= | -1.914 |
lections | -1.905 |
++) | -1.874 |
Token | interview |
Token ID | 2720 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Mug | +1.832 |
iron | +1.711 |
imus | +1.605 |
rone | +1.452 |
throat | +1.439 |
Neg logit contributions | |
Animation | -3.500 |
bj | -3.449 |
lections | -3.417 |
+= | -3.410 |
++) | -3.378 |
Token | . |
Token ID | 13 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Mug | +2.623 |
iron | +2.507 |
imus | +2.372 |
rone | +2.205 |
mia | +2.204 |
Neg logit contributions | |
Animation | -2.661 |
lections | -2.640 |
bj | -2.607 |
DAR | -2.554 |
ternity | -2.533 |
Token | Sw |
Token ID | 2451 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Mug | +1.105 |
iron | +1.030 |
imus | +0.990 |
rone | +0.931 |
throat | +0.909 |
Neg logit contributions | |
Animation | -0.952 |
bj | -0.936 |
lections | -0.932 |
+= | -0.911 |
DAR | -0.891 |
Token | immer |
Token ID | 10957 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
Mug | +2.518 |
iron | +2.490 |
imus | +2.417 |
rone | +2.278 |
mia | +2.253 |
Neg logit contributions | |
Animation | -1.320 |
bj | -1.271 |
DAR | -1.256 |
+= | -1.250 |
lections | -1.222 |
Token | means |
Token ID | 1724 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
Animation | +0.173 |
bj | +0.170 |
lections | +0.168 |
+= | +0.166 |
DAR | +0.165 |
Neg logit contributions | |
Mug | -0.217 |
iron | -0.208 |
imus | -0.201 |
rone | -0.189 |
mia | -0.186 |
Token | to |
Token ID | 284 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
Mug | +4.268 |
iron | +4.052 |
imus | +3.813 |
throat | +3.604 |
rone | +3.563 |
Neg logit contributions | |
Animation | -4.149 |
bj | -4.105 |
lections | -4.045 |
DAR | -3.965 |
+= | -3.920 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Mug | +3.847 |
iron | +3.622 |
imus | +3.408 |
throat | +3.246 |
isol | +3.208 |
Neg logit contributions | |
Animation | -4.740 |
lections | -4.571 |
bj | -4.570 |
ternity | -4.440 |
DAR | -4.424 |
Token | fit |
Token ID | 4197 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Mug | +5.709 |
iron | +5.527 |
imus | +5.074 |
throat | +4.994 |
isol | +4.982 |
Neg logit contributions | |
lections | -7.130 |
Animation | -7.068 |
bj | -7.000 |
DAR | -6.875 |
INC | -6.767 |
Token | moving |
Token ID | 3867 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Mug | +5.464 |
iron | +5.111 |
imus | +4.955 |
isol | +4.670 |
throat | +4.528 |
Neg logit contributions | |
bj | -6.618 |
lections | -6.584 |
Animation | -6.582 |
DAR | -6.485 |
++) | -6.315 |
Token | about |
Token ID | 546 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Mug | +3.420 |
iron | +3.188 |
imus | +3.118 |
throat | +2.903 |
isol | +2.862 |
Neg logit contributions | |
Animation | -3.480 |
bj | -3.480 |
lections | -3.371 |
DAR | -3.324 |
+= | -3.311 |
Token | ( |
Token ID | 357 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
Animation | +2.426 |
bj | +2.354 |
+= | +2.348 |
lections | +2.329 |
DAR | +2.302 |
Neg logit contributions | |
Mug | -2.631 |
iron | -2.511 |
imus | -2.416 |
rone | -2.282 |
mia | -2.236 |
Token | 7 |
Token ID | 22 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Mug | +0.423 |
iron | +0.408 |
imus | +0.385 |
rone | +0.356 |
mia | +0.349 |
Neg logit contributions | |
Animation | -0.571 |
bj | -0.557 |
lections | -0.556 |
+= | -0.554 |
DAR | -0.553 |
Token | Europe |
Token ID | 2031 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
Animation | +1.067 |
bj | +1.045 |
lections | +1.033 |
+= | +1.031 |
DAR | +1.018 |
Neg logit contributions | |
Mug | -0.983 |
iron | -0.932 |
imus | -0.894 |
rone | -0.835 |
mia | -0.817 |
Token | against |
Token ID | 1028 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
Mug | +3.006 |
iron | +2.878 |
imus | +2.737 |
rone | +2.576 |
isol | +2.567 |
Neg logit contributions | |
Animation | -3.111 |
bj | -3.027 |
+= | -3.026 |
lections | -3.000 |
DAR | -2.987 |
Token | short |
Token ID | 1790 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
Mug | +0.203 |
iron | +0.189 |
imus | +0.182 |
rone | +0.171 |
throat | +0.171 |
Neg logit contributions | |
Animation | -0.182 |
bj | -0.177 |
lections | -0.174 |
+= | -0.174 |
DAR | -0.170 |
Token | - |
Token ID | 12 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
Mug | +0.487 |
iron | +0.465 |
imus | +0.442 |
rone | +0.424 |
throat | +0.418 |
Neg logit contributions | |
Animation | -0.400 |
bj | -0.392 |
lections | -0.390 |
+= | -0.386 |
DAR | -0.380 |
Token | and |
Token ID | 290 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
Mug | +2.978 |
iron | +2.911 |
imus | +2.691 |
rone | +2.597 |
omy | +2.501 |
Neg logit contributions | |
Animation | -2.760 |
lections | -2.716 |
bj | -2.705 |
+= | -2.652 |
DAR | -2.624 |
Token | medium |
Token ID | 7090 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Mug | +4.016 |
iron | +3.381 |
imus | +3.205 |
throat | +3.146 |
omy | +3.053 |
Neg logit contributions | |
Animation | -7.326 |
bj | -7.113 |
lections | -7.006 |
+= | -6.973 |
ternity | -6.931 |
Token | - |
Token ID | 12 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
Mug | +5.497 |
iron | +5.429 |
imus | +4.790 |
isol | +4.643 |
rone | +4.604 |
Neg logit contributions | |
Animation | -7.343 |
lections | -7.313 |
ternity | -7.271 |
龍喚士 | -7.247 |
bj | -7.122 |
Token | range |
Token ID | 9521 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Mug | +3.912 |
iron | +3.904 |
imus | +3.499 |
rone | +3.458 |
mia | +3.280 |
Neg logit contributions | |
Animation | -4.308 |
bj | -4.239 |
lections | -4.178 |
+= | -4.044 |
Architects | -4.015 |
Token | Iranian |
Token ID | 10704 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
Mug | +2.631 |
iron | +2.412 |
imus | +2.296 |
throat | +2.211 |
rone | +2.210 |
Neg logit contributions | |
Animation | -2.690 |
bj | -2.612 |
lections | -2.535 |
+= | -2.534 |
CH | -2.494 |
Token | missiles |
Token ID | 12798 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Animation | +0.154 |
bj | +0.151 |
lections | +0.149 |
+= | +0.148 |
DAR | +0.146 |
Neg logit contributions | |
Mug | -0.140 |
iron | -0.131 |
imus | -0.126 |
rone | -0.119 |
throat | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Mug | +2.333 |
iron | +2.234 |
imus | +2.132 |
rone | +1.971 |
isol | +1.963 |
Neg logit contributions | |
Animation | -2.258 |
bj | -2.171 |
+= | -2.154 |
lections | -2.150 |
++) | -2.113 |
Token |
|
Token ID | 198 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
Mug | +0.003 |
iron | +0.003 |
imus | +0.003 |
rone | +0.002 |
mia | +0.002 |
Neg logit contributions | |
Animation | -0.003 |
bj | -0.003 |
lections | -0.003 |
+= | -0.003 |
DAR | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
Animation | +0.442 |
bj | +0.433 |
lections | +0.427 |
+= | +0.426 |
DAR | +0.422 |
Neg logit contributions | |
Mug | -0.458 |
iron | -0.437 |
imus | -0.421 |
rone | -0.395 |
mia | -0.387 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Mug | +0.454 |
iron | +0.435 |
imus | +0.414 |
rone | +0.387 |
mia | +0.382 |
Neg logit contributions | |
Animation | -0.479 |
bj | -0.475 |
lections | -0.472 |
+= | -0.470 |
DAR | -0.468 |
Token | Continue |
Token ID | 10054 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
Mug | +1.781 |
iron | +1.662 |
imus | +1.611 |
rone | +1.492 |
mia | +1.488 |
Neg logit contributions | |
Animation | -1.947 |
bj | -1.925 |
lections | -1.902 |
DAR | -1.859 |
+= | -1.849 |
Token | reading |
Token ID | 3555 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Animation | +0.475 |
bj | +0.466 |
lections | +0.461 |
+= | +0.459 |
DAR | +0.454 |
Neg logit contributions | |
Mug | -0.452 |
iron | -0.430 |
imus | -0.413 |
rone | -0.385 |
mia | -0.379 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Mug | +2.524 |
iron | +2.335 |
imus | +2.236 |
omy | +2.079 |
mia | +2.071 |
Neg logit contributions | |
Animation | -2.902 |
lections | -2.860 |
bj | -2.852 |
+= | -2.773 |
ternity | -2.759 |
Token | main |
Token ID | 1388 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Mug | +3.736 |
iron | +3.213 |
imus | +2.875 |
throat | +2.835 |
omy | +2.804 |
Neg logit contributions | |
龍喚士 | -9.539 |
Animation | -9.267 |
bj | -9.195 |
ternity | -9.172 |
lections | -9.165 |
Token | story |
Token ID | 1621 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Mug | +2.042 |
iron | +1.834 |
imus | +1.706 |
rone | +1.611 |
omy | +1.594 |
Neg logit contributions | |
Animation | -3.987 |
lections | -3.906 |
bj | -3.893 |
+= | -3.853 |
龍喚士 | -3.846 |
Token |
|
Token ID | 198 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Animation | +1.876 |
+= | +1.813 |
bj | +1.805 |
DAR | +1.786 |
Women | +1.776 |
Neg logit contributions | |
Mug | -2.172 |
iron | -2.107 |
imus | -2.043 |
rone | -1.926 |
throat | -1.897 |
Token |
|
Token ID | 198 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Mug | +0.949 |
iron | +0.902 |
imus | +0.860 |
rone | +0.802 |
mia | +0.794 |
Neg logit contributions | |
Animation | -1.033 |
lections | -1.015 |
bj | -1.014 |
+= | -0.989 |
DAR | -0.987 |
Token | Although |
Token ID | 7003 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Mug | +2.351 |
iron | +2.278 |
imus | +2.144 |
Rog | +2.016 |
rone | +2.014 |
Neg logit contributions | |
bj | -2.288 |
lections | -2.287 |
+= | -2.283 |
DAR | -2.280 |
Animation | -2.272 |
Token | @ |
Token ID | 2488 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
Animation | +0.410 |
bj | +0.401 |
lections | +0.395 |
+= | +0.392 |
DAR | +0.387 |
Neg logit contributions | |
Mug | -0.609 |
iron | -0.584 |
imus | -0.566 |
rone | -0.536 |
mia | -0.527 |
Token | 144 |
Token ID | 20224 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Mug | +5.102 |
iron | +4.514 |
imus | +4.371 |
throat | +3.931 |
impedance | +3.873 |
Neg logit contributions | |
bj | -6.610 |
lections | -6.495 |
Animation | -6.453 |
ternity | -6.390 |
+= | -6.152 |
Token | Hz |
Token ID | 7399 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Mug | +1.249 |
iron | +1.182 |
imus | +1.087 |
mia | +1.009 |
rone | +1.007 |
Neg logit contributions | |
Animation | -2.329 |
lections | -2.300 |
bj | -2.285 |
+= | -2.260 |
DAR | -2.258 |
Token | ( |
Token ID | 357 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
Animation | +1.273 |
bj | +1.246 |
lections | +1.231 |
+= | +1.230 |
DAR | +1.217 |
Neg logit contributions | |
Mug | -1.263 |
iron | -1.206 |
imus | -1.159 |
rone | -1.086 |
mia | -1.064 |
Token | AMA |
Token ID | 25087 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Mug | +0.362 |
iron | +0.348 |
imus | +0.335 |
rone | +0.313 |
mia | +0.308 |
Neg logit contributions | |
Animation | -0.332 |
bj | -0.331 |
lections | -0.326 |
+= | -0.325 |
DAR | -0.323 |
Token | = |
Token ID | 796 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Mug | +1.201 |
iron | +1.163 |
imus | +1.125 |
rone | +1.081 |
mia | +1.067 |
Neg logit contributions | |
Animation | -0.467 |
bj | -0.454 |
lections | -0.445 |
DAR | -0.437 |
+= | -0.426 |
Token | High |
Token ID | 3334 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Mug | +7.098 |
imus | +6.282 |
iron | +6.152 |
Lime | +5.827 |
throat | +5.641 |
Neg logit contributions | |
bj | -6.010 |
lections | -5.937 |
ternity | -5.888 |
Animation | -5.748 |
+= | -5.590 |
Token | ) |
Token ID | 8 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
Mug | +3.392 |
iron | +3.161 |
imus | +3.084 |
rone | +2.900 |
isol | +2.842 |
Neg logit contributions | |
Animation | -2.655 |
bj | -2.637 |
lections | -2.613 |
+= | -2.555 |
ternity | -2.506 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Mug | +0.393 |
iron | +0.370 |
imus | +0.354 |
rone | +0.330 |
throat | +0.325 |
Neg logit contributions | |
Animation | -0.394 |
bj | -0.389 |
lections | -0.385 |
+= | -0.381 |
DAR | -0.375 |
Token |
|
Token ID | 198 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Mug | +0.715 |
iron | +0.682 |
imus | +0.647 |
rone | +0.604 |
mia | +0.597 |
Neg logit contributions | |
Animation | -0.772 |
lections | -0.759 |
bj | -0.758 |
+= | -0.740 |
DAR | -0.738 |
Token | 23 |
Token ID | 1954 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
Animation | +1.539 |
bj | +1.500 |
lections | +1.477 |
+= | +1.477 |
DAR | +1.456 |
Neg logit contributions | |
Mug | -1.592 |
iron | -1.516 |
imus | -1.465 |
rone | -1.375 |
mia | -1.345 |
Token | – |
Token ID | 1906 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
Animation | +0.584 |
bj | +0.573 |
lections | +0.566 |
+= | +0.562 |
DAR | +0.557 |
Neg logit contributions | |
Mug | -0.666 |
iron | -0.637 |
imus | -0.614 |
rone | -0.576 |
mia | -0.566 |
Token | be |
Token ID | 1350 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Animation | +0.032 |
bj | +0.030 |
lections | +0.030 |
+= | +0.030 |
DAR | +0.029 |
Neg logit contributions | |
Mug | -0.069 |
iron | -0.067 |
imus | -0.065 |
rone | -0.062 |
mia | -0.062 |
Token | arer |
Token ID | 11258 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Mug | +0.577 |
iron | +0.551 |
imus | +0.520 |
rone | +0.470 |
omy | +0.451 |
Neg logit contributions | |
Animation | -1.122 |
bj | -1.099 |
DAR | -1.087 |
+= | -1.086 |
lections | -1.086 |
Token | setting |
Token ID | 4634 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Mug | +4.808 |
iron | +4.531 |
isol | +4.092 |
imus | +4.087 |
throat | +3.983 |
Neg logit contributions | |
lections | -9.377 |
bj | -9.265 |
Animation | -8.940 |
ternity | -8.927 |
++) | -8.919 |
Token | box |
Token ID | 3091 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
Mug | +2.486 |
iron | +2.375 |
imus | +2.220 |
rone | +2.136 |
throat | +2.125 |
