Token | Irvine |
Token ID | 37277 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
ipal | +0.229 |
init | +0.226 |
shift | +0.216 |
actory | +0.216 |
ounge | +0.211 |
Neg logit contributions | |
Dent | -0.151 |
Nadu | -0.143 |
Devi | -0.139 |
Equity | -0.126 |
Benefit | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ipal | +0.492 |
init | +0.482 |
shift | +0.453 |
actory | +0.452 |
ounge | +0.439 |
Neg logit contributions | |
Dent | -0.575 |
Nadu | -0.553 |
Devi | -0.541 |
Equity | -0.505 |
iaz | -0.503 |
Token | California |
Token ID | 3442 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
Dent | +0.085 |
Nadu | +0.080 |
Devi | +0.078 |
Equity | +0.072 |
Benefit | +0.071 |
Neg logit contributions | |
ipal | -0.124 |
init | -0.122 |
shift | -0.117 |
actory | -0.117 |
ounge | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
Dent | +0.548 |
Nadu | +0.520 |
Devi | +0.511 |
Benefit | +0.476 |
Equity | +0.475 |
Neg logit contributions | |
ipal | -0.530 |
init | -0.523 |
shift | -0.502 |
actory | -0.500 |
ounge | -0.486 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ipal | +0.331 |
init | +0.328 |
shift | +0.309 |
actory | +0.307 |
ounge | +0.297 |
Neg logit contributions | |
Dent | -0.342 |
Nadu | -0.332 |
Devi | -0.321 |
iaz | -0.302 |
Equity | -0.299 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
ipal | +0.563 |
init | +0.560 |
shift | +0.498 |
actory | +0.472 |
photo | +0.460 |
Neg logit contributions | |
Dent | -1.670 |
Nadu | -1.636 |
Devi | -1.612 |
iaz | -1.543 |
merce | -1.539 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
init | +2.171 |
ipal | +2.093 |
shift | +1.856 |
actory | +1.778 |
photo | +1.752 |
Neg logit contributions | |
Dent | -6.045 |
Nadu | -5.967 |
Devi | -5.770 |
iaz | -5.752 |
merce | -5.713 |
Token | of |
Token ID | 286 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
init | +0.853 |
ipal | +0.834 |
shift | +0.795 |
actory | +0.770 |
photo | +0.750 |
Neg logit contributions | |
Dent | -1.315 |
Nadu | -1.287 |
Devi | -1.252 |
merce | -1.184 |
Equity | -1.170 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
init | +0.101 |
ipal | +0.098 |
shift | +0.091 |
actory | +0.090 |
photo | +0.084 |
Neg logit contributions | |
Dent | -0.215 |
Nadu | -0.211 |
Devi | -0.208 |
iaz | -0.199 |
ouri | -0.195 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
init | +0.478 |
ipal | +0.469 |
shift | +0.428 |
actory | +0.424 |
photo | +0.420 |
Neg logit contributions | |
Dent | -1.009 |
Nadu | -0.995 |
Devi | -0.969 |
merce | -0.935 |
iaz | -0.930 |
Token | : |
Token ID | 25 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
init | +1.717 |
ipal | +1.574 |
shift | +1.550 |
actory | +1.420 |
photo | +1.419 |
Neg logit contributions | |
Dent | -4.730 |
Nadu | -4.695 |
eleph | -4.650 |
Devi | -4.605 |
merce | -4.582 |
Token | Women |
Token ID | 6926 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
ipal | +0.476 |
init | +0.469 |
shift | +0.451 |
actory | +0.450 |
ounge | +0.441 |
Neg logit contributions | |
Dent | -0.180 |
Nadu | -0.173 |
Devi | -0.159 |
iaz | -0.140 |
Equity | -0.137 |
Token | in |
Token ID | 287 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
Dent | +0.375 |
Nadu | +0.362 |
Devi | +0.353 |
iaz | +0.329 |
Equity | +0.327 |
Neg logit contributions | |
ipal | -0.329 |
init | -0.324 |
shift | -0.306 |
actory | -0.304 |
ounge | -0.293 |
Token | politics |
Token ID | 4819 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
Dent | +0.005 |
Nadu | +0.005 |
Devi | +0.004 |
iaz | +0.004 |
Benefit | +0.004 |
Neg logit contributions | |
ipal | -0.005 |
init | -0.005 |
shift | -0.005 |