Neg logit contributions | |
Animation | -2.362 |
lections | -2.316 |
bj | -2.279 |
ternity | -2.224 |
DAR | -2.217 |
Token | underneath |
Token ID | 14638 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Mug | +0.699 |
iron | +0.671 |
imus | +0.650 |
rone | +0.608 |
throat | +0.602 |
Neg logit contributions | |
Animation | -0.479 |
lections | -0.467 |
bj | -0.467 |
DAR | -0.452 |
+= | -0.449 |
Token | roughly |
Token ID | 7323 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Mug | +4.417 |
imus | +4.043 |
iron | +3.969 |
throat | +3.456 |
rone | +3.408 |
Neg logit contributions | |
Animation | -8.572 |
bj | -8.331 |
lections | -8.320 |
DAR | -8.143 |
ternity | -7.962 |
Token | ( |
Token ID | 357 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Animation | +2.024 |
bj | +1.978 |
+= | +1.959 |
lections | +1.953 |
DAR | +1.930 |
Neg logit contributions | |
Mug | -2.048 |
iron | -1.951 |
imus | -1.878 |
rone | -1.763 |
mia | -1.724 |
Token | 6 |
Token ID | 21 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
Mug | +0.669 |
iron | +0.651 |
imus | +0.612 |
rone | +0.576 |
omy | +0.561 |
Neg logit contributions | |
Animation | -0.820 |
bj | -0.799 |
DAR | -0.794 |
+= | -0.793 |
lections | -0.792 |
Token | ) |
Token ID | 8 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Mug | +2.927 |
iron | +2.849 |
imus | +2.723 |
rone | +2.575 |
omy | +2.558 |
Neg logit contributions | |
Animation | -2.182 |
bj | -2.126 |
lections | -2.113 |
+= | -2.101 |
DAR | -2.084 |
Token | C |
Token ID | 327 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
Mug | +1.266 |
iron | +1.160 |
imus | +1.125 |
rone | +1.019 |
throat | +1.015 |
Neg logit contributions | |
Animation | -1.398 |
bj | -1.382 |
lections | -1.365 |
+= | -1.323 |
ternity | -1.318 |
Token | MP |
Token ID | 4904 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
Animation | +0.701 |
bj | +0.688 |
lections | +0.683 |
+= | +0.677 |
DAR | +0.668 |
Neg logit contributions | |
Mug | -0.677 |
iron | -0.628 |
imus | -0.608 |
rone | -0.567 |
mia | -0.558 |
Token | P |
Token ID | 47 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
Animation | +2.716 |
bj | +2.648 |
+= | +2.599 |
CH | +2.559 |
++) | +2.501 |
Neg logit contributions | |
Mug | -4.003 |
iron | -3.802 |
imus | -3.737 |
throat | -3.510 |
rone | -3.496 |
Token | grade |
Token ID | 9559 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
Animation | +0.331 |
bj | +0.325 |
lections | +0.324 |
+= | +0.321 |
DAR | +0.319 |
Neg logit contributions | |
Mug | -0.115 |
iron | -0.105 |
imus | -0.097 |
rone | -0.084 |
mia | -0.081 |
Token | : |
Token ID | 25 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
Animation | +0.202 |
bj | +0.197 |
lections | +0.194 |
+= | +0.192 |
DAR | +0.190 |
Neg logit contributions | |
Mug | -0.310 |
iron | -0.298 |
imus | -0.289 |
rone | -0.274 |
mia | -0.270 |
Token | C |
Token ID | 327 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Mug | +3.684 |
iron | +3.401 |
imus | +3.291 |
rone | +3.158 |
mia | +3.077 |
Neg logit contributions | |
Animation | -3.207 |
bj | -3.109 |
lections | -3.064 |
ternity | -2.963 |
+= | -2.929 |
Token | - |
Token ID | 12 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Mug | +2.623 |
iron | +2.538 |
imus | +2.406 |
rone | +2.273 |
mia | +2.236 |
Neg logit contributions | |
Animation | -2.562 |
bj | -2.501 |
lections | -2.490 |
DAR | -2.447 |
+= | -2.429 |
Token |
|
Token ID | 198 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Mug | +5.525 |
iron | +5.468 |
imus | +4.984 |
rone | +4.828 |
mia | +4.600 |
Neg logit contributions | |
bj | -7.197 |
Animation | -7.106 |
lections | -7.036 |
DAR | -6.959 |
+= | -6.829 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
Mug | +2.468 |
iron | +2.337 |
imus | +2.182 |
rone | +2.031 |
mia | +2.030 |
Neg logit contributions | |
lections | -3.137 |
Animation | -3.124 |
bj | -3.084 |
ternity | -3.038 |
DAR | -2.995 |
Token | In |
Token ID | 818 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
Mug | +1.279 |
iron | +1.231 |
imus | +1.143 |
mia | +1.056 |
Rog | +1.053 |
Neg logit contributions | |
Animation | -1.775 |
DAR | -1.770 |
lections | -1.770 |
bj | -1.758 |
+= | -1.749 |
Token | an |
Token ID | 281 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Mug | +0.187 |
iron | +0.178 |
imus | +0.171 |
rone | +0.162 |
mia | +0.159 |
Neg logit contributions | |
Animation | -0.165 |
bj | -0.160 |
lections | -0.158 |
+= | -0.157 |
DAR | -0.155 |
Token | appearance |
Token ID | 5585 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
Mug | +1.823 |
iron | +1.726 |
imus | +1.646 |
throat | +1.495 |
rone | +1.488 |
Neg logit contributions | |
Animation | -2.568 |
bj | -2.528 |
lections | -2.518 |
+= | -2.496 |
++) | -2.463 |
Token | the |
Token ID | 262 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
Mug | +0.401 |
iron | +0.381 |
imus | +0.367 |
rone | +0.345 |
mia | +0.339 |
Neg logit contributions | |
Animation | -0.386 |
bj | -0.378 |
lections | -0.375 |
+= | -0.371 |
DAR | -0.368 |
Token | margin |
Token ID | 10330 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
Animation | +2.991 |
bj | +2.929 |
+= | +2.905 |
DAR | +2.880 |
lections | +2.864 |
Neg logit contributions | |
Mug | -2.305 |
iron | -2.206 |
imus | -2.087 |
rone | -1.958 |
omy | -1.911 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Animation | +2.300 |
bj | +2.234 |
+= | +2.200 |
lections | +2.189 |
DAR | +2.167 |
Neg logit contributions | |
Mug | -3.382 |
iron | -3.232 |
imus | -3.151 |
rone | -2.987 |
mia | -2.936 |
Token | as |
Token ID | 355 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Animation | +1.444 |
bj | +1.400 |
+= | +1.367 |
lections | +1.364 |
DAR | +1.343 |
Neg logit contributions | |
Mug | -2.745 |
iron | -2.644 |
imus | -2.579 |
rone | -2.465 |
mia | -2.429 |
Token | the |
Token ID | 262 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Animation | +0.634 |
bj | +0.620 |
lections | +0.613 |
+= | +0.611 |
DAR | +0.604 |
Neg logit contributions | |
Mug | -0.680 |
iron | -0.649 |
imus | -0.625 |
rone | -0.587 |
mia | -0.576 |
Token | dwelling |
Token ID | 26765 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Mug | +1.936 |
iron | +1.835 |
imus | +1.772 |
rone | +1.707 |
mia | +1.650 |
Neg logit contributions | |
Animation | -1.641 |
bj | -1.596 |
lections | -1.567 |
+= | -1.557 |
DAR | -1.525 |
Token | supply |
Token ID | 5127 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
Mug | +2.238 |
iron | +2.146 |
imus | +1.667 |
rone | +1.489 |
impedance | +1.455 |
Neg logit contributions | |
Animation | -10.591 |
bj | -10.504 |
lections | -10.374 |
龍喚士 | -10.246 |
ternity | -10.220 |
Token | builds |
Token ID | 12188 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
Mug | +4.670 |
iron | +4.332 |
imus | +4.112 |
isol | +4.083 |
mia | +3.973 |
Neg logit contributions | |
Animation | -4.252 |
lections | -4.220 |
bj | -4.064 |
龍喚士 | -4.000 |
ternity | -3.996 |
Token | over |
Token ID | 625 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Mug | +0.391 |
iron | +0.371 |
imus | +0.355 |
rone | +0.330 |
mia | +0.324 |
Neg logit contributions | |
Animation | -0.441 |
bj | -0.430 |
lections | -0.429 |
+= | -0.423 |
DAR | -0.421 |
Token | time |
Token ID | 640 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
Mug | +2.099 |
iron | +1.991 |
imus | +1.896 |
throat | +1.795 |
rone | +1.784 |
Neg logit contributions | |
Animation | -1.967 |
lections | -1.914 |
bj | -1.901 |
DAR | -1.848 |
+= | -1.847 |
Token | . |
Token ID | 13 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Animation | +0.578 |
bj | +0.566 |
lections | +0.560 |
+= | +0.557 |
DAR | +0.552 |
Neg logit contributions | |
Mug | -0.675 |
iron | -0.647 |
imus | -0.624 |
rone | -0.585 |
mia | -0.575 |
Token | = |
Token ID | 796 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
Animation | +0.851 |
bj | +0.813 |
+= | +0.799 |
lections | +0.797 |
DAR | +0.771 |
Neg logit contributions | |
Mug | -2.464 |
iron | -2.386 |
imus | -2.324 |
rone | -2.231 |
mia | -2.204 |
Token | ($ |
Token ID | 7198 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Animation | +0.402 |
bj | +0.395 |
lections | +0.389 |
+= | +0.385 |
DAR | +0.383 |
Neg logit contributions | |
Mug | -0.412 |
iron | -0.392 |
imus | -0.377 |
rone | -0.352 |
mia | -0.346 |
Token | text |
Token ID | 5239 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
Animation | +2.033 |
bj | +1.986 |
lections | +1.961 |
+= | +1.953 |
CH | +1.919 |
Neg logit contributions | |
Mug | -1.947 |
iron | -1.836 |
imus | -1.771 |
rone | -1.669 |
throat | -1.624 |
Token | - |
Token ID | 532 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Animation | +0.463 |
bj | +0.458 |
lections | +0.449 |
DAR | +0.444 |
+= | +0.439 |
Neg logit contributions | |
Mug | -0.603 |
iron | -0.580 |
imus | -0.559 |
rone | -0.525 |
mia | -0.520 |
Token | split |
Token ID | 35312 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Mug | +0.962 |
iron | +0.934 |
imus | +0.888 |
rone | +0.828 |
omy | +0.816 |
Neg logit contributions | |
Animation | -0.952 |
bj | -0.940 |
lections | -0.928 |
DAR | -0.918 |
+= | -0.913 |
Token | "\ |
Token ID | 37082 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Mug | +1.266 |
iron | +1.220 |
imus | +1.177 |
rone | +1.107 |
throat | +1.097 |
Neg logit contributions | |
Animation | -0.747 |
bj | -0.739 |
lections | -0.727 |
+= | -0.704 |
DAR | -0.701 |
Token | r |
Token ID | 81 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Mug | +6.725 |
iron | +6.640 |
imus | +6.104 |
rone | +5.922 |
mia | +5.854 |
Neg logit contributions | |
DAR | -5.655 |
bj | -5.593 |
lections | -5.510 |
Animation | -5.495 |
ternity | -5.265 |
Token |
|
Token ID | 198 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
Mug | +2.190 |
iron | +2.131 |
imus | +1.996 |
rone | +1.891 |
mia | +1.868 |
Neg logit contributions | |
Animation | -2.387 |
bj | -2.386 |
lections | -2.368 |
DAR | -2.295 |
+= | -2.261 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Mug | +1.953 |
iron | +1.899 |
imus | +1.775 |
rone | +1.660 |
mia | +1.645 |
Neg logit contributions | |
Animation | -2.345 |
lections | -2.322 |
bj | -2.304 |
DAR | -2.270 |
ternity | -2.244 |
Token | ") |
Token ID | 4943 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Mug | +1.997 |
iron | +1.963 |
imus | +1.874 |
rone | +1.777 |
mia | +1.742 |
Neg logit contributions | |
Animation | -1.694 |
bj | -1.673 |
DAR | -1.663 |
lections | -1.660 |
+= | -1.636 |
Token | $ |
Token ID | 720 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
Animation | +0.615 |
bj | +0.601 |
lections | +0.591 |
+= | +0.582 |
DAR | +0.580 |
Neg logit contributions | |
Mug | -0.880 |
iron | -0.844 |
imus | -0.817 |
rone | -0.773 |
mia | -0.760 |
Token | posted |
Token ID | 4481 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
Mug | +0.484 |
iron | +0.456 |
imus | +0.441 |
rone | +0.411 |
throat | +0.406 |
Neg logit contributions | |
Animation | -0.451 |
bj | -0.444 |
lections | -0.438 |
+= | -0.428 |
DAR | -0.425 |
Token | by |
Token ID | 416 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Mug | +0.071 |
iron | +0.068 |
imus | +0.066 |
rone | +0.062 |
omy | +0.061 |
Neg logit contributions | |
Animation | -0.049 |
bj | -0.048 |
lections | -0.047 |
+= | -0.046 |
DAR | -0.046 |
Token | Robert |
Token ID | 5199 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Mug | +2.630 |
iron | +2.475 |
imus | +2.388 |
throat | +2.215 |
rone | +2.204 |
Neg logit contributions | |
Animation | -2.233 |
bj | -2.148 |
lections | -2.145 |
+= | -2.115 |
++) | -2.070 |
Token | Math |
Token ID | 16320 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Mug | +1.267 |
iron | +1.177 |
imus | +1.134 |
rone | +1.078 |
mia | +1.045 |
Neg logit contributions | |
Animation | -1.157 |
bj | -1.113 |
lections | -1.112 |
+= | -1.106 |
DAR | -1.084 |
Token | is |
Token ID | 271 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Animation | +1.911 |
bj | +1.874 |
lections | +1.850 |
+= | +1.845 |
DAR | +1.824 |
Neg logit contributions | |
Mug | -2.048 |
iron | -1.952 |
imus | -1.880 |
rone | -1.766 |
mia | -1.734 |
Token | (@ |
Token ID | 4275 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Animation | +0.093 |
bj | +0.091 |
lections | +0.091 |
+= | +0.090 |
DAR | +0.088 |
Neg logit contributions | |
Mug | -0.110 |
iron | -0.105 |
imus | -0.102 |
rone | -0.095 |
mia | -0.094 |
Token | r |
Token ID | 81 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
iron | +6.463 |
Mug | +6.177 |
imus | +6.079 |
rone | +5.867 |
mia | +5.652 |
Neg logit contributions | |
DAR | -5.898 |
+= | -5.800 |
Women | -5.761 |
Animation | -5.723 |
lections | -5.674 |
Token | math |
Token ID | 11018 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
iron | +3.178 |
Mug | +3.162 |
imus | +3.037 |
omy | +2.843 |
mia | +2.828 |
Neg logit contributions | |
Animation | -3.358 |
DAR | -3.328 |
Women | -3.260 |
+= | -3.242 |
lections | -3.211 |
Token | is |
Token ID | 271 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
Mug | +0.403 |
iron | +0.401 |
imus | +0.390 |
rone | +0.361 |
omy | +0.357 |
Neg logit contributions | |
Animation | -0.345 |
DAR | -0.328 |
+= | -0.328 |
bj | -0.326 |
lections | -0.325 |
Token | _ |
Token ID | 62 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Animation | +0.122 |
bj | +0.118 |
+= | +0.117 |
lections | +0.117 |
DAR | +0.116 |
Neg logit contributions | |
Mug | -0.150 |
iron | -0.145 |
imus | -0.140 |
rone | -0.132 |
mia | -0.129 |
Token | the |
Token ID | 1169 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Mug | +2.259 |
iron | +2.244 |
imus | +2.171 |
rone | +2.026 |
mia | +2.002 |
Neg logit contributions | |
Animation | -1.994 |
+= | -1.920 |
DAR | -1.902 |
lections | -1.896 |
bj | -1.873 |
Token | wild |
Token ID | 4295 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Animation | +0.621 |
bj | +0.608 |
lections | +0.601 |
+= | +0.598 |
DAR | +0.589 |
Neg logit contributions | |
Mug | -0.664 |
iron | -0.632 |
imus | -0.609 |
rone | -0.571 |
mia | -0.560 |
Token | beasts |
Token ID | 21930 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Animation | +1.645 |
bj | +1.612 |
lections | +1.592 |
+= | +1.587 |
DAR | +1.566 |
Neg logit contributions | |
Mug | -1.752 |
iron | -1.672 |
imus | -1.609 |
rone | -1.513 |
mia | -1.482 |
Token | and |
Token ID | 290 |
Feature activation | +8.44e-03 |
Pos logit contributions | |
Animation | +1.654 |
bj | +1.617 |
+= | +1.593 |
lections | +1.592 |
DAR | +1.576 |
Neg logit contributions | |
Mug | -1.977 |
iron | -1.892 |
imus | -1.825 |
rone | -1.724 |
mia | -1.692 |
Token | tearing |
Token ID | 24447 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Animation | +0.054 |
bj | +0.053 |
lections | +0.053 |
+= | +0.052 |
DAR | +0.052 |
Neg logit contributions | |
Mug | -0.052 |
iron | -0.050 |
imus | -0.048 |
rone | -0.044 |
throat | -0.044 |
Token | them |
Token ID | 606 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
Mug | +0.863 |
iron | +0.816 |
imus | +0.790 |
rone | +0.734 |
throat | +0.731 |
Neg logit contributions | |
Animation | -0.859 |
bj | -0.839 |
lections | -0.837 |
+= | -0.824 |
DAR | -0.808 |
Token | to |
Token ID | 284 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Mug | +2.157 |
iron | +2.063 |
imus | +1.981 |
throat | +1.880 |
rone | +1.824 |
Neg logit contributions | |
Animation | -2.548 |
lections | -2.487 |
bj | -2.487 |
+= | -2.413 |
DAR | -2.388 |
Token | shred |
Token ID | 21163 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Mug | +4.683 |
iron | +4.480 |
throat | +4.116 |
imus | +4.072 |
omy | +3.798 |
Neg logit contributions | |
Animation | -7.722 |
bj | -7.604 |
lections | -7.459 |
+= | -7.337 |
DAR | -7.290 |
Token | s |
Token ID | 82 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Mug | +1.579 |
iron | +1.534 |
imus | +1.473 |
rone | +1.411 |
throat | +1.388 |
Neg logit contributions | |
Animation | -1.095 |
lections | -1.052 |
bj | -1.032 |
+= | -1.024 |
DAR | -1.021 |
Token | , |
Token ID | 11 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
Mug | +1.023 |
iron | +0.984 |
imus | +0.950 |
rone | +0.884 |
throat | +0.882 |
Neg logit contributions | |
Animation | -0.887 |
bj | -0.868 |
lections | -0.867 |
+= | -0.848 |
DAR | -0.841 |
Token | it |
Token ID | 340 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Animation | +2.078 |
bj | +2.031 |
+= | +2.005 |
lections | +2.004 |
DAR | +1.986 |
Neg logit contributions | |
Mug | -2.231 |
iron | -2.135 |
imus | -2.058 |
rone | -1.935 |
mia | -1.899 |
Token | � |
Token ID | 447 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Animation | +2.529 |
bj | +2.463 |
+= | +2.421 |
lections | +2.413 |
DAR | +2.379 |
Neg logit contributions | |
Mug | -3.787 |
iron | -3.637 |
imus | -3.518 |
rone | -3.344 |
mia | -3.288 |
Token | {{ |
Token ID | 22935 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Mug | +0.437 |
iron | +0.414 |
imus | +0.396 |
rone | +0.369 |
mia | +0.362 |
Neg logit contributions | |
Animation | -0.469 |
bj | -0.460 |
lections | -0.455 |
+= | -0.450 |
DAR | -0.449 |
Token | 2 |
Token ID | 17 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Mug | +3.380 |
iron | +3.263 |
imus | +3.006 |
rone | +2.834 |
mia | +2.807 |
Neg logit contributions | |
Animation | -3.854 |
DAR | -3.784 |
lections | -3.780 |
bj | -3.749 |
+= | -3.715 |
Token | , |
Token ID | 11 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Mug | +1.549 |
iron | +1.490 |
imus | +1.414 |
rone | +1.339 |
mia | +1.316 |
Neg logit contributions | |
Animation | -1.305 |
lections | -1.274 |
bj | -1.270 |
+= | -1.242 |
DAR | -1.237 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
Mug | +1.815 |
iron | +1.710 |
imus | +1.616 |
rone | +1.523 |
omy | +1.493 |
Neg logit contributions | |
Animation | -1.887 |
bj | -1.855 |
lections | -1.854 |
DAR | -1.802 |
+= | -1.796 |
Token | }, |
Token ID | 5512 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Mug | +2.310 |
iron | +2.231 |
imus | +2.140 |
rone | +2.019 |
omy | +2.002 |
Neg logit contributions | |
Animation | -1.614 |
bj | -1.560 |
lections | -1.548 |
+= | -1.536 |
DAR | -1.514 |
Token | {{ |
Token ID | 22935 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Mug | +1.272 |
iron | +1.209 |
imus | +1.162 |
rone | +1.083 |
omy | +1.068 |
Neg logit contributions | |
Animation | -1.193 |
bj | -1.170 |
lections | -1.157 |
+= | -1.141 |
DAR | -1.140 |
Token | 1 |
Token ID | 16 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Mug | +4.186 |
iron | +4.179 |
imus | +3.509 |
rone | +3.422 |
omy | +3.308 |
Neg logit contributions | |
DAR | -7.950 |
Animation | -7.800 |
lections | -7.734 |
bj | -7.686 |
Architects | -7.643 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Mug | +1.419 |
iron | +1.363 |
imus | +1.302 |
rone | +1.229 |
mia | +1.214 |
Neg logit contributions | |
Animation | -1.185 |
lections | -1.164 |
bj | -1.153 |
+= | -1.126 |
DAR | -1.124 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Mug | +0.679 |
iron | +0.642 |
imus | +0.611 |
rone | +0.575 |
omy | +0.562 |
Neg logit contributions | |
Animation | -0.687 |
bj | -0.674 |
lections | -0.670 |
+= | -0.654 |
DAR | -0.652 |
Token | }, |
Token ID | 5512 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Mug | +0.845 |
iron | +0.815 |
imus | +0.786 |
rone | +0.744 |
omy | +0.733 |
Neg logit contributions | |
Animation | -0.555 |
bj | -0.540 |
lections | -0.534 |
+= | -0.530 |
DAR | -0.522 |
Token | { |
Token ID | 1391 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
Mug | +0.718 |
iron | +0.678 |
imus | +0.649 |
rone | +0.599 |
mia | +0.588 |
Neg logit contributions | |
Animation | -0.858 |
bj | -0.843 |
lections | -0.834 |
+= | -0.827 |
DAR | -0.823 |
Token | Sw |
Token ID | 2451 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Mug | +1.105 |
iron | +1.030 |
imus | +0.990 |
rone | +0.931 |
throat | +0.909 |
Neg logit contributions | |
Animation | -0.952 |
bj | -0.936 |
lections | -0.932 |
+= | -0.911 |
DAR | -0.891 |
Token | immer |
Token ID | 10957 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
Mug | +2.518 |
iron | +2.490 |
imus | +2.417 |
rone | +2.278 |
mia | +2.253 |
Neg logit contributions | |
Animation | -1.320 |
bj | -1.271 |
DAR | -1.256 |
+= | -1.250 |
lections | -1.222 |
Token | means |
Token ID | 1724 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
Animation | +0.173 |
bj | +0.170 |
lections | +0.168 |
+= | +0.166 |
DAR | +0.165 |
Neg logit contributions | |
Mug | -0.217 |
iron | -0.208 |
imus | -0.201 |
rone | -0.189 |
mia | -0.186 |
Token | to |
Token ID | 284 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
Mug | +4.268 |
iron | +4.052 |
imus | +3.813 |
throat | +3.604 |
rone | +3.563 |
Neg logit contributions | |
Animation | -4.149 |
bj | -4.105 |
lections | -4.045 |
DAR | -3.965 |
+= | -3.920 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Mug | +3.847 |
iron | +3.622 |
imus | +3.408 |
throat | +3.246 |
isol | +3.208 |
Neg logit contributions | |
Animation | -4.740 |
lections | -4.571 |
bj | -4.570 |
ternity | -4.440 |
DAR | -4.424 |
Token | fit |
Token ID | 4197 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Mug | +5.709 |
iron | +5.527 |
imus | +5.074 |
throat | +4.994 |
isol | +4.982 |
Neg logit contributions | |
lections | -7.130 |
Animation | -7.068 |
bj | -7.000 |
DAR | -6.875 |
INC | -6.767 |
Token | moving |
Token ID | 3867 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Mug | +5.464 |
iron | +5.111 |
imus | +4.955 |
isol | +4.670 |
throat | +4.528 |
Neg logit contributions | |
bj | -6.618 |
lections | -6.584 |
Animation | -6.582 |
DAR | -6.485 |
++) | -6.315 |
Token | about |
Token ID | 546 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Mug | +3.420 |
iron | +3.188 |
imus | +3.118 |
throat | +2.903 |
isol | +2.862 |
Neg logit contributions | |
Animation | -3.480 |
bj | -3.480 |
lections | -3.371 |
DAR | -3.324 |
+= | -3.311 |
Token | ( |
Token ID | 357 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
Animation | +2.426 |
bj | +2.354 |
+= | +2.348 |
lections | +2.329 |
DAR | +2.302 |
Neg logit contributions | |
Mug | -2.631 |
iron | -2.511 |
imus | -2.416 |
rone | -2.282 |
mia | -2.236 |
Token | 7 |
Token ID | 22 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Mug | +0.423 |
iron | +0.408 |
imus | +0.385 |
rone | +0.356 |
mia | +0.349 |
Neg logit contributions | |
Animation | -0.571 |
bj | -0.557 |
lections | -0.556 |
+= | -0.554 |
DAR | -0.553 |
Token | ) |
Token ID | 8 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Mug | +0.985 |
iron | +0.954 |
imus | +0.921 |
rone | +0.873 |
omy | +0.857 |
Neg logit contributions | |
Animation | -0.662 |
bj | -0.645 |
lections | -0.637 |
+= | -0.634 |
DAR | -0.627 |
Token | which |
Token ID | 543 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
Mug | +4.618 |
iron | +4.282 |
imus | +4.083 |
isol | +4.057 |
throat | +3.950 |
Neg logit contributions | |
Animation | -4.072 |
lections | -3.975 |
bj | -3.948 |
++) | -3.903 |
龍喚士 | -3.857 |
Token | would |
Token ID | 561 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Mug | +1.883 |
iron | +1.746 |
imus | +1.720 |
isol | +1.637 |
rone | +1.618 |
Neg logit contributions | |
Animation | -1.260 |
bj | -1.217 |
lections | -1.216 |
+= | -1.177 |
ternity | -1.145 |
Token | likely |
Token ID | 1884 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Mug | +1.169 |
iron | +1.115 |
imus | +1.076 |
rone | +0.991 |
throat | +0.991 |
Neg logit contributions | |
Animation | -1.277 |
bj | -1.232 |
lections | -1.225 |
+= | -1.202 |
DAR | -1.198 |
Token | involve |
Token ID | 6211 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
Mug | +1.305 |
iron | +1.237 |
imus | +1.195 |
throat | +1.099 |
rone | +1.097 |
Neg logit contributions | |
Animation | -1.543 |
bj | -1.489 |
lections | -1.482 |
+= | -1.452 |
DAR | -1.446 |
Token | medication |
Token ID | 14103 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Mug | +2.386 |
iron | +2.200 |
imus | +2.142 |
isol | +2.041 |
throat | +2.036 |
Neg logit contributions | |
Animation | -2.464 |
bj | -2.432 |
lections | -2.376 |
+= | -2.355 |
++) | -2.301 |
Token | ; |
Token ID | 26 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Mug | +0.758 |
iron | +0.718 |
imus | +0.698 |
rone | +0.657 |
mia | +0.650 |
Neg logit contributions | |
Animation | -0.602 |
bj | -0.590 |
lections | -0.582 |
+= | -0.570 |
DAR | -0.569 |
Token | or |
Token ID | 393 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Mug | +6.356 |
iron | +5.811 |
isol | +5.669 |
imus | +5.502 |
omy | +5.456 |
Neg logit contributions | |
Animation | -5.834 |
lections | -5.715 |
bj | -5.600 |
龍喚士 | -5.592 |
++) | -5.480 |
Token | the |
Token ID | 262 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Mug | +2.778 |
iron | +2.547 |
imus | +2.479 |
isol | +2.389 |
rone | +2.371 |
Neg logit contributions | |
Animation | -2.828 |
bj | -2.738 |
lections | -2.727 |
+= | -2.663 |
++) | -2.632 |
Token | � |
Token ID | 564 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Mug | +2.670 |
iron | +2.447 |
imus | +2.406 |
isol | +2.294 |
throat | +2.289 |
Neg logit contributions | |
Animation | -2.940 |
bj | -2.866 |
lections | -2.839 |
+= | -2.757 |
++) | -2.725 |
Token | � |
Token ID | 246 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
Mug | +0.804 |
iron | +0.783 |
imus | +0.743 |
rone | +0.698 |
mia | +0.687 |
Neg logit contributions | |
Animation | -0.773 |
bj | -0.756 |
lections | -0.745 |
+= | -0.743 |
DAR | -0.743 |
Token | talking |
Token ID | 48186 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Animation | +0.048 |
bj | +0.047 |
lections | +0.046 |
+= | +0.046 |
DAR | +0.046 |
Neg logit contributions | |
Mug | -0.053 |
iron | -0.051 |
imus | -0.049 |
rone | -0.046 |
mia | -0.045 |
Token | "] |
Token ID | 8973 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
Animation | +0.904 |
bj | +0.889 |
+= | +0.883 |
lections | +0.874 |
DAR | +0.870 |
Neg logit contributions | |
Mug | -0.684 |
iron | -0.648 |
imus | -0.622 |
rone | -0.572 |
throat | -0.559 |
Token | [ |
Token ID | 685 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Mug | +0.559 |
iron | +0.523 |
imus | +0.498 |
rone | +0.464 |
mia | +0.457 |
Neg logit contributions | |
Animation | -0.680 |
bj | -0.672 |
lections | -0.670 |
+= | -0.652 |
DAR | -0.650 |
Token | P |
Token ID | 47 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Mug | +2.507 |
iron | +2.411 |
mia | +2.160 |
rone | +2.091 |
imus | +2.088 |
Neg logit contributions | |
bj | -2.942 |
DAR | -2.932 |
lections | -2.920 |
Animation | -2.914 |
+= | -2.843 |
Token | ly |
Token ID | 306 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
Animation | +1.605 |
bj | +1.548 |
CH | +1.547 |
+= | +1.535 |
lections | +1.486 |
Neg logit contributions | |
Mug | -2.351 |
iron | -2.214 |
imus | -2.198 |
rone | -2.096 |
throat | -2.050 |
Token | Count |
Token ID | 12332 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
+= | +2.393 |
Animation | +2.293 |
CH | +2.271 |
DAR | +2.260 |
Women | +2.228 |
Neg logit contributions | |
Mug | -4.551 |
iron | -4.509 |
imus | -4.457 |
rone | -4.222 |