actory | -0.005 |
ounge | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
ipal | +0.600 |
init | +0.596 |
shift | +0.560 |
actory | +0.552 |
ounge | +0.533 |
Neg logit contributions | |
Dent | -0.741 |
Nadu | -0.719 |
Devi | -0.704 |
iaz | -0.656 |
Equity | -0.653 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ipal | +0.307 |
init | +0.305 |
shift | +0.287 |
actory | +0.284 |
ounge | +0.275 |
Neg logit contributions | |
Dent | -0.337 |
Nadu | -0.329 |
Devi | -0.318 |
iaz | -0.299 |
Equity | -0.295 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
ipal | +0.651 |
init | +0.646 |
shift | +0.576 |
actory | +0.551 |
photo | +0.535 |
Neg logit contributions | |
Dent | -1.962 |
Nadu | -1.919 |
Devi | -1.894 |
iaz | -1.806 |
merce | -1.795 |
Token | 7 |
Token ID | 767 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
ipal | +1.852 |
init | +1.837 |
actory | +1.638 |
shift | +1.622 |
photo | +1.554 |
Neg logit contributions | |
Dent | -6.403 |
Nadu | -6.384 |
Devi | -6.103 |
merce | -5.946 |
ouri | -5.913 |
Token | of |
Token ID | 286 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
init | +0.388 |
ipal | +0.384 |
shift | +0.363 |
actory | +0.352 |
photo | +0.343 |
Neg logit contributions | |
Dent | -0.581 |
Nadu | -0.570 |
Devi | -0.554 |
Equity | -0.517 |
merce | -0.514 |
Token | 15 |
Token ID | 1315 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
init | +0.044 |
ipal | +0.043 |
shift | +0.040 |
actory | +0.039 |
photo | +0.036 |
Neg logit contributions | |
Dent | -0.093 |
Nadu | -0.092 |
Devi | -0.090 |
iaz | -0.086 |
ouri | -0.085 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
init | +0.453 |
ipal | +0.445 |
shift | +0.405 |
actory | +0.403 |
photo | +0.397 |
Neg logit contributions | |
Dent | -0.954 |
Nadu | -0.939 |
Devi | -0.915 |
merce | -0.878 |
iaz | -0.876 |
Token | : |
Token ID | 25 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
init | +1.769 |
ipal | +1.625 |
shift | +1.603 |
photo | +1.472 |
actory | +1.462 |
Neg logit contributions | |
Dent | -4.887 |
Nadu | -4.852 |
eleph | -4.790 |
Devi | -4.756 |
merce | -4.730 |
Token | Irvine |
Token ID | 37277 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
ipal | +0.094 |
init | +0.093 |
shift | +0.089 |
actory | +0.089 |
ounge | +0.086 |
Neg logit contributions | |
Dent | -0.069 |
Nadu | -0.066 |
Devi | -0.064 |
iaz | -0.058 |
Equity | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
ipal | +0.384 |
init | +0.377 |
shift | +0.358 |
actory | +0.357 |
ounge | +0.346 |
Neg logit contributions | |
Dent | -0.421 |
Nadu | -0.403 |
Devi | -0.394 |
Equity | -0.368 |
Benefit | -0.367 |
Token | California |
Token ID | 3442 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
Dent | +0.048 |
Nadu | +0.045 |
Devi | +0.044 |
iaz | +0.041 |
Equity | +0.040 |
Neg logit contributions | |
ipal | -0.060 |
init | -0.060 |
shift | -0.057 |
actory | -0.056 |
itual | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
Dent | +0.584 |
Nadu | +0.554 |
Devi | +0.543 |
Equity | +0.507 |
Benefit | +0.507 |
Neg logit contributions | |
ipal | -0.573 |
init | -0.565 |
shift | -0.544 |
actory | -0.541 |
ounge | -0.525 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ipal | +0.278 |
init | +0.276 |
shift | +0.261 |
actory | +0.259 |
ounge | +0.250 |
Neg logit contributions | |
Dent | -0.290 |
Nadu | -0.281 |
Devi | -0.273 |
iaz | -0.255 |
Equity | -0.252 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
ipal | +0.561 |
init | +0.559 |
shift | +0.496 |
actory | +0.473 |
photo | +0.460 |
Neg logit contributions | |
Dent | -1.680 |
Nadu | -1.644 |
Devi | -1.623 |
iaz | -1.548 |
merce | -1.544 |