terday | -4.198 |
Token | " |
Token ID | 366 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Animation | +0.339 |
bj | +0.330 |
+= | +0.326 |
lections | +0.324 |
DAR | +0.320 |
Neg logit contributions | |
Mug | -0.484 |
iron | -0.466 |
imus | -0.451 |
rone | -0.426 |
mia | -0.419 |
Token | 94 |
Token ID | 5824 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Mug | +5.445 |
iron | +5.233 |
imus | +4.844 |
rone | +4.601 |
Rog | +4.554 |
Neg logit contributions | |
lections | -6.573 |
Animation | -6.523 |
bj | -6.435 |
DAR | -6.337 |
ternity | -6.304 |
Token | "] |
Token ID | 8973 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Mug | +2.107 |
iron | +1.986 |
imus | +1.821 |
rone | +1.717 |
mia | +1.704 |
Neg logit contributions | |
Animation | -3.582 |
bj | -3.528 |
lections | -3.494 |
+= | -3.434 |
DAR | -3.422 |
Token | [ |
Token ID | 685 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
Mug | +1.883 |
iron | +1.740 |
imus | +1.636 |
rone | +1.530 |
mia | +1.507 |
Neg logit contributions | |
bj | -2.410 |
Animation | -2.409 |
lections | -2.405 |
+= | -2.303 |
DAR | -2.302 |
Token | Event |
Token ID | 9237 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Mug | +3.867 |
iron | +3.294 |
Rog | +2.827 |
rone | +2.785 |
mia | +2.768 |
Neg logit contributions | |
bj | -7.696 |
Animation | -7.510 |
DAR | -7.490 |
lections | -7.372 |
awar | -7.338 |
Token | Date |
Token ID | 10430 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Mug | +1.356 |
iron | +1.272 |
imus | +1.193 |
rone | +1.112 |
mia | +1.102 |
Neg logit contributions | |
Animation | -1.855 |
lections | -1.852 |
bj | -1.837 |
+= | -1.818 |
DAR | -1.809 |
Token | { |
Token ID | 1391 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Mug | +0.154 |
iron | +0.148 |
imus | +0.143 |
rone | +0.135 |
mia | +0.132 |
Neg logit contributions | |
Animation | -0.116 |
bj | -0.114 |
lections | -0.113 |
DAR | -0.111 |
+= | -0.109 |
Token | | |
Token ID | 91 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
Mug | +1.706 |
iron | +1.612 |
imus | +1.540 |
rone | +1.453 |
throat | +1.447 |
Neg logit contributions | |
Animation | -1.520 |
bj | -1.498 |
lections | -1.489 |
DAR | -1.456 |
+= | -1.434 |
Token | i |
Token ID | 72 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Animation | +0.445 |
bj | +0.434 |
lections | +0.429 |
+= | +0.427 |
DAR | +0.422 |
Neg logit contributions | |
Mug | -0.589 |
iron | -0.566 |
imus | -0.546 |
rone | -0.516 |
mia | -0.508 |
Token | | |
Token ID | 91 |
Feature activation | +2.42e-03 |
Pos logit contributions | |
Mug | +1.237 |
iron | +1.173 |
imus | +1.118 |
rone | +0.999 |
omy | +0.992 |
Neg logit contributions | |
Animation | -1.935 |
bj | -1.921 |
lections | -1.877 |
DAR | -1.848 |
+= | -1.841 |
Token | print |
Token ID | 3601 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
Animation | +0.015 |
bj | +0.015 |
lections | +0.015 |
DAR | +0.015 |
+= | +0.015 |
Neg logit contributions | |
Mug | -0.015 |
iron | -0.014 |
imus | -0.014 |
rone | -0.013 |
mia | -0.013 |
Token | "# |
Token ID | 25113 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Animation | +0.215 |
bj | +0.211 |
lections | +0.209 |
+= | +0.206 |
DAR | +0.206 |
Neg logit contributions | |
Mug | -0.201 |
iron | -0.191 |
imus | -0.183 |
rone | -0.171 |
mia | -0.168 |
Token | { |
Token ID | 90 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
Mug | +6.487 |
iron | +6.390 |
imus | +6.065 |
mia | +5.711 |
rone | +5.639 |
Neg logit contributions | |
Animation | -5.412 |
bj | -5.357 |
lections | -5.288 |
DAR | -5.206 |
Architects | -5.142 |
Token | i |
Token ID | 72 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
Mug | +2.490 |
iron | +2.425 |
imus | +2.297 |
rone | +2.145 |
mia | +2.124 |
Neg logit contributions | |
Animation | -2.600 |
bj | -2.532 |
lections | -2.515 |
DAR | -2.498 |
+= | -2.467 |
Token | } |
Token ID | 92 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
Mug | +0.200 |
iron | +0.194 |
imus | +0.185 |
rone | +0.174 |
omy | +0.172 |
Neg logit contributions | |
Animation | -0.169 |
bj | -0.168 |
lections | -0.166 |
DAR | -0.162 |
+= | -0.159 |
Token | " |
Token ID | 366 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
Mug | +3.647 |
iron | +3.479 |
imus | +3.365 |
isol | +3.168 |
rone | +3.146 |
Neg logit contributions | |
Animation | -3.078 |
bj | -3.013 |
lections | -2.969 |
DAR | -2.929 |
龍喚士 | -2.880 |
Token | } |
Token ID | 92 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
Mug | +2.498 |
iron | +2.420 |
imus | +2.309 |
rone | +2.160 |
mia | +2.135 |
Neg logit contributions | |
Animation | -2.477 |
bj | -2.412 |
lections | -2.411 |
DAR | -2.355 |
CH | -2.309 |
Token | — |
Token ID | 851 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Mug | +1.929 |
iron | +1.766 |
imus | +1.688 |
rone | +1.581 |
omy | +1.549 |
Neg logit contributions | |
Animation | -2.683 |
lections | -2.628 |
bj | -2.606 |
+= | -2.592 |
DAR | -2.576 |
Token | tele |
Token ID | 5735 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Mug | +1.049 |
iron | +0.981 |
imus | +0.948 |
rone | +0.887 |
mia | +0.883 |
Neg logit contributions | |
Animation | -0.887 |
bj | -0.861 |
lections | -0.855 |
+= | -0.851 |
++) | -0.823 |
Token | S |
Token ID | 50 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Mug | +1.007 |
iron | +0.980 |
imus | +0.937 |
rone | +0.870 |
mia | +0.865 |
Neg logit contributions | |
Animation | -0.917 |
bj | -0.895 |
lections | -0.885 |
+= | -0.884 |
DAR | -0.874 |
Token | UR |
Token ID | 4261 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
Mug | +1.706 |
iron | +1.695 |
imus | +1.610 |
mia | +1.542 |
omy | +1.530 |
Neg logit contributions | |
Animation | -0.793 |
lections | -0.751 |
+= | -0.746 |
bj | -0.743 |
DAR | -0.739 |
Token | English |
Token ID | 3594 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
Animation | +0.141 |
bj | +0.137 |
lections | +0.135 |
+= | +0.135 |
DAR | +0.133 |
Neg logit contributions | |
Mug | -0.162 |
iron | -0.155 |
imus | -0.149 |
rone | -0.140 |
mia | -0.138 |
Token | (@ |
Token ID | 4275 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Animation | +0.201 |
bj | +0.197 |
lections | +0.194 |
+= | +0.193 |
DAR | +0.191 |
Neg logit contributions | |
Mug | -0.235 |
iron | -0.224 |
imus | -0.217 |
rone | -0.204 |
mia | -0.201 |
Token | tel |
Token ID | 37524 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
iron | +5.731 |
Mug | +5.542 |
imus | +5.405 |
mia | +4.963 |
Rog | +4.841 |
Neg logit contributions | |
Animation | -6.244 |
DAR | -6.189 |
+= | -6.184 |
lections | -6.092 |
Architects | -6.003 |
Token | es |
Token ID | 274 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Mug | +0.086 |
iron | +0.084 |
imus | +0.081 |
rone | +0.075 |
mia | +0.075 |
Neg logit contributions | |
Animation | -0.072 |
bj | -0.070 |
+= | -0.069 |
DAR | -0.069 |
lections | -0.069 |
Token | ure |
Token ID | 495 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
Mug | +1.313 |
iron | +1.293 |
imus | +1.265 |
rone | +1.194 |
mia | +1.184 |
Neg logit contributions | |
Animation | -0.552 |
bj | -0.516 |
DAR | -0.509 |
+= | -0.508 |
lections | -0.503 |
Token | ng |
Token ID | 782 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
Animation | +0.213 |
bj | +0.208 |
lections | +0.205 |
+= | +0.205 |
DAR | +0.203 |
Neg logit contributions | |
Mug | -0.254 |
iron | -0.244 |
imus | -0.235 |
rone | -0.222 |
mia | -0.218 |
Token | lish |
Token ID | 1836 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
Mug | +0.517 |
iron | +0.501 |
imus | +0.483 |
rone | +0.457 |
omy | +0.449 |
Neg logit contributions | |
Animation | -0.393 |
bj | -0.382 |
+= | -0.377 |
DAR | -0.376 |
lections | -0.376 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
Mug | +1.007 |
iron | +0.971 |
imus | +0.922 |
rone | +0.873 |
omy | +0.856 |
Neg logit contributions | |
Animation | -0.879 |
bj | -0.857 |
lections | -0.849 |
+= | -0.843 |
DAR | -0.835 |
Token | open |
Token ID | 1280 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Animation | +0.077 |
bj | +0.075 |
lections | +0.074 |
+= | +0.074 |
DAR | +0.073 |
Neg logit contributions | |
Mug | -0.055 |
iron | -0.052 |
imus | -0.050 |
rone | -0.046 |
throat | -0.045 |
Token | flights |
Token ID | 13956 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Animation | +2.328 |
bj | +2.280 |
lections | +2.258 |
+= | +2.253 |
DAR | +2.220 |
Neg logit contributions | |
Mug | -2.254 |
iron | -2.098 |
imus | -2.050 |
rone | -1.899 |
mia | -1.872 |
Token | to |
Token ID | 284 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
Animation | +1.361 |
bj | +1.328 |
+= | +1.310 |
lections | +1.300 |
DAR | +1.292 |
Neg logit contributions | |
Mug | -1.753 |
iron | -1.690 |
imus | -1.648 |
rone | -1.550 |
mia | -1.517 |
Token | US |
Token ID | 1294 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
Animation | +0.295 |
+= | +0.288 |
bj | +0.285 |
lections | +0.283 |
++) | +0.277 |
Neg logit contributions | |
Mug | -0.306 |
iron | -0.292 |
imus | -0.271 |
rone | -0.261 |
isol | -0.259 |
Token | on |
Token ID | 319 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
Animation | +0.243 |
bj | +0.237 |
lections | +0.236 |
+= | +0.235 |
DAR | +0.229 |
Neg logit contributions | |
Mug | -0.248 |
iron | -0.236 |
imus | -0.222 |
rone | -0.215 |
omy | -0.207 |
Token | sidelines |
Token ID | 29394 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Animation | +4.944 |
bj | +4.844 |
lections | +4.789 |
+= | +4.775 |
DAR | +4.750 |
Neg logit contributions | |
Mug | -5.321 |
iron | -5.188 |
imus | -4.981 |
rone | -4.651 |
mia | -4.604 |
Token | of |
Token ID | 286 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
Animation | +1.572 |
bj | +1.528 |
+= | +1.527 |
lections | +1.501 |
DAR | +1.491 |
Neg logit contributions | |
Mug | -2.336 |
iron | -2.272 |
imus | -2.219 |
rone | -2.094 |
omy | -2.074 |
Token | Trump |
Token ID | 1301 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Women | +2.641 |
DAR | +2.530 |
++) | +2.422 |
Animation | +2.404 |
CH | +2.394 |
Neg logit contributions | |
Mug | -3.916 |
iron | -3.867 |
imus | -3.833 |
rone | -3.697 |
omy | -3.630 |
Token | - |
Token ID | 12 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
Animation | +2.757 |
Women | +2.709 |
bj | +2.665 |
lections | +2.648 |
DAR | +2.594 |
Neg logit contributions | |
Mug | -4.001 |
iron | -3.935 |
imus | -3.765 |
rone | -3.546 |
ebted | -3.543 |
Token | Kim |
Token ID | 26374 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Animation | +5.290 |
bj | +5.083 |
CH | +4.972 |
DAR | +4.864 |
lections | +4.849 |
Neg logit contributions | |
Mug | -6.360 |
imus | -6.217 |
iron | -5.934 |
throat | -5.652 |
mia | -5.641 |
Token | to |
Token ID | 284 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
Animation | +3.284 |
bj | +3.197 |
DAR | +3.163 |
lections | +3.160 |
+= | +3.156 |
Neg logit contributions | |
Mug | -3.970 |
iron | -3.819 |
imus | -3.686 |
rone | -3.474 |
mia | -3.425 |
Token | do |
Token ID | 466 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
Animation | +1.653 |
bj | +1.613 |
+= | +1.585 |
lections | +1.582 |
DAR | +1.573 |
Neg logit contributions | |
Mug | -2.567 |
iron | -2.487 |
imus | -2.402 |
rone | -2.272 |
mia | -2.246 |
Token | with |
Token ID | 351 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
Animation | +2.397 |
bj | +2.342 |
+= | +2.325 |
DAR | +2.300 |
lections | +2.271 |
Neg logit contributions | |
Mug | -2.940 |
iron | -2.827 |
imus | -2.741 |
rone | -2.548 |
mia | -2.545 |
Token | electoral |
Token ID | 13901 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
Animation | +0.256 |
bj | +0.251 |
+= | +0.247 |
lections | +0.247 |
DAR | +0.242 |
Neg logit contributions | |
Mug | -0.240 |
iron | -0.225 |
imus | -0.217 |
rone | -0.203 |
mia | -0.199 |
Token | politics |
Token ID | 4819 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Animation | +0.680 |
bj | +0.665 |
lections | +0.658 |
+= | +0.655 |
DAR | +0.645 |
Neg logit contributions | |
Mug | -0.730 |
iron | -0.699 |
imus | -0.666 |
rone | -0.631 |
mia | -0.622 |
Token | than |
Token ID | 621 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
Animation | +1.360 |
bj | +1.330 |
lections | +1.313 |
+= | +1.308 |
DAR | +1.294 |
Neg logit contributions | |
Mug | -1.624 |
iron | -1.555 |
imus | -1.500 |
rone | -1.412 |
mia | -1.389 |
Token | it |
Token ID | 340 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
Animation | +4.120 |
DAR | +4.109 |
bj | +4.093 |
Women | +4.006 |
lections | +4.000 |
Neg logit contributions | |
Mug | -4.388 |
iron | -4.335 |
imus | -4.157 |
rone | -3.905 |
mia | -3.850 |
Token | had |
Token ID | 550 |
Feature activation | +1.46e-03 |
Pos logit contributions | |
Animation | +0.256 |
bj | +0.248 |
lections | +0.247 |
+= | +0.246 |
DAR | +0.240 |
Neg logit contributions | |
Mug | -0.393 |
iron | -0.377 |
imus | -0.365 |
rone | -0.347 |
omy | -0.342 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Animation | +0.009 |
bj | +0.009 |
+= | +0.009 |
lections | +0.009 |
DAR | +0.008 |
Neg logit contributions | |
Mug | -0.010 |
iron | -0.009 |
imus | -0.009 |
rone | -0.008 |
omy | -0.008 |
Token | do |
Token ID | 466 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Animation | +0.553 |
bj | +0.533 |
lections | +0.531 |
+= | +0.526 |
DAR | +0.513 |
Neg logit contributions | |
Mug | -0.729 |
iron | -0.692 |
imus | -0.670 |
rone | -0.638 |
omy | -0.625 |
Token | with |
Token ID | 351 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Mug | +1.635 |
iron | +1.515 |
imus | +1.451 |
rone | +1.375 |
omy | +1.356 |
Neg logit contributions | |
Animation | -1.890 |
bj | -1.851 |
+= | -1.836 |
lections | -1.823 |
DAR | -1.772 |
Token | suggest |
Token ID | 1950 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Mug | +1.386 |
iron | +1.299 |
imus | +1.252 |
throat | +1.175 |
rone | +1.167 |
Neg logit contributions | |
Animation | -1.439 |
lections | -1.400 |
bj | -1.399 |
+= | -1.377 |
DAR | -1.364 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Mug | +0.837 |
iron | +0.790 |
imus | +0.761 |
rone | +0.710 |
throat | +0.704 |
Neg logit contributions | |
Animation | -0.867 |
bj | -0.858 |
lections | -0.845 |
+= | -0.843 |
DAR | -0.838 |
Token | few |
Token ID | 1178 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Mug | +0.685 |
iron | +0.641 |
imus | +0.612 |
throat | +0.579 |
rone | +0.579 |
Neg logit contributions | |
Animation | -0.689 |
bj | -0.679 |
lections | -0.671 |
+= | -0.664 |
DAR | -0.658 |
Token | non |
Token ID | 1729 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Mug | +0.068 |
iron | +0.064 |
imus | +0.062 |
rone | +0.057 |
throat | +0.057 |
Neg logit contributions | |
Animation | -0.075 |
bj | -0.074 |
lections | -0.073 |
+= | -0.073 |
DAR | -0.072 |
Token | - |
Token ID | 12 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Animation | +0.650 |
bj | +0.637 |
lections | +0.627 |
+= | +0.627 |
DAR | +0.622 |
Neg logit contributions | |
Mug | -0.769 |
iron | -0.739 |
imus | -0.710 |
rone | -0.670 |
mia | -0.658 |
Token | tax |
Token ID | 19290 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
Animation | +1.384 |
bj | +1.354 |
lections | +1.338 |
+= | +1.333 |
DAR | +1.318 |
Neg logit contributions | |
Mug | -1.430 |
iron | -1.362 |
imus | -1.313 |
rone | -1.231 |
mia | -1.207 |
Token | ing |
Token ID | 278 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Animation | +4.543 |
bj | +4.488 |
lections | +4.410 |
+= | +4.330 |
DAR | +4.222 |
Neg logit contributions | |
Mug | -5.450 |
iron | -5.136 |
imus | -4.954 |
rone | -4.667 |
throat | -4.618 |
Token | activities |
Token ID | 4568 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Mug | +0.623 |
iron | +0.576 |
imus | +0.550 |
rone | +0.514 |
throat | +0.513 |
Neg logit contributions | |
Animation | -0.795 |
bj | -0.791 |
lections | -0.772 |
+= | -0.772 |
DAR | -0.761 |
Token | that |
Token ID | 326 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Mug | +1.228 |
iron | +1.175 |
imus | +1.130 |
rone | +1.050 |
isol | +1.047 |
Neg logit contributions | |
Animation | -1.122 |
bj | -1.093 |
lections | -1.091 |
+= | -1.072 |
DAR | -1.067 |
Token | the |
Token ID | 262 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Mug | +0.924 |
iron | +0.867 |
imus | +0.841 |
rone | +0.791 |
throat | +0.780 |
Neg logit contributions | |
Animation | -0.879 |
bj | -0.858 |
lections | -0.857 |
+= | -0.841 |
DAR | -0.828 |
Token | person |
Token ID | 1048 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Mug | +2.382 |
iron | +2.172 |
imus | +2.099 |
rone | +1.990 |
throat | +1.984 |
Neg logit contributions | |
Animation | -2.973 |
bj | -2.935 |
lections | -2.918 |
+= | -2.862 |
DAR | -2.823 |
Token | This |
Token ID | 770 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
Animation | +2.659 |
bj | +2.606 |
+= | +2.568 |
DAR | +2.547 |
lections | +2.541 |
Neg logit contributions | |
Mug | -2.939 |
iron | -2.858 |
imus | -2.748 |
rone | -2.585 |
mia | -2.541 |
Token | is |
Token ID | 318 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
Animation | +0.122 |
bj | +0.119 |
lections | +0.119 |
+= | +0.117 |
DAR | +0.115 |
Neg logit contributions | |
Mug | -0.163 |
iron | -0.155 |
imus | -0.150 |
rone | -0.142 |
throat | -0.140 |
Token | also |
Token ID | 635 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Mug | +0.303 |
iron | +0.288 |
imus | +0.275 |
rone | +0.256 |
mia | +0.252 |
Neg logit contributions | |
Animation | -0.327 |
bj | -0.319 |
lections | -0.317 |
+= | -0.316 |
DAR | -0.311 |
Token | mentioned |
Token ID | 4750 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
Animation | +0.082 |
bj | +0.080 |
lections | +0.080 |
+= | +0.079 |
DAR | +0.078 |
Neg logit contributions | |
Mug | -0.072 |
iron | -0.068 |
imus | -0.066 |
rone | -0.061 |
mia | -0.060 |
Token | in |
Token ID | 287 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Animation | +0.408 |
bj | +0.400 |
lections | +0.395 |
+= | +0.393 |
DAR | +0.388 |
Neg logit contributions | |
Mug | -0.490 |
iron | -0.469 |
imus | -0.453 |
rone | -0.426 |
mia | -0.418 |
Token | Sunni |
Token ID | 18592 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
Animation | +2.460 |
bj | +2.413 |
lections | +2.380 |
+= | +2.378 |
DAR | +2.360 |
Neg logit contributions | |
Mug | -2.725 |
iron | -2.632 |
imus | -2.533 |
rone | -2.385 |
mia | -2.341 |
Token | Had |
Token ID | 11161 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Animation | +3.664 |
bj | +3.505 |
lections | +3.501 |
+= | +3.491 |
Women | +3.445 |
Neg logit contributions | |
Mug | -5.415 |
iron | -5.274 |
imus | -5.105 |
rone | -4.901 |
mia | -4.729 |
Token | ith |
Token ID | 342 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
Animation | +1.244 |
bj | +1.214 |
+= | +1.203 |
lections | +1.203 |
DAR | +1.189 |
Neg logit contributions | |
Mug | -1.205 |
iron | -1.159 |
imus | -1.106 |
rone | -1.038 |
mia | -1.018 |
Token | collections |
Token ID | 17268 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Animation | +0.505 |
bj | +0.497 |
+= | +0.487 |
lections | +0.484 |
DAR | +0.483 |
Neg logit contributions | |
Mug | -0.652 |
iron | -0.623 |
imus | -0.602 |
rone | -0.570 |
mia | -0.562 |
Token | : |
Token ID | 25 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Animation | +1.705 |
bj | +1.663 |
lections | +1.643 |
+= | +1.637 |
DAR | +1.618 |
Neg logit contributions | |
Mug | -2.264 |
iron | -2.174 |
imus | -2.101 |
rone | -1.990 |
mia | -1.953 |
Token |
|
Token ID | 198 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Animation | +1.961 |
bj | +1.918 |
+= | +1.893 |
lections | +1.887 |
DAR | +1.874 |
Neg logit contributions | |
Mug | -2.118 |
iron | -2.037 |
imus | -1.963 |
rone | -1.847 |
mia | -1.809 |
Token | � |
Token ID | 447 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Animation | +0.031 |
bj | +0.030 |
+= | +0.030 |
lections | +0.030 |
DAR | +0.029 |
Neg logit contributions | |
Mug | -0.045 |
iron | -0.044 |
imus | -0.042 |
rone | -0.040 |
throat | -0.039 |
Token | � |
Token ID | 247 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Animation | +0.607 |
bj | +0.595 |
lections | +0.586 |
+= | +0.583 |
DAR | +0.581 |
Neg logit contributions | |
Mug | -0.742 |
iron | -0.711 |
imus | -0.684 |
rone | -0.644 |
mia | -0.635 |
Token | s |
Token ID | 82 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Animation | +1.094 |
bj | +1.069 |
lections | +1.055 |
+= | +1.046 |
DAR | +1.032 |
Neg logit contributions | |
Mug | -1.612 |
iron | -1.546 |
imus | -1.495 |
rone | -1.417 |
mia | -1.393 |
Token | point |
Token ID | 966 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Animation | +1.352 |
bj | +1.327 |
lections | +1.313 |
+= | +1.311 |
DAR | +1.298 |
Neg logit contributions | |
Mug | -1.036 |
iron | -0.980 |
imus | -0.937 |
rone | -0.867 |
mia | -0.847 |
Token | of |
Token ID | 286 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
Animation | +0.874 |
bj | +0.852 |
lections | +0.841 |
+= | +0.838 |
DAR | +0.827 |
Neg logit contributions | |
Mug | -1.212 |
iron | -1.164 |
imus | -1.125 |
rone | -1.065 |
mia | -1.047 |
Token | view |
Token ID | 1570 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
Animation | +3.188 |
bj | +3.111 |
lections | +3.093 |
+= | +3.079 |
DAR | +3.073 |
Neg logit contributions | |
Mug | -3.293 |
iron | -3.157 |
imus | -3.028 |
rone | -2.855 |
mia | -2.794 |
Token | ) |
Token ID | 8 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Animation | +3.308 |
bj | +3.216 |
+= | +3.183 |
lections | +3.162 |
++) | +3.083 |
Neg logit contributions | |
Mug | -6.096 |
iron | -5.872 |
imus | -5.665 |
rone | -5.468 |
mia | -5.349 |
Token | right |
Token ID | 826 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Animation | +2.580 |
bj | +2.489 |
DAR | +2.489 |
+= | +2.482 |
lections | +2.471 |
Neg logit contributions | |
Mug | -2.878 |
iron | -2.768 |
imus | -2.665 |
rone | -2.512 |
mia | -2.496 |
Token | - |
Token ID | 12 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Animation | +1.059 |
bj | +1.037 |
lections | +1.023 |
+= | +1.020 |
DAR | +1.007 |
Neg logit contributions | |
Mug | -1.337 |
iron | -1.282 |
imus | -1.239 |
rone | -1.170 |
omy | -1.145 |
Token | wing |
Token ID | 5469 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
Animation | +1.800 |
bj | +1.743 |
lections | +1.709 |
+= | +1.705 |
DAR | +1.683 |
Neg logit contributions | |
Mug | -3.306 |
iron | -3.162 |
imus | -3.092 |
rone | -2.926 |
mia | -2.906 |
Token | ers |
Token ID | 364 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
Animation | +3.122 |
bj | +3.008 |
DAR | +2.993 |
lections | +2.988 |
+= | +2.987 |
Neg logit contributions | |
Mug | -3.257 |
iron | -3.120 |
imus | -2.970 |
rone | -2.804 |
mia | -2.787 |
Token | parliament |
Token ID | 8540 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Mug | +1.349 |
iron | +1.276 |
imus | +1.225 |
rone | +1.152 |
throat | +1.143 |
Neg logit contributions | |
Animation | -1.192 |
bj | -1.161 |
lections | -1.150 |
+= | -1.139 |
DAR | -1.120 |
Token | . |
Token ID | 13 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
Mug | +1.916 |
iron | +1.846 |
imus | +1.755 |
rone | +1.669 |
mia | +1.637 |
Neg logit contributions | |
Animation | -1.686 |
bj | -1.643 |
lections | -1.624 |
+= | -1.622 |
DAR | -1.608 |
Token | � |
Token ID | 447 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Mug | +1.832 |
iron | +1.703 |
imus | +1.620 |
rone | +1.534 |
mia | +1.494 |
Neg logit contributions | |
Animation | -1.759 |
lections | -1.740 |
bj | -1.737 |
+= | -1.691 |
DAR | -1.660 |
Token | � |
Token ID | 251 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Animation | +0.744 |
bj | +0.729 |
lections | +0.723 |
+= | +0.719 |
DAR | +0.714 |
Neg logit contributions | |
Mug | -0.725 |
iron | -0.693 |
imus | -0.663 |
rone | -0.621 |
mia | -0.610 |
Token |
|
Token ID | 198 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
Mug | +1.024 |
iron | +0.957 |
imus | +0.920 |
rone | +0.865 |
mia | +0.848 |
Neg logit contributions | |
Animation | -0.993 |
bj | -0.978 |
lections | -0.976 |
+= | -0.960 |
DAR | -0.948 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Animation | +0.362 |
bj | +0.354 |
lections | +0.351 |
+= | +0.349 |
DAR | +0.345 |
Neg logit contributions | |
Mug | -0.366 |
iron | -0.349 |
imus | -0.335 |
rone | -0.314 |
mia | -0.309 |
Token | Relations |
Token ID | 47117 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Animation | +1.081 |
bj | +1.056 |
lections | +1.039 |
+= | +1.038 |
DAR | +1.024 |
Neg logit contributions | |
Mug | -1.209 |
iron | -1.152 |
imus | -1.114 |
rone | -1.048 |
mia | -1.026 |
Token | between |
Token ID | 1022 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
Mug | +0.934 |
iron | +0.891 |
imus | +0.857 |
rone | +0.794 |
mia | +0.783 |
Neg logit contributions | |
Animation | -0.970 |
lections | -0.956 |
bj | -0.946 |
DAR | -0.943 |
+= | -0.939 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Mug | +0.231 |
iron | +0.219 |
imus | +0.211 |
rone | +0.200 |
mia | +0.196 |
Neg logit contributions | |
Animation | -0.177 |
bj | -0.173 |
lections | -0.171 |
+= | -0.169 |
DAR | -0.166 |
Token | Catalan |
Token ID | 31066 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Mug | +0.851 |
iron | +0.802 |
imus | +0.773 |
rone | +0.728 |
throat | +0.716 |
Neg logit contributions | |
Animation | -0.761 |
bj | -0.744 |
lections | -0.737 |
+= | -0.731 |
DAR | -0.716 |
Token | and |
Token ID | 290 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Animation | +0.803 |
bj | +0.789 |
lections | +0.780 |
+= | +0.777 |
DAR | +0.768 |
Neg logit contributions | |
Mug | -0.713 |
iron | -0.676 |
imus | -0.647 |
rone | -0.605 |
mia | -0.592 |
Token | services |
Token ID | 2594 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
Animation | +1.394 |
bj | +1.367 |
lections | +1.351 |
+= | +1.348 |
DAR | +1.334 |
Neg logit contributions | |
Mug | -1.292 |
iron | -1.230 |
imus | -1.181 |
rone | -1.103 |
mia | -1.081 |
Token | of |
Token ID | 286 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
Animation | +2.695 |
lections | +2.581 |
bj | +2.560 |
+= | +2.546 |
DAR | +2.526 |
Neg logit contributions | |
Mug | -4.208 |
iron | -4.120 |
imus | -3.977 |
rone | -3.793 |
mia | -3.713 |
Token | Elliot |
Token ID | 30451 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
Animation | +1.878 |
bj | +1.834 |
lections | +1.816 |
+= | +1.811 |
DAR | +1.799 |
Neg logit contributions | |
Mug | -2.045 |
iron | -1.969 |
imus | -1.895 |
rone | -1.779 |
mia | -1.746 |
Token | Weinstein |
Token ID | 22473 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Mug | +0.364 |
iron | +0.342 |
imus | +0.331 |
rone | +0.311 |
mia | +0.305 |
Neg logit contributions | |
Animation | -0.367 |
bj | -0.355 |
lections | -0.353 |
+= | -0.352 |
DAR | -0.347 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Animation | +1.578 |
bj | +1.540 |
lections | +1.519 |
+= | +1.515 |
DAR | +1.496 |
Neg logit contributions | |
Mug | -2.089 |
iron | -2.004 |
imus | -1.937 |
rone | -1.830 |
mia | -1.800 |
Token | a |
Token ID | 257 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Animation | +2.006 |