Token | 9 |
Token ID | 860 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
ipal | +1.443 |
init | +1.391 |
shift | +1.210 |
actory | +1.183 |
photo | +1.047 |
Neg logit contributions | |
Dent | -6.754 |
Nadu | -6.740 |
Devi | -6.514 |
merce | -6.317 |
iaz | -6.282 |
Token | of |
Token ID | 286 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
init | +0.278 |
ipal | +0.272 |
shift | +0.258 |
actory | +0.251 |
photo | +0.242 |
Neg logit contributions | |
Dent | -0.414 |
Nadu | -0.406 |
Devi | -0.394 |
merce | -0.369 |
Equity | -0.368 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
init | +0.108 |
ipal | +0.104 |
shift | +0.097 |
actory | +0.096 |
photo | +0.089 |
Neg logit contributions | |
Dent | -0.229 |
Nadu | -0.224 |
Devi | -0.221 |
iaz | -0.211 |
ouri | -0.208 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
init | +0.513 |
ipal | +0.503 |
shift | +0.459 |
actory | +0.456 |
photo | +0.451 |
Neg logit contributions | |
Dent | -1.085 |
Nadu | -1.069 |
Devi | -1.041 |
merce | -1.004 |
iaz | -0.999 |
Token | : |
Token ID | 25 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
init | +1.736 |
ipal | +1.591 |
shift | +1.568 |
photo | +1.440 |
actory | +1.433 |
Neg logit contributions | |
Dent | -4.785 |
Nadu | -4.750 |
eleph | -4.700 |
Devi | -4.658 |
merce | -4.631 |
Token | Hills |
Token ID | 14379 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
Dent | +1.449 |
Nadu | +1.378 |
Devi | +1.347 |
Equity | +1.259 |
Benefit | +1.254 |
Neg logit contributions | |
ipal | -1.383 |
init | -1.357 |
shift | -1.292 |
actory | -1.290 |
ounge | -1.251 |
Token | , |
Token ID | 11 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ipal | +0.618 |
init | +0.607 |
shift | +0.574 |
actory | +0.572 |
ounge | +0.555 |
Neg logit contributions | |
Dent | -0.694 |
Nadu | -0.666 |
Devi | -0.651 |
Equity | -0.608 |
Benefit | -0.606 |
Token | California |
Token ID | 3442 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Dent | +0.248 |
Nadu | +0.235 |
Devi | +0.229 |
Equity | +0.209 |
Benefit | +0.208 |
Neg logit contributions | |
ipal | -0.343 |
init | -0.338 |
shift | -0.323 |
actory | -0.322 |
ounge | -0.314 |
Token | . |
Token ID | 13 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
Dent | +0.829 |
Nadu | +0.792 |
Devi | +0.769 |
Benefit | +0.721 |
Equity | +0.720 |
Neg logit contributions | |
ipal | -0.829 |
init | -0.818 |
shift | -0.786 |
actory | -0.785 |
itual | -0.761 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ipal | +0.276 |
init | +0.273 |
shift | +0.257 |
actory | +0.255 |
ounge | +0.246 |
Neg logit contributions | |
Dent | -0.313 |
Nadu | -0.303 |
Devi | -0.295 |
iaz | -0.276 |
Equity | -0.274 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
ipal | +0.514 |
init | +0.513 |
shift | +0.451 |
actory | +0.431 |
photo | +0.421 |
Neg logit contributions | |
Dent | -1.534 |
Nadu | -1.507 |
Devi | -1.483 |
iaz | -1.422 |
merce | -1.417 |
Token | 14 |
Token ID | 1478 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
init | +1.678 |
ipal | +1.547 |
shift | +1.507 |
actory | +1.328 |
photo | +1.321 |
Neg logit contributions | |
Dent | -6.413 |
Nadu | -6.263 |
Devi | -6.183 |
merce | -6.063 |
iaz | -5.983 |
Token | of |
Token ID | 286 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
init | +0.660 |
ipal | +0.644 |
shift | +0.614 |
actory | +0.594 |
photo | +0.578 |
Neg logit contributions | |
Dent | -1.004 |
Nadu | -0.986 |
Devi | -0.957 |
merce | -0.902 |
Equity | -0.895 |
Token | 15 |
Token ID | 1315 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
init | +0.052 |
ipal | +0.050 |
shift | +0.047 |
actory | +0.046 |