bj | +1.964 |
lections | +1.938 |
+= | +1.936 |
DAR | +1.925 |
Neg logit contributions | |
Mug | -2.165 |
iron | -2.083 |
imus | -2.006 |
rone | -1.888 |
mia | -1.852 |
Token | well |
Token ID | 880 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Animation | +1.501 |
bj | +1.470 |
lections | +1.453 |
+= | +1.451 |
DAR | +1.439 |
Neg logit contributions | |
Mug | -1.494 |
iron | -1.430 |
imus | -1.373 |
rone | -1.286 |
mia | -1.261 |
Token | - |
Token ID | 12 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
Animation | +1.349 |
bj | +1.321 |
lections | +1.304 |
+= | +1.301 |
DAR | +1.287 |
Neg logit contributions | |
Mug | -1.447 |
iron | -1.382 |
imus | -1.331 |
rone | -1.249 |
mia | -1.227 |
Token | known |
Token ID | 4002 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Mug | +0.500 |
iron | +0.485 |
imus | +0.458 |
rone | +0.430 |
mia | +0.421 |
Neg logit contributions | |
Animation | -0.537 |
lections | -0.521 |
bj | -0.521 |
+= | -0.520 |
DAR | -0.511 |
Token | defense |
Token ID | 3761 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Animation | +1.408 |
bj | +1.380 |
lections | +1.364 |
+= | +1.361 |
DAR | +1.348 |
Neg logit contributions | |
Mug | -1.329 |
iron | -1.267 |
imus | -1.216 |
rone | -1.137 |
mia | -1.114 |
Token | lawyer |
Token ID | 6853 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
Animation | +1.897 |
bj | +1.865 |
lections | +1.846 |
+= | +1.840 |
DAR | +1.820 |
Neg logit contributions | |
Mug | -1.511 |
iron | -1.429 |
imus | -1.368 |
rone | -1.269 |
mia | -1.238 |
Token | say |
Token ID | 910 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Animation | +0.293 |
bj | +0.286 |
lections | +0.283 |
+= | +0.280 |
DAR | +0.278 |
Neg logit contributions | |
Mug | -0.330 |
iron | -0.315 |
imus | -0.303 |
rone | -0.285 |
mia | -0.281 |
Token | it |
Token ID | 340 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Animation | +1.716 |
bj | +1.677 |
+= | +1.661 |
lections | +1.658 |
DAR | +1.646 |
Neg logit contributions | |
Mug | -1.715 |
iron | -1.634 |
imus | -1.579 |
rone | -1.472 |
mia | -1.449 |
Token | 's |
Token ID | 338 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Animation | +0.724 |
bj | +0.704 |
lections | +0.693 |
+= | +0.691 |
DAR | +0.681 |
Neg logit contributions | |
Mug | -1.195 |
iron | -1.150 |
imus | -1.116 |
rone | -1.060 |
mia | -1.044 |
Token | a |
Token ID | 257 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Animation | +2.097 |
+= | +2.051 |
bj | +2.043 |
lections | +2.030 |
DAR | +2.023 |
Neg logit contributions | |
Mug | -2.372 |
iron | -2.281 |
imus | -2.198 |
rone | -2.082 |
mia | -2.039 |
Token | circle |
Token ID | 9197 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
Animation | +2.189 |
bj | +2.152 |
+= | +2.151 |
DAR | +2.131 |
lections | +2.123 |
Neg logit contributions | |
Mug | -1.958 |
iron | -1.876 |
imus | -1.805 |
rone | -1.667 |
mia | -1.649 |
Token | . |
Token ID | 13 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
Animation | +0.401 |
bj | +0.393 |
lections | +0.388 |
+= | +0.386 |
DAR | +0.382 |
Neg logit contributions | |
Mug | -0.468 |
iron | -0.449 |
imus | -0.432 |
rone | -0.407 |
mia | -0.400 |
Token | So |
Token ID | 1406 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
Animation | +0.376 |
bj | +0.371 |
lections | +0.369 |
+= | +0.361 |
DAR | +0.356 |
Neg logit contributions | |
Mug | -0.409 |
iron | -0.387 |
imus | -0.371 |
rone | -0.351 |
omy | -0.341 |
Token | , |
Token ID | 11 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Animation | +0.384 |
bj | +0.377 |
lections | +0.372 |
+= | +0.369 |
DAR | +0.364 |
Neg logit contributions | |
Mug | -0.416 |
iron | -0.399 |
imus | -0.381 |
rone | -0.360 |
mia | -0.352 |
Token | Earth |
Token ID | 3668 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
Animation | +1.456 |
bj | +1.423 |
+= | +1.406 |
lections | +1.405 |
DAR | +1.390 |
Neg logit contributions | |
Mug | -1.656 |
iron | -1.583 |
imus | -1.530 |
rone | -1.437 |
mia | -1.414 |
Token | 's |
Token ID | 338 |
Feature activation | -8.71e-03 |
Pos logit contributions | |
Animation | +0.301 |
bj | +0.295 |
lections | +0.292 |
+= | +0.287 |
DAR | +0.285 |
Neg logit contributions | |
Mug | -0.436 |
iron | -0.421 |
imus | -0.406 |
rone | -0.384 |
mia | -0.378 |
Token | orbit |
Token ID | 13066 |
Feature activation | -3.13e-04 |
Pos logit contributions | |
Mug | +0.052 |
iron | +0.050 |
imus | +0.048 |
rone | +0.045 |
throat | +0.044 |
Neg logit contributions | |
Animation | -0.057 |
bj | -0.057 |
lections | -0.056 |
+= | -0.055 |
DAR | -0.055 |
Token | more |
Token ID | 517 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Mug | +0.714 |
iron | +0.679 |
imus | +0.649 |
isol | +0.603 |
rone | +0.600 |
Neg logit contributions | |
Animation | -0.782 |
bj | -0.766 |
lections | -0.757 |
+= | -0.753 |
DAR | -0.737 |
Token | commun |
Token ID | 1316 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Mug | +0.704 |
iron | +0.667 |
imus | +0.633 |
isol | +0.583 |
rone | +0.583 |
Neg logit contributions | |
Animation | -0.895 |
bj | -0.878 |
lections | -0.866 |
+= | -0.861 |
DAR | -0.847 |
Token | icative |
Token ID | 43058 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
Mug | +0.937 |
iron | +0.910 |
imus | +0.867 |
rone | +0.814 |
omy | +0.796 |
Neg logit contributions | |
Animation | -1.006 |
bj | -0.983 |
+= | -0.972 |
lections | -0.968 |
DAR | -0.963 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
Animation | +0.216 |
bj | +0.212 |
lections | +0.209 |
+= | +0.207 |
DAR | +0.205 |
Neg logit contributions | |
Mug | -0.260 |
iron | -0.249 |
imus | -0.240 |
rone | -0.226 |
throat | -0.222 |
Token | But |
Token ID | 887 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
Mug | +0.175 |
iron | +0.164 |
imus | +0.158 |
rone | +0.148 |
mia | +0.144 |
Neg logit contributions | |
Animation | -0.168 |
lections | -0.165 |
bj | -0.165 |
+= | -0.161 |
DAR | -0.157 |
Token | it |
Token ID | 340 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
Mug | +0.290 |
iron | +0.274 |
imus | +0.263 |
rone | +0.247 |
isol | +0.242 |
Neg logit contributions | |
Animation | -0.299 |
bj | -0.294 |
lections | -0.291 |
+= | -0.288 |
DAR | -0.283 |
Token | was |
Token ID | 373 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
Animation | +0.456 |
bj | +0.441 |
lections | +0.439 |
+= | +0.432 |
DAR | +0.428 |
Neg logit contributions | |
Mug | -0.734 |
iron | -0.708 |
imus | -0.687 |
rone | -0.651 |
isol | -0.644 |
Token | so |
Token ID | 523 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Mug | +0.479 |
iron | +0.453 |
imus | +0.430 |
rone | +0.402 |
isol | +0.398 |
Neg logit contributions | |
Animation | -0.558 |
bj | -0.546 |
lections | -0.541 |
+= | -0.538 |
DAR | -0.529 |
Token | baff |
Token ID | 25989 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
Mug | +1.675 |
iron | +1.606 |
imus | +1.494 |
isol | +1.417 |
rone | +1.396 |
Neg logit contributions | |
Animation | -2.130 |
lections | -2.076 |
bj | -2.074 |
+= | -2.051 |
DAR | -2.013 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Mug | +0.614 |
iron | +0.596 |
imus | +0.564 |
rone | +0.533 |
omy | +0.523 |
Neg logit contributions | |
Animation | -0.605 |
bj | -0.590 |
+= | -0.582 |
lections | -0.579 |
DAR | -0.578 |
Token | to |
Token ID | 284 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Mug | +1.141 |
iron | +1.095 |
imus | +1.050 |
isol | +0.977 |
rone | +0.975 |
Neg logit contributions | |
Animation | -1.084 |
bj | -1.065 |
lections | -1.058 |
+= | -1.049 |
DAR | -1.034 |
Token | recognize |
Token ID | 7564 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Mug | +1.230 |
iron | +1.179 |
imus | +1.115 |
rone | +1.047 |
throat | +1.025 |
Neg logit contributions | |
Animation | -1.507 |
bj | -1.464 |
lections | -1.439 |
+= | -1.414 |
DAR | -1.413 |
Token | that |
Token ID | 326 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
Mug | +1.195 |
iron | +1.129 |
imus | +1.079 |
rone | +1.013 |
mia | +0.997 |
Neg logit contributions | |
Animation | -1.251 |
bj | -1.222 |
+= | -1.208 |
lections | -1.206 |
DAR | -1.183 |
Token | his |
Token ID | 465 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
Animation | +0.295 |
bj | +0.288 |
lections | +0.284 |
+= | +0.284 |
DAR | +0.280 |
Neg logit contributions | |
Mug | -0.319 |
iron | -0.304 |
imus | -0.292 |
rone | -0.275 |
mia | -0.270 |
Token | campaign |
Token ID | 1923 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Mug | +0.397 |
iron | +0.376 |
imus | +0.359 |
rone | +0.336 |
throat | +0.329 |
Neg logit contributions | |
Animation | -0.463 |
bj | -0.454 |
lections | -0.449 |
+= | -0.448 |
DAR | -0.441 |
Token | often |
Token ID | 1690 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
Animation | +1.012 |
bj | +0.993 |
lections | +0.980 |
+= | +0.976 |
DAR | +0.963 |
Neg logit contributions | |
Mug | -1.236 |
iron | -1.183 |
imus | -1.141 |
rone | -1.077 |
mia | -1.059 |
Token | ve |
Token ID | 1569 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Mug | +0.623 |
iron | +0.596 |
imus | +0.575 |
rone | +0.538 |
isol | +0.536 |
Neg logit contributions | |
Animation | -0.544 |
bj | -0.531 |
lections | -0.525 |
+= | -0.520 |
DAR | -0.511 |
Token | ered |
Token ID | 1068 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
Animation | +1.288 |
bj | +1.257 |
lections | +1.240 |
+= | +1.239 |
DAR | +1.225 |
Neg logit contributions | |
Mug | -1.501 |
iron | -1.438 |
imus | -1.387 |
rone | -1.306 |
mia | -1.282 |
Token | off |
Token ID | 572 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Animation | +0.120 |
bj | +0.118 |
lections | +0.117 |
+= | +0.116 |
DAR | +0.115 |
Neg logit contributions | |
Mug | -0.112 |
iron | -0.107 |
imus | -0.102 |
rone | -0.095 |
mia | -0.093 |
Token | - |
Token ID | 12 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Animation | +1.295 |
bj | +1.267 |
lections | +1.251 |
+= | +1.248 |
DAR | +1.235 |
Neg logit contributions | |
Mug | -1.388 |
iron | -1.325 |
imus | -1.277 |
rone | -1.199 |
mia | -1.178 |
Token | road |
Token ID | 6344 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Animation | +1.484 |
bj | +1.453 |
lections | +1.435 |
+= | +1.431 |
DAR | +1.415 |
Neg logit contributions | |
Mug | -1.383 |
iron | -1.307 |
imus | -1.263 |
rone | -1.176 |
mia | -1.157 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Animation | +0.956 |
bj | +0.934 |
lections | +0.922 |
+= | +0.920 |
DAR | +0.909 |
Neg logit contributions | |
Mug | -1.174 |
iron | -1.128 |
imus | -1.087 |
rone | -1.025 |
mia | -1.007 |
Token | | |
Token ID | 930 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Animation | +1.273 |
bj | +1.246 |
lections | +1.230 |
+= | +1.230 |
DAR | +1.216 |
Neg logit contributions | |
Mug | -1.312 |
iron | -1.254 |
imus | -1.206 |
rone | -1.132 |
mia | -1.109 |
Token | aut |
Token ID | 2306 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
Animation | +0.744 |
bj | +0.726 |
lections | +0.716 |
+= | +0.713 |
DAR | +0.704 |
Neg logit contributions | |
Mug | -1.080 |
iron | -1.038 |
imus | -1.004 |
rone | -0.950 |
mia | -0.937 |
Token | oc |
Token ID | 420 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Mug | +0.130 |
iron | +0.125 |
imus | +0.119 |
rone | +0.109 |
omy | +0.108 |
Neg logit contributions | |
Animation | -0.194 |
bj | -0.191 |
DAR | -0.189 |
lections | -0.188 |
+= | -0.187 |
Token | omm |
Token ID | 2002 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Animation | +1.289 |
bj | +1.261 |
lections | +1.248 |
+= | +1.240 |
DAR | +1.239 |
Neg logit contributions | |
Mug | -0.988 |
iron | -0.945 |
imus | -0.903 |
rone | -0.836 |
mia | -0.817 |
Token | and |
Token ID | 392 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Animation | +0.703 |
bj | +0.689 |
lections | +0.681 |
+= | +0.678 |
DAR | +0.673 |
Neg logit contributions | |
Mug | -0.644 |
iron | -0.612 |
imus | -0.588 |
rone | -0.549 |
mia | -0.538 |
Token | | |
Token ID | 91 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
Animation | +0.758 |
bj | +0.747 |
lections | +0.738 |
+= | +0.735 |
DAR | +0.732 |
Neg logit contributions | |
Mug | -0.597 |
iron | -0.567 |
imus | -0.543 |
rone | -0.502 |
mia | -0.492 |
Token | . |
Token ID | 13 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
Animation | +0.254 |
bj | +0.248 |
lections | +0.246 |
+= | +0.244 |
DAR | +0.242 |
Neg logit contributions | |
Mug | -0.329 |
iron | -0.317 |
imus | -0.306 |
rone | -0.288 |
mia | -0.284 |
Token | 3 |
Token ID | 513 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Mug | +3.332 |
iron | +3.038 |
imus | +2.920 |
rone | +2.724 |
throat | +2.708 |
Neg logit contributions | |
lections | -3.461 |
Animation | -3.455 |
bj | -3.432 |
ternity | -3.339 |
+= | -3.293 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
Animation | +1.574 |
bj | +1.534 |
+= | +1.523 |
lections | +1.504 |
DAR | +1.494 |
Neg logit contributions | |
Mug | -1.990 |
iron | -1.914 |
imus | -1.853 |
rone | -1.750 |
mia | -1.718 |
Token | If |
Token ID | 1002 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Animation | +1.673 |
bj | +1.633 |
+= | +1.611 |
lections | +1.610 |
DAR | +1.590 |
Neg logit contributions | |
Mug | -2.086 |
iron | -2.004 |
imus | -1.936 |
rone | -1.827 |
mia | -1.795 |
Token | you |
Token ID | 345 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
Mug | +0.751 |
iron | +0.696 |
imus | +0.670 |
rone | +0.614 |
mia | +0.609 |
Neg logit contributions | |
Animation | -0.958 |
bj | -0.943 |
lections | -0.931 |
+= | -0.920 |
DAR | -0.910 |
Token | C |
Token ID | 34 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
Animation | +0.992 |
bj | +0.971 |
lections | +0.959 |
+= | +0.957 |
DAR | +0.947 |
Neg logit contributions | |
Mug | -1.102 |
iron | -1.054 |
imus | -1.015 |
rone | -0.955 |
mia | -0.938 |
Token | ultural |
Token ID | 8596 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Mug | +0.134 |
iron | +0.130 |
imus | +0.125 |
rone | +0.119 |
mia | +0.117 |
Neg logit contributions | |
Animation | -0.098 |
bj | -0.096 |
+= | -0.094 |
DAR | -0.094 |
lections | -0.094 |
Token | and |
Token ID | 290 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Mug | +2.443 |
iron | +2.236 |
imus | +2.126 |
isol | +2.060 |
rone | +2.030 |
Neg logit contributions | |
bj | -2.333 |
Animation | -2.324 |
+= | -2.245 |
lections | -2.219 |
DAR | -2.209 |
Token | educational |
Token ID | 9856 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Mug | +3.197 |
iron | +2.839 |
imus | +2.723 |
isol | +2.596 |
omy | +2.571 |
Neg logit contributions | |
Animation | -3.744 |
bj | -3.692 |
lections | -3.656 |
+= | -3.583 |
++) | -3.577 |
Token | representations |
Token ID | 24612 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
Mug | +3.217 |
iron | +2.899 |
imus | +2.733 |
isol | +2.722 |
ostr | +2.622 |
Neg logit contributions | |
bj | -3.584 |
Animation | -3.583 |
lections | -3.435 |
+= | -3.429 |
++) | -3.428 |
Token | continue |
Token ID | 2555 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Mug | +0.484 |
iron | +0.459 |
imus | +0.441 |
rone | +0.414 |
isol | +0.412 |
Neg logit contributions | |
Animation | -0.410 |
bj | -0.403 |
lections | -0.394 |
+= | -0.391 |
DAR | -0.387 |
Token | to |
Token ID | 284 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Mug | +0.851 |
iron | +0.816 |
imus | +0.780 |
rone | +0.728 |
mia | +0.727 |
Neg logit contributions | |
Animation | -0.740 |
bj | -0.734 |
+= | -0.715 |
lections | -0.714 |
DAR | -0.712 |
Token | perpetuate |
Token ID | 43874 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Mug | +1.132 |
iron | +1.071 |
imus | +1.027 |
throat | +0.958 |
isol | +0.957 |
Neg logit contributions | |
Animation | -1.258 |
bj | -1.225 |
lections | -1.208 |
+= | -1.185 |
DAR | -1.184 |
Token | negative |
Token ID | 4633 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
Mug | +2.337 |
iron | +2.144 |
imus | +2.008 |
isol | +1.948 |
rone | +1.876 |
Neg logit contributions | |
Animation | -2.957 |
bj | -2.903 |
+= | -2.849 |
lections | -2.819 |
++) | -2.816 |
Token | stereotypes |
Token ID | 22364 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
Mug | +1.810 |
iron | +1.635 |
imus | +1.520 |
isol | +1.436 |
rone | +1.399 |
Neg logit contributions | |
Animation | -3.160 |
bj | -3.135 |
+= | -3.050 |
lections | -3.038 |
++) | -3.021 |
Token |
|
Token ID | 198 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
Mug | +2.851 |
iron | +2.684 |
imus | +2.545 |
isol | +2.428 |
mia | +2.403 |
Neg logit contributions | |
bj | -2.577 |
Animation | -2.575 |
+= | -2.512 |
lections | -2.475 |
DAR | -2.467 |
Token | test |
Token ID | 1332 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Animation | +0.987 |
bj | +0.969 |
+= | +0.959 |
lections | +0.958 |
DAR | +0.952 |
Neg logit contributions | |
Mug | -0.834 |
iron | -0.793 |
imus | -0.760 |
rone | -0.709 |
mia | -0.692 |
Token | methods |
Token ID | 5050 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Mug | +0.968 |
iron | +0.908 |
imus | +0.886 |
rone | +0.823 |
isol | +0.818 |
Neg logit contributions | |
Animation | -0.896 |
bj | -0.873 |
lections | -0.868 |
+= | -0.861 |
++) | -0.831 |
Token | to |
Token ID | 284 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Mug | +1.340 |
iron | +1.261 |
imus | +1.230 |
rone | +1.132 |
isol | +1.128 |
Neg logit contributions | |
Animation | -1.236 |
+= | -1.195 |
lections | -1.195 |
bj | -1.194 |
++) | -1.157 |
Token | measure |
Token ID | 3953 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Mug | +1.848 |
iron | +1.733 |
imus | +1.651 |
isol | +1.533 |
throat | +1.515 |
Neg logit contributions | |
Animation | -2.423 |
bj | -2.364 |
lections | -2.347 |
+= | -2.303 |
CH | -2.266 |
Token | weak |
Token ID | 4939 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
Mug | +0.858 |
iron | +0.813 |
imus | +0.791 |
rone | +0.741 |
throat | +0.731 |
Neg logit contributions | |
Animation | -0.715 |
bj | -0.698 |
lections | -0.689 |
+= | -0.681 |
DAR | -0.664 |
Token | gravitational |
Token ID | 29973 |
Feature activation | +3.38e-03 |
Pos logit contributions | |
Mug | +0.078 |
iron | +0.075 |
imus | +0.072 |
rone | +0.068 |
throat | +0.067 |
Neg logit contributions | |
Animation | -0.064 |
bj | -0.063 |
+= | -0.061 |
lections | -0.061 |
DAR | -0.060 |
Token | lens |
Token ID | 10317 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
Animation | +0.017 |
bj | +0.016 |
+= | +0.016 |
lections | +0.016 |
++) | +0.015 |
Neg logit contributions | |
Mug | -0.026 |
iron | -0.025 |
imus | -0.024 |
throat | -0.023 |
isol | -0.023 |
Token | ing |
Token ID | 278 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Mug | +0.021 |
iron | +0.020 |
imus | +0.020 |
rone | +0.018 |
omy | +0.018 |
Neg logit contributions | |
Animation | -0.018 |
bj | -0.018 |
+= | -0.018 |
lections | -0.017 |
DAR | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Mug | +1.123 |
iron | +1.069 |
imus | +1.043 |
rone | +0.974 |
isol | +0.963 |
Neg logit contributions | |
Animation | -1.033 |
bj | -1.016 |
+= | -0.997 |
lections | -0.993 |
DAR | -0.975 |
Token | another |
Token ID | 1194 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
Mug | +1.304 |
iron | +1.240 |
imus | +1.183 |
isol | +1.116 |
rone | +1.114 |
Neg logit contributions | |
Animation | -1.163 |
bj | -1.131 |
+= | -1.124 |
lections | -1.122 |
++) | -1.087 |
Token | way |
Token ID | 835 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Animation | +1.389 |
bj | +1.362 |
lections | +1.347 |
+= | +1.344 |
DAR | +1.329 |
Neg logit contributions | |
Mug | -1.249 |
iron | -1.187 |
imus | -1.139 |
rone | -1.062 |
mia | -1.040 |
Token | Forum |
Token ID | 14867 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
Animation | +0.136 |
bj | +0.132 |
+= | +0.130 |
lections | +0.129 |
DAR | +0.127 |
Neg logit contributions | |
Mug | -0.244 |
iron | -0.233 |
imus | -0.227 |
rone | -0.215 |
omy | -0.211 |
Token | at |
Token ID | 379 |
Feature activation | -9.45e-03 |
Pos logit contributions | |
Animation | +0.115 |
bj | +0.112 |
lections | +0.110 |
+= | +0.110 |
DAR | +0.109 |
Neg logit contributions | |
Mug | -0.153 |
iron | -0.147 |
imus | -0.142 |
rone | -0.134 |
mia | -0.132 |
Token | Newcastle |
Token ID | 22410 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
Mug | +0.058 |
iron | +0.055 |
imus | +0.053 |
rone | +0.050 |
mia | +0.048 |
Neg logit contributions | |
Animation | -0.062 |
bj | -0.060 |
lections | -0.060 |
+= | -0.060 |
DAR | -0.058 |
Token | United |
Token ID | 1578 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Mug | +0.501 |
iron | +0.478 |
imus | +0.460 |
rone | +0.434 |
mia | +0.425 |
Neg logit contributions | |
Animation | -0.389 |
bj | -0.382 |
+= | -0.374 |
lections | -0.373 |
DAR | -0.368 |
Token | will |
Token ID | 481 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
Animation | +0.591 |
bj | +0.577 |
lections | +0.569 |
+= | +0.567 |
DAR | +0.560 |
Neg logit contributions | |
Mug | -0.778 |
iron | -0.744 |
imus | -0.720 |
rone | -0.680 |
mia | -0.668 |
Token | be |
Token ID | 307 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Mug | +2.070 |
iron | +1.999 |
imus | +1.913 |
rone | +1.787 |
throat | +1.773 |
Neg logit contributions | |
Animation | -2.334 |
bj | -2.231 |
lections | -2.217 |
DAR | -2.182 |
+= | -2.176 |
Token | required |
Token ID | 2672 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Mug | +2.068 |
iron | +1.933 |
imus | +1.865 |
rone | +1.718 |
throat | +1.715 |
Neg logit contributions | |
Animation | -2.423 |
bj | -2.367 |
lections | -2.338 |
+= | -2.325 |
DAR | -2.284 |
Token | to |
Token ID | 284 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
Mug | +0.986 |
iron | +0.945 |
imus | +0.910 |
rone | +0.860 |
mia | +0.840 |
Neg logit contributions | |
Animation | -0.830 |
bj | -0.818 |
+= | -0.802 |
lections | -0.799 |
DAR | -0.795 |
Token | select |
Token ID | 2922 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
Animation | +0.234 |
bj | +0.229 |
lections | +0.227 |
+= | +0.226 |
DAR | +0.223 |
Neg logit contributions | |
Mug | -0.224 |
iron | -0.213 |
imus | -0.205 |
rone | -0.191 |
mia | -0.188 |
Token | an |
Token ID | 281 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Animation | +0.439 |
bj | +0.430 |
lections | +0.424 |
+= | +0.423 |
DAR | +0.417 |
Neg logit contributions | |
Mug | -0.509 |
iron | -0.484 |
imus | -0.467 |
rone | -0.441 |
mia | -0.431 |
Token | individual |
Token ID | 1981 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
Animation | +1.083 |
bj | +1.060 |
lections | +1.049 |
+= | +1.048 |
DAR | +1.039 |
Neg logit contributions | |
Mug | -0.889 |
iron | -0.847 |
imus | -0.809 |
rone | -0.753 |
mia | -0.739 |
Token | ation |
Token ID | 341 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Mug | +1.762 |
iron | +1.697 |
imus | +1.615 |
rone | +1.489 |
omy | +1.479 |
Neg logit contributions | |
Animation | -2.376 |
lections | -2.319 |
bj | -2.317 |
DAR | -2.309 |
+= | -2.298 |
Token | might |
Token ID | 1244 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
Mug | +1.411 |
iron | +1.330 |
imus | +1.258 |
throat | +1.194 |
isol | +1.192 |
Neg logit contributions | |
Animation | -1.611 |
lections | -1.610 |
bj | -1.599 |
+= | -1.549 |
DAR | -1.537 |
Token | have |
Token ID | 423 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Animation | +0.534 |
bj | +0.520 |
lections | +0.515 |
+= | +0.510 |
DAR | +0.506 |
Neg logit contributions | |
Mug | -0.556 |
iron | -0.532 |
imus | -0.511 |
rone | -0.479 |
throat | -0.471 |
Token | been |
Token ID | 587 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Mug | +0.772 |
iron | +0.729 |
imus | +0.698 |
throat | +0.649 |
rone | +0.647 |
Neg logit contributions | |
Animation | -0.823 |
bj | -0.807 |
lections | -0.801 |
+= | -0.789 |
DAR | -0.776 |
Token | a |
Token ID | 257 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
Mug | +1.134 |
iron | +1.085 |
imus | +1.021 |
isol | +0.958 |
rone | +0.948 |
Neg logit contributions | |
Animation | -1.295 |
bj | -1.266 |
+= | -1.262 |
lections | -1.261 |
DAR | -1.232 |
Token | � |
Token ID | 564 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Animation | +0.125 |
bj | +0.122 |
lections | +0.122 |
+= | +0.121 |
DAR | +0.119 |
Neg logit contributions | |
Mug | -0.103 |
iron | -0.096 |
imus | -0.092 |
rone | -0.086 |
throat | -0.085 |
Token | � |
Token ID | 250 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
Mug | +0.772 |
iron | +0.746 |
imus | +0.705 |
rone | +0.652 |
mia | +0.645 |
Neg logit contributions | |
Animation | -0.981 |
bj | -0.961 |
lections | -0.958 |
DAR | -0.946 |
+= | -0.945 |
Token | black |
Token ID | 13424 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Mug | +0.509 |
iron | +0.502 |
imus | +0.475 |
rone | +0.448 |
mia | +0.443 |
Neg logit contributions | |
Animation | -0.446 |
bj | -0.434 |
+= | -0.433 |
lections | -0.433 |
DAR | -0.431 |
Token | ace |
Token ID | 31506 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
Animation | +2.307 |
bj | +2.264 |
lections | +2.238 |
+= | +2.237 |
DAR | +2.214 |
Neg logit contributions | |
Mug | -1.882 |
iron | -1.781 |
imus | -1.711 |
rone | -1.585 |
mia | -1.552 |
Token | � |
Token ID | 447 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
Animation | +0.518 |
bj | +0.506 |
lections | +0.501 |
+= | +0.497 |
DAR | +0.492 |
Neg logit contributions | |
Mug | -0.716 |
iron | -0.692 |
imus | -0.670 |
rone | -0.632 |
mia | -0.624 |
Token | � |
Token ID | 251 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
Mug | +0.469 |
iron | +0.452 |
imus | +0.427 |
rone | +0.397 |
omy | +0.394 |
Neg logit contributions | |
Animation | -0.580 |
bj | -0.567 |
lections | -0.565 |
+= | -0.561 |
DAR | -0.561 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Mug | +0.497 |
iron | +0.481 |
imus | +0.461 |
rone | +0.434 |
mia | +0.426 |
Neg logit contributions | |
Animation | -0.429 |
bj | -0.417 |
lections | -0.416 |
DAR | -0.405 |
+= | -0.402 |
Token | | |
Token ID | 930 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Mug | +0.706 |
iron | +0.661 |
imus | +0.624 |
rone | +0.572 |
mia | +0.562 |
Neg logit contributions | |
Animation | -1.042 |
lections | -1.030 |
bj | -1.028 |
DAR | -0.998 |
ternity | -0.992 |
Token | [ |
Token ID | 685 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Animation | +1.569 |
bj | +1.532 |
+= | +1.526 |
lections | +1.510 |
DAR | +1.504 |
Neg logit contributions | |
Mug | -1.448 |
iron | -1.385 |
imus | -1.326 |
rone | -1.242 |
mia | -1.215 |
Token | address |
Token ID | 21975 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Mug | +0.760 |
iron | +0.736 |
imus | +0.690 |
rone | +0.638 |
mia | +0.630 |
Neg logit contributions | |
Animation | -1.083 |
bj | -1.051 |
lections | -1.047 |
+= | -1.038 |
DAR | -1.036 |
Token | of |
Token ID | 286 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
Mug | +2.215 |
iron | +2.120 |
imus | +2.013 |
rone | +1.888 |
mia | +1.873 |
Neg logit contributions | |
Animation | -2.024 |
lections | -1.977 |
bj | -1.977 |
ternity | -1.938 |
DAR | -1.905 |
Token | " |
Token ID | 366 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