photo | +0.043 |
Neg logit contributions | |
Dent | -0.110 |
Nadu | -0.108 |
Devi | -0.106 |
iaz | -0.102 |
ouri | -0.100 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
init | +0.367 |
ipal | +0.361 |
shift | +0.328 |
actory | +0.326 |
photo | +0.325 |
Neg logit contributions | |
Dent | -0.776 |
Nadu | -0.765 |
Devi | -0.744 |
merce | -0.718 |
iaz | -0.715 |
Token | : |
Token ID | 25 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
init | +1.673 |
ipal | +1.539 |
shift | +1.511 |
photo | +1.386 |
actory | +1.384 |
Neg logit contributions | |
Dent | -4.575 |
Nadu | -4.552 |
eleph | -4.501 |
Devi | -4.457 |
merce | -4.442 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Dent | +1.137 |
Nadu | +1.083 |
Devi | +1.062 |
Equity | +0.990 |
Benefit | +0.989 |
Neg logit contributions | |
ipal | -1.083 |
init | -1.064 |
shift | -1.014 |
actory | -1.012 |
itual | -0.980 |
Token | New |
Token ID | 968 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Dent | +0.103 |
Nadu | +0.099 |
Devi | +0.095 |
iaz | +0.088 |
Equity | +0.087 |
Neg logit contributions | |
init | -0.145 |
ipal | -0.145 |
shift | -0.137 |
actory | -0.136 |
ounge | -0.133 |
Token | Hampshire |
Token ID | 13910 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Dent | +0.199 |
Nadu | +0.191 |
Devi | +0.184 |
Equity | +0.168 |
iaz | +0.168 |
Neg logit contributions | |
init | -0.252 |
ipal | -0.252 |
shift | -0.239 |
actory | -0.238 |
ounge | -0.228 |
Token | . |
Token ID | 13 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
Dent | +0.233 |
Nadu | +0.221 |
Devi | +0.217 |
Benefit | +0.203 |
Equity | +0.203 |
Neg logit contributions | |
ipal | -0.224 |
init | -0.219 |
shift | -0.211 |
actory | -0.209 |
ounge | -0.204 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ipal | +0.494 |
init | +0.490 |
shift | +0.461 |
actory | +0.455 |
ounge | +0.439 |
Neg logit contributions | |
Dent | -0.562 |
Nadu | -0.546 |
Devi | -0.531 |
iaz | -0.499 |
Equity | -0.494 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
ipal | +0.660 |
init | +0.658 |
shift | +0.582 |
actory | +0.556 |
photo | +0.544 |
Neg logit contributions | |
Dent | -2.001 |
Nadu | -1.950 |
Devi | -1.932 |
iaz | -1.840 |
merce | -1.835 |
Token | 6 |
Token ID | 718 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
init | +2.460 |
ipal | +2.411 |
shift | +2.215 |
actory | +2.116 |
photo | +2.103 |
Neg logit contributions | |
Dent | -5.594 |
Nadu | -5.459 |
Devi | -5.286 |
merce | -5.134 |
iaz | -5.095 |
Token | of |
Token ID | 286 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
init | +0.361 |
ipal | +0.355 |
shift | +0.337 |
actory | +0.327 |
photo | +0.318 |
Neg logit contributions | |
Dent | -0.542 |
Nadu | -0.531 |
Devi | -0.517 |
Equity | -0.482 |
merce | -0.481 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
init | +0.104 |
ipal | +0.101 |
shift | +0.094 |
actory | +0.093 |
photo | +0.087 |
Neg logit contributions | |
Dent | -0.221 |
Nadu | -0.217 |
Devi | -0.214 |
iaz | -0.204 |
ouri | -0.201 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
init | +0.495 |
ipal | +0.488 |
shift | +0.442 |
actory | +0.441 |
photo | +0.433 |
Neg logit contributions | |
Dent | -1.041 |
Nadu | -1.023 |
Devi | -0.997 |
iaz | -0.953 |
merce | -0.952 |
Token | : |
Token ID | 25 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
init | +1.740 |
ipal | +1.596 |
shift | +1.573 |
photo | +1.444 |
actory | +1.442 |
Neg logit contributions | |
Dent | -4.795 |
Nadu | -4.755 |
eleph | -4.691 |
Devi | -4.663 |
merce | -4.635 |
Token | in |
Token ID | 259 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ipal | +1.392 |
init | +1.388 |
shift | +1.285 |
actory | +1.273 |
ounge | +1.258 |
Neg logit contributions | |
Dent | -1.594 |
Nadu | -1.518 |
Devi | -1.498 |
Benefit | -1.391 |
Equity | -1.391 |
Token | , |
Token ID | 11 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Dent | +0.445 |
Nadu | +0.426 |
Devi | +0.416 |
Equity | +0.388 |
Benefit | +0.388 |
Neg logit contributions | |
ipal | -0.411 |
init | -0.404 |
shift | -0.383 |
actory | -0.383 |
ounge | -0.371 |
Token | Iowa |
Token ID | 9406 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
Dent | +0.157 |
Nadu | +0.148 |
Devi | +0.144 |
Equity | +0.132 |
Benefit | +0.132 |
Neg logit contributions | |
ipal | -0.216 |
init | -0.213 |
shift | -0.203 |
actory | -0.203 |
ounge | -0.197 |
Token | . |
Token ID | 13 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
ipal | +0.375 |
init | +0.369 |
shift | +0.350 |
actory | +0.350 |
ounge | +0.339 |
Neg logit contributions | |
Dent | -0.414 |
Nadu | -0.395 |
Devi | -0.387 |
Equity | -0.362 |
Benefit | -0.361 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ipal | +0.379 |
init | +0.375 |
shift | +0.353 |
actory | +0.350 |
ounge | +0.338 |
Neg logit contributions | |
Dent | -0.429 |
Nadu | -0.416 |
Devi | -0.404 |
iaz | -0.379 |
Equity | -0.377 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
ipal | +0.616 |
init | +0.612 |
shift | +0.537 |
actory | +0.516 |
photo | +0.510 |
Neg logit contributions | |
Dent | -1.831 |
Nadu | -1.781 |
Devi | -1.764 |
iaz | -1.677 |
merce | -1.671 |
Token | 5 |
Token ID | 642 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
ipal | +2.765 |
init | +2.733 |
actory | +2.534 |
shift | +2.522 |
photo | +2.479 |
Neg logit contributions | |
Nadu | -5.224 |
Dent | -5.163 |
Devi | -4.950 |
merce | -4.854 |
ouri | -4.780 |
Token | of |
Token ID | 286 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
init | +0.423 |
ipal | +0.416 |
shift | +0.394 |
actory | +0.385 |
photo | +0.374 |
Neg logit contributions | |
Dent | -0.627 |
Nadu | -0.615 |
Devi | -0.598 |
Equity | -0.557 |
merce | -0.556 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
init | +0.090 |
ipal | +0.089 |
shift | +0.082 |
actory | +0.081 |
ounge | +0.076 |
Neg logit contributions | |
Dent | -0.191 |
Nadu | -0.187 |
Devi | -0.184 |
iaz | -0.175 |
ouri | -0.173 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
init | +0.510 |
ipal | +0.504 |
actory | +0.454 |
shift | +0.453 |
photo | +0.447 |
Neg logit contributions | |
Dent | -1.070 |
Nadu | -1.050 |
Devi | -1.025 |
iaz | -0.980 |
merce | -0.973 |
Token | : |
Token ID | 25 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
init | +1.763 |
ipal | +1.636 |
shift | +1.611 |
photo | +1.513 |
actory | +1.481 |
Neg logit contributions | |
Dent | -4.813 |
Nadu | -4.763 |
Devi | -4.673 |
eleph | -4.650 |
merce | -4.635 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
ipal | +0.070 |
init | +0.069 |
shift | +0.066 |
actory | +0.066 |
ounge | +0.064 |
Neg logit contributions | |
Dent | -0.068 |
Nadu | -0.066 |
Devi | -0.064 |
iaz | -0.059 |
Equity | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ipal | +0.038 |
init | +0.037 |
actory | +0.036 |
shift | +0.035 |
itual | +0.034 |
Neg logit contributions | |
Dent | -0.038 |
Nadu | -0.036 |
Devi | -0.035 |
Benefit | -0.033 |
Equity | -0.033 |
Token | California |
Token ID | 3442 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Dent | +0.114 |
Nadu | +0.106 |
Devi | +0.103 |
Equity | +0.095 |
Benefit | +0.094 |
Neg logit contributions | |
ipal | -0.175 |
init | -0.174 |
actory | -0.166 |
shift | -0.166 |
ounge | -0.163 |
Token | . |
Token ID | 13 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Dent | +0.905 |