Mug | +2.269 |
iron | +1.960 |
imus | +1.924 |
throat | +1.747 |
isol | +1.684 |
Neg logit contributions | |
Animation | -6.703 |
bj | -6.617 |
lections | -6.558 |
ternity | -6.503 |
龍喚士 | -6.500 |
Token | pp |
Token ID | 381 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Mug | +3.938 |
iron | +3.852 |
imus | +3.705 |
mia | +3.426 |
rone | +3.411 |
Neg logit contributions | |
Animation | -3.854 |
lections | -3.755 |
+= | -3.749 |
bj | -3.699 |
DAR | -3.695 |
Token | pr |
Token ID | 1050 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Animation | +0.672 |
bj | +0.650 |
lections | +0.639 |
+= | +0.637 |
DAR | +0.629 |
Neg logit contributions | |
Mug | -1.293 |
iron | -1.250 |
imus | -1.214 |
rone | -1.157 |
mia | -1.140 |
Token | "] |
Token ID | 8973 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
Animation | +0.582 |
bj | +0.567 |
lections | +0.560 |
+= | +0.557 |
DAR | +0.551 |
Neg logit contributions | |
Mug | -0.803 |
iron | -0.771 |
imus | -0.746 |
rone | -0.706 |
mia | -0.695 |
Token | | |
Token ID | 930 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
Mug | +2.958 |
iron | +2.799 |
imus | +2.694 |
rone | +2.458 |
omy | +2.452 |
Neg logit contributions | |
Animation | -3.616 |
bj | -3.574 |
lections | -3.534 |
DAR | -3.466 |
Women | -3.394 |
Token | + |
Token ID | 1343 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Animation | +0.310 |
bj | +0.302 |
lections | +0.297 |
+= | +0.291 |
DAR | +0.290 |
Neg logit contributions | |
Mug | -0.558 |
iron | -0.538 |
imus | -0.522 |
rone | -0.497 |
mia | -0.489 |
Token | | |
Token ID | 930 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
Mug | +0.955 |
iron | +0.901 |
imus | +0.853 |
rone | +0.783 |
mia | +0.768 |
Neg logit contributions | |
Animation | -1.407 |
bj | -1.381 |
lections | -1.381 |
DAR | -1.350 |
+= | -1.334 |
Token | < |
Token ID | 1279 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
Mug | +0.088 |
iron | +0.085 |
imus | +0.082 |
rone | +0.078 |
mia | +0.077 |
Neg logit contributions | |
Animation | -0.050 |
bj | -0.048 |
lections | -0.047 |
+= | -0.046 |
DAR | -0.046 |
Token | -- |
Token ID | 438 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Mug | +2.046 |
iron | +1.952 |
imus | +1.848 |
rone | +1.687 |
throat | +1.661 |
Neg logit contributions | |
Animation | -2.859 |
bj | -2.797 |
lections | -2.760 |
DAR | -2.736 |
+= | -2.734 |
Token | read |
Token ID | 1100 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
Animation | +1.271 |
bj | +1.240 |
lections | +1.222 |
+= | +1.217 |
DAR | +1.202 |
Neg logit contributions | |
Mug | -1.776 |
iron | -1.704 |
imus | -1.649 |
rone | -1.560 |
mia | -1.535 |
Token | () |
Token ID | 3419 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
Animation | +0.937 |
bj | +0.917 |
lections | +0.905 |
+= | +0.898 |
DAR | +0.889 |
Neg logit contributions | |
Mug | -1.237 |
iron | -1.186 |
imus | -1.147 |
rone | -1.084 |
mia | -1.067 |
Token | ' |
Token ID | 6 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Animation | +0.346 |
bj | +0.340 |
lections | +0.336 |
+= | +0.330 |
DAR | +0.328 |
Neg logit contributions | |
Mug | -0.375 |
iron | -0.356 |
imus | -0.345 |
rone | -0.324 |
throat | -0.320 |
Token | s |
Token ID | 82 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
Mug | +4.204 |
iron | +4.074 |
imus | +3.916 |
mia | +3.697 |
rone | +3.671 |
Neg logit contributions | |
Animation | -3.203 |
lections | -3.078 |
bj | -3.048 |
DAR | -3.035 |
ternity | -3.018 |
Token | frame |
Token ID | 5739 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
Mug | +0.261 |
iron | +0.246 |
imus | +0.237 |
rone | +0.221 |
throat | +0.219 |
Neg logit contributions | |
Animation | -0.319 |
bj | -0.313 |
lections | -0.311 |
+= | -0.303 |
DAR | -0.302 |
Token | + |
Token ID | 1343 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
Mug | +0.496 |
iron | +0.467 |
imus | +0.448 |
rone | +0.414 |
throat | +0.408 |
Neg logit contributions | |
Animation | -0.617 |
bj | -0.610 |
lections | -0.603 |
DAR | -0.590 |
+= | -0.589 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
Mug | +0.440 |
iron | +0.423 |
imus | +0.407 |
rone | +0.382 |
mia | +0.376 |
Neg logit contributions | |
Animation | -0.376 |
bj | -0.365 |
lections | -0.363 |
+= | -0.357 |
DAR | -0.356 |
Token | --+ |
Token ID | 44785 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
Animation | +0.025 |
bj | +0.024 |
lections | +0.024 |
DAR | +0.024 |
+= | +0.024 |
Neg logit contributions | |
Mug | -0.031 |
iron | -0.030 |
imus | -0.028 |
rone | -0.027 |
mia | -0.026 |
Token | / |
Token ID | 14 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
Mug | +2.572 |
iron | +2.452 |
imus | +2.324 |
rone | +2.166 |
mia | +2.142 |
Neg logit contributions | |
Animation | -3.033 |
bj | -2.949 |
lections | -2.931 |
+= | -2.930 |
DAR | -2.892 |
Token | blogs |
Token ID | 49096 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Mug | +3.675 |
iron | +3.612 |
imus | +3.422 |
rone | +3.231 |
mia | +3.227 |
Neg logit contributions | |
Animation | -3.177 |
+= | -3.094 |
DAR | -3.079 |
lections | -3.053 |
bj | -3.052 |
Token | / |
Token ID | 14 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Mug | +1.988 |
iron | +1.919 |
imus | +1.832 |
rone | +1.686 |
mia | +1.660 |
Neg logit contributions | |
Animation | -2.444 |
bj | -2.385 |
+= | -2.359 |
DAR | -2.341 |
lections | -2.333 |
Token | beat |
Token ID | 12945 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
iron | +4.110 |
Mug | +4.061 |
imus | +3.873 |
rone | +3.663 |
mia | +3.658 |
Neg logit contributions | |
Animation | -3.410 |
+= | -3.289 |
DAR | -3.286 |
lections | -3.210 |
bj | -3.198 |
Token | - |
Token ID | 12 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Mug | +3.194 |
iron | +3.144 |
imus | +2.991 |
rone | +2.814 |
mia | +2.792 |
Neg logit contributions | |
Animation | -2.731 |
DAR | -2.631 |
bj | -2.610 |
+= | -2.607 |
lections | -2.602 |
Token | the |
Token ID | 1169 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
Mug | +0.804 |
iron | +0.787 |
imus | +0.751 |
rone | +0.707 |
mia | +0.701 |
Neg logit contributions | |
Animation | -0.702 |
bj | -0.675 |
+= | -0.674 |
DAR | -0.672 |
lections | -0.671 |
Token | - |
Token ID | 12 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Mug | +3.767 |
iron | +3.701 |
imus | +3.535 |
rone | +3.316 |
mia | +3.288 |
Neg logit contributions | |
Animation | -3.711 |
bj | -3.584 |
lections | -3.566 |
+= | -3.555 |
DAR | -3.536 |
Token | press |
Token ID | 8439 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Mug | +2.517 |
iron | +2.507 |
imus | +2.361 |
rone | +2.238 |
mia | +2.207 |
Neg logit contributions | |
Animation | -2.320 |
+= | -2.221 |
DAR | -2.216 |
lections | -2.212 |
bj | -2.198 |
Token | / |
Token ID | 14 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
Mug | +2.459 |
iron | +2.386 |
imus | +2.277 |
rone | +2.132 |
mia | +2.078 |
Neg logit contributions | |
Animation | -2.372 |
bj | -2.319 |
+= | -2.267 |
lections | -2.267 |
DAR | -2.248 |
Token | the |
Token ID | 1169 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Mug | +2.754 |
iron | +2.693 |
imus | +2.547 |
rone | +2.414 |
mia | +2.379 |
Neg logit contributions | |
Animation | -2.424 |
+= | -2.319 |
DAR | -2.318 |
bj | -2.317 |
lections | -2.311 |
Token | - |
Token ID | 12 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
Mug | +1.679 |
iron | +1.639 |
imus | +1.569 |
rone | +1.474 |
mia | +1.456 |
Neg logit contributions | |
Animation | -1.462 |
bj | -1.419 |
+= | -1.398 |
lections | -1.397 |
DAR | -1.394 |
Token | of |
Token ID | 286 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
Animation | +1.546 |
bj | +1.511 |
lections | +1.491 |
+= | +1.487 |
DAR | +1.469 |
Neg logit contributions | |
Mug | -1.912 |
iron | -1.832 |
imus | -1.768 |
rone | -1.667 |
mia | -1.639 |
Token | 1987 |
Token ID | 12923 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Mug | +0.525 |
iron | +0.497 |
imus | +0.475 |
rone | +0.447 |
mia | +0.436 |
Neg logit contributions | |
Animation | -0.500 |
bj | -0.493 |
lections | -0.485 |
+= | -0.479 |
DAR | -0.467 |
Token | , |
Token ID | 11 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
Mug | +2.290 |
iron | +2.202 |
imus | +2.116 |
rone | +1.972 |
isol | +1.954 |
Neg logit contributions | |
Animation | -1.995 |
bj | -1.979 |
+= | -1.954 |
lections | -1.940 |
DAR | -1.869 |
Token | included |
Token ID | 3017 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
Mug | +0.301 |
iron | +0.289 |
imus | +0.278 |
rone | +0.262 |
mia | +0.258 |
Neg logit contributions | |
Animation | -0.235 |
bj | -0.229 |
lections | -0.225 |
+= | -0.225 |
DAR | -0.220 |
Token | Hat |
Token ID | 10983 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Mug | +3.189 |
iron | +2.947 |
imus | +2.846 |
isol | +2.689 |
throat | +2.682 |
Neg logit contributions | |
Animation | -3.175 |
bj | -3.097 |
+= | -3.011 |
lections | -3.004 |
++) | -2.950 |
Token | ay |
Token ID | 323 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
Animation | +0.741 |
bj | +0.722 |
lections | +0.711 |
+= | +0.709 |
DAR | +0.699 |
Neg logit contributions | |
Mug | -1.127 |
iron | -1.084 |
imus | -1.050 |
rone | -0.995 |
mia | -0.980 |
Token | as |
Token ID | 355 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Mug | +3.877 |
iron | +3.694 |
imus | +3.522 |
mia | +3.355 |
rone | +3.337 |
Neg logit contributions | |
Animation | -3.456 |
bj | -3.373 |
lections | -3.366 |
+= | -3.324 |
++) | -3.301 |
Token | part |
Token ID | 636 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
Mug | +2.108 |
iron | +1.970 |
imus | +1.906 |
throat | +1.775 |
rone | +1.760 |
Neg logit contributions | |
Animation | -2.175 |
bj | -2.103 |
lections | -2.093 |
+= | -2.072 |
DAR | -2.014 |
Token | of |
Token ID | 286 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Animation | +0.470 |
bj | +0.458 |
lections | +0.452 |
+= | +0.451 |
DAR | +0.445 |
Neg logit contributions | |
Mug | -0.642 |
iron | -0.616 |
imus | -0.596 |
rone | -0.563 |
mia | -0.554 |
Token | Syria |
Token ID | 4392 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Mug | +1.416 |
iron | +1.326 |
imus | +1.274 |
rone | +1.194 |
throat | +1.183 |
Neg logit contributions | |
Animation | -1.416 |
bj | -1.383 |
+= | -1.357 |
lections | -1.349 |
++) | -1.312 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Mug | +0.763 |
iron | +0.732 |
imus | +0.703 |
rone | +0.664 |
throat | +0.657 |
Neg logit contributions | |
Animation | -0.600 |
bj | -0.594 |
lections | -0.585 |
+= | -0.581 |
DAR | -0.567 |
Token | ar |
Token ID | 283 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Mug | +0.240 |
iron | +0.233 |
imus | +0.222 |
rone | +0.211 |
mia | +0.208 |
Neg logit contributions | |
Animation | -0.175 |
bj | -0.166 |
+= | -0.165 |
lections | -0.165 |
DAR | -0.164 |
Token | con |
Token ID | 1102 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Mug | +1.761 |
iron | +1.723 |
imus | +1.641 |
rone | +1.579 |
mia | +1.564 |
Neg logit contributions | |
Animation | -1.523 |
lections | -1.490 |
+= | -1.471 |
DAR | -1.448 |
bj | -1.440 |
Token | Ortiz |
Token ID | 39039 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Mug | +4.042 |
iron | +3.793 |
imus | +3.653 |
rone | +3.344 |
omy | +3.231 |
Neg logit contributions | |
Animation | -4.353 |
+= | -4.232 |
++) | -4.184 |
lections | -4.168 |
bj | -4.158 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Mug | +3.454 |
iron | +3.203 |
imus | +3.103 |
rone | +2.854 |
throat | +2.775 |
Neg logit contributions | |
Animation | -3.564 |
bj | -3.449 |
lections | -3.434 |
+= | -3.393 |
++) | -3.389 |
Token | arrival |
Token ID | 10325 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
Mug | +0.612 |
iron | +0.568 |
imus | +0.548 |
rone | +0.508 |
throat | +0.501 |
Neg logit contributions | |
Animation | -0.666 |
bj | -0.653 |
lections | -0.644 |
+= | -0.643 |
DAR | -0.633 |
Token | at |
Token ID | 379 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Mug | +4.062 |
iron | +3.827 |
imus | +3.608 |
throat | +3.358 |
rone | +3.338 |
Neg logit contributions | |
Animation | -4.020 |
bj | -3.954 |
lections | -3.906 |
++) | -3.879 |
+= | -3.859 |
Token | the |
Token ID | 262 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Mug | +3.715 |
iron | +3.269 |
imus | +3.114 |
Lime | +2.974 |
rone | +2.921 |
Neg logit contributions | |
Animation | -4.032 |
bj | -3.989 |
+= | -3.908 |
lections | -3.848 |
++) | -3.782 |
Token | Jose |
Token ID | 5264 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
Mug | +2.722 |
iron | +2.453 |
imus | +2.389 |
throat | +2.245 |
rone | +2.228 |
Neg logit contributions | |
Animation | -2.530 |
bj | -2.499 |
lections | -2.479 |
+= | -2.445 |
ternity | -2.374 |
Token | Mart |
Token ID | 3981 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Mug | +0.317 |
iron | +0.299 |
imus | +0.287 |
rone | +0.268 |
mia | +0.264 |
Neg logit contributions | |
Animation | -0.326 |
bj | -0.317 |
lections | -0.314 |
+= | -0.314 |
DAR | -0.308 |
Token | i |
Token ID | 72 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
Animation | +0.713 |
bj | +0.696 |
lections | +0.686 |
+= | +0.685 |
DAR | +0.676 |
Neg logit contributions | |
Mug | -0.935 |
iron | -0.897 |
imus | -0.867 |
rone | -0.818 |
mia | -0.803 |
Token | International |
Token ID | 4037 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
Animation | +0.164 |
bj | +0.161 |
lections | +0.160 |
+= | +0.159 |
DAR | +0.156 |
Neg logit contributions | |
Mug | -0.169 |
iron | -0.160 |
imus | -0.154 |
rone | -0.144 |
mia | -0.141 |