Nadu | +0.858 |
Devi | +0.842 |
Benefit | +0.791 |
Equity | +0.788 |
Neg logit contributions | |
ipal | -0.893 |
init | -0.884 |
actory | -0.846 |
shift | -0.845 |
ounge | -0.820 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ipal | +0.288 |
init | +0.285 |
shift | +0.268 |
actory | +0.266 |
ounge | +0.257 |
Neg logit contributions | |
Dent | -0.328 |
Nadu | -0.318 |
Devi | -0.309 |
iaz | -0.289 |
Equity | -0.288 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
ipal | +0.469 |
init | +0.466 |
shift | +0.413 |
actory | +0.393 |
photo | +0.382 |
Neg logit contributions | |
Dent | -1.392 |
Nadu | -1.364 |
Devi | -1.346 |
iaz | -1.288 |
merce | -1.282 |
Token | 12 |
Token ID | 1105 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
init | +2.108 |
ipal | +1.942 |
shift | +1.828 |
actory | +1.741 |
photo | +1.712 |
Neg logit contributions | |
Dent | -5.871 |
Nadu | -5.812 |
merce | -5.741 |
Devi | -5.640 |
iaz | -5.518 |
Token | of |
Token ID | 286 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
init | +0.623 |
ipal | +0.610 |
shift | +0.583 |
actory | +0.564 |
photo | +0.546 |
Neg logit contributions | |
Dent | -0.947 |
Nadu | -0.927 |
Devi | -0.903 |
merce | -0.847 |
Equity | -0.843 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
init | +0.125 |
ipal | +0.121 |
shift | +0.113 |
actory | +0.112 |
photo | +0.104 |
Neg logit contributions | |
Dent | -0.268 |
Nadu | -0.261 |
Devi | -0.258 |
iaz | -0.247 |
ouri | -0.243 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
init | +0.394 |
ipal | +0.387 |
shift | +0.352 |
actory | +0.351 |
photo | +0.347 |
Neg logit contributions | |
Dent | -0.825 |
Nadu | -0.812 |
Devi | -0.792 |
merce | -0.760 |
iaz | -0.759 |
Token | : |
Token ID | 25 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
init | +1.660 |
ipal | +1.527 |
shift | +1.500 |
actory | +1.376 |
photo | +1.371 |
Neg logit contributions | |
Dent | -4.528 |
Nadu | -4.499 |
eleph | -4.441 |
Devi | -4.409 |
merce | -4.382 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ipal | +0.105 |
init | +0.104 |
shift | +0.099 |
actory | +0.099 |
ounge | +0.096 |
Neg logit contributions | |
Dent | -0.092 |
Nadu | -0.088 |
Devi | -0.086 |
iaz | -0.079 |
Equity | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Dent | +0.103 |
Nadu | +0.098 |
Devi | +0.096 |
Equity | +0.090 |
Benefit | +0.090 |
Neg logit contributions | |
ipal | -0.101 |
init | -0.101 |
actory | -0.096 |
shift | -0.095 |
ounge | -0.092 |
Token | California |
Token ID | 3442 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Dent | +0.263 |
Nadu | +0.248 |
Devi | +0.240 |
Equity | +0.220 |
Benefit | +0.219 |
Neg logit contributions | |
ipal | -0.384 |
init | -0.379 |
shift | -0.363 |
actory | -0.362 |
ounge | -0.354 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Dent | +0.951 |
Nadu | +0.902 |
Devi | +0.879 |
Benefit | +0.826 |
Equity | +0.823 |
Neg logit contributions | |
ipal | -0.942 |
init | -0.931 |
shift | -0.895 |
actory | -0.892 |
itual | -0.867 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ipal | +0.203 |
init | +0.200 |
shift | +0.189 |
actory | +0.187 |
ounge | +0.181 |
Neg logit contributions | |
Dent | -0.221 |
Nadu | -0.213 |
Devi | -0.207 |
iaz | -0.194 |
Equity | -0.193 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
ipal | +0.460 |
init | +0.456 |
shift | +0.405 |
actory | +0.386 |
photo | +0.373 |
Neg logit contributions | |
Dent | -1.356 |
Nadu | -1.327 |
Devi | -1.309 |
iaz | -1.250 |
merce | -1.244 |
Token | 11 |
Token ID | 1367 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
init | +2.069 |
ipal | +1.918 |
shift | +1.821 |
actory | +1.756 |
photo | +1.670 |
Neg logit contributions | |
Nadu | -5.817 |
Dent | -5.805 |
Devi | -5.717 |
merce | -5.601 |
iaz | -5.516 |
Token | of |
Token ID | 286 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
init | +0.639 |
ipal | +0.625 |
shift | +0.597 |
actory | +0.579 |
photo | +0.560 |
Neg logit contributions | |
Dent | -0.973 |
Nadu | -0.956 |
Devi | -0.929 |
merce | -0.871 |
Equity | -0.866 |
Token | 15 |
Token ID | 1315 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
init | +0.064 |
ipal | +0.062 |
shift | +0.058 |
actory | +0.057 |
photo | +0.053 |
Neg logit contributions | |
Dent | -0.136 |
Nadu | -0.133 |
Devi | -0.131 |
iaz | -0.126 |
ouri | -0.124 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
init | +0.332 |
ipal | +0.327 |
shift | +0.298 |
actory | +0.297 |
photo | +0.292 |
Neg logit contributions | |
Dent | -0.694 |
Nadu | -0.682 |
Devi | -0.666 |
merce | -0.638 |
iaz | -0.637 |
Token | : |
Token ID | 25 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
init | +1.638 |
ipal | +1.510 |
shift | +1.483 |
actory | +1.361 |
photo | +1.358 |
Neg logit contributions | |
Dent | -4.448 |
Nadu | -4.417 |
eleph | -4.338 |
Devi | -4.330 |
merce | -4.293 |
Token | aga |
Token ID | 8126 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
ipal | +0.584 |
init | +0.572 |
shift | +0.535 |
actory | +0.533 |
ounge | +0.514 |
Neg logit contributions | |
Dent | -0.849 |
Nadu | -0.818 |
Devi | -0.803 |
Equity | -0.755 |
Benefit | -0.754 |
Token | , |
Token ID | 11 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
Dent | +0.673 |
Nadu | +0.643 |
Devi | +0.629 |
Equity | +0.586 |
Benefit | +0.584 |
Neg logit contributions | |
ipal | -0.636 |
init | -0.625 |
shift | -0.593 |
actory | -0.591 |
ounge | -0.573 |
Token | California |
Token ID | 3442 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Dent | +0.302 |
Nadu | +0.286 |
Devi | +0.280 |
iaz | +0.256 |
Equity | +0.256 |
Neg logit contributions | |
ipal | -0.414 |
init | -0.409 |
shift | -0.391 |
actory | -0.389 |
ounge | -0.378 |
Token | . |
Token ID | 13 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Dent | +1.006 |
Nadu | +0.959 |
Devi | +0.934 |
Benefit | +0.876 |
Equity | +0.874 |
Neg logit contributions | |
ipal | -1.002 |
init | -0.992 |
shift | -0.955 |
actory | -0.953 |
ounge | -0.927 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ipal | +0.241 |
init | +0.238 |
shift | +0.225 |
actory | +0.222 |
ounge | +0.216 |
Neg logit contributions | |
Dent | -0.276 |
Nadu | -0.266 |
Devi | -0.259 |
iaz | -0.243 |
Equity | -0.241 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
ipal | +0.490 |
init | +0.487 |
shift | +0.429 |
actory | +0.411 |
photo | +0.398 |
Neg logit contributions | |
Dent | -1.438 |
Nadu | -1.409 |
Devi | -1.390 |
iaz | -1.327 |
merce | -1.323 |
Token | 13 |
Token ID | 1511 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
init | +1.752 |
ipal | +1.730 |
shift | +1.641 |
actory | +1.597 |
photo | +1.470 |
Neg logit contributions | |
Nadu | -6.035 |
Dent | -5.973 |
Devi | -5.781 |
merce | -5.651 |
iaz | -5.561 |
Token | of |
Token ID | 286 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
init | +0.748 |
ipal | +0.730 |
shift | +0.696 |
actory | +0.678 |
photo | +0.656 |
Neg logit contributions | |
Dent | -1.144 |
Nadu | -1.122 |
Devi | -1.093 |
merce | -1.030 |
Equity | -1.021 |
Token | 15 |
Token ID | 1315 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
init | +0.020 |
ipal | +0.019 |
shift | +0.018 |
actory | +0.018 |
photo | +0.017 |
Neg logit contributions | |
Dent | -0.043 |
Nadu | -0.042 |
Devi | -0.041 |
iaz | -0.039 |
ouri | -0.039 |
Token | Photos |
Token ID | 9434 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
init | +0.374 |
ipal | +0.368 |
shift | +0.335 |
actory | +0.332 |
photo | +0.330 |
Neg logit contributions | |
Dent | -0.786 |
Nadu | -0.775 |
Devi | -0.754 |
merce | -0.727 |
iaz | -0.724 |
Token | : |
Token ID | 25 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
init | +1.652 |
ipal | +1.522 |
shift | +1.492 |
actory | +1.369 |
photo | +1.368 |
Neg logit contributions | |
Dent | -4.501 |
Nadu | -4.473 |
eleph | -4.414 |
Devi | -4.385 |
merce | -4.361 |
Token | Grove |
Token ID | 24144 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ipal | +0.740 |
init | +0.730 |
shift | +0.697 |
actory | +0.695 |
ounge | +0.676 |
Neg logit contributions | |
Dent | -0.605 |
Nadu | -0.576 |
Devi | -0.561 |
Equity | -0.515 |
Benefit | -0.512 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ipal | +0.727 |
init | +0.714 |
shift | +0.675 |
actory | +0.674 |
ounge | +0.653 |
Neg logit contributions | |
Dent | -0.812 |
Nadu | -0.779 |
Devi | -0.761 |
Equity | -0.711 |
Benefit | -0.708 |
Token | California |
Token ID | 3442 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Dent | +0.149 |
Nadu | +0.141 |
Devi | +0.137 |
Equity | +0.126 |
iaz | +0.125 |
Neg logit contributions | |
ipal | -0.202 |
init | -0.200 |
shift | -0.191 |
actory | -0.191 |
ounge | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Dent | +0.780 |
Nadu | +0.744 |
Devi | +0.726 |
Benefit | +0.680 |
Equity | +0.678 |
Neg logit contributions | |
ipal | -0.777 |
init | -0.766 |
shift | -0.736 |
actory | -0.730 |
itual | -0.713 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ipal | +0.236 |
init | +0.234 |
shift | +0.220 |
actory | +0.218 |
ounge | +0.211 |
Neg logit contributions | |
Dent | -0.262 |
Nadu | -0.254 |
Devi | -0.246 |
iaz | -0.231 |
Equity | -0.229 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
ipal | +0.487 |
init | +0.486 |
shift | +0.429 |
actory | +0.410 |
photo | +0.398 |
Neg logit contributions | |
Dent | -1.443 |
Nadu | -1.417 |
Devi | -1.394 |
iaz | -1.337 |
merce | -1.331 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
init | +2.123 |
ipal | +2.011 |
shift | +1.940 |
actory | +1.875 |
photo | +1.826 |
Neg logit contributions | |
Nadu | -5.556 |
Dent | -5.516 |
Devi | -5.388 |
merce | -5.303 |
iaz | -5.267 |
Token | of |
Token ID | 286 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
init | +0.533 |
ipal | +0.519 |
shift | +0.494 |
photo | +0.480 |
actory | +0.479 |
Neg logit contributions | |
Dent | -0.786 |
Nadu | -0.776 |
Devi | -0.747 |
iaz | -0.707 |
merce | -0.699 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
init | +0.048 |
ipal | +0.047 |
shift | +0.044 |
actory | +0.043 |
photo | +0.041 |
Neg logit contributions | |
Dent | -0.103 |
Nadu | -0.101 |
Devi | -0.100 |
iaz | -0.095 |
ouri | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
init | +0.545 |
ipal | +0.545 |
shift | +0.506 |
actory | +0.495 |
photo | +0.491 |
Neg logit contributions | |
Dent | -0.728 |
Nadu | -0.713 |
Devi | -0.696 |
iaz | -0.652 |
ouri | -0.643 |
Token |
|
Token ID | 198 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
init | +0.345 |
ipal | +0.335 |
shift | +0.321 |
actory | +0.310 |
photo | +0.302 |
Neg logit contributions | |
Dent | -0.471 |
Nadu | -0.457 |
Devi | -0.446 |
iaz | -0.419 |
Equity | -0.416 |
Token | View |
Token ID | 3582 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ipal | +0.152 |
init | +0.146 |
shift | +0.135 |
actory | +0.133 |
photo | +0.128 |
Neg logit contributions | |
Dent | -0.263 |
Nadu | -0.259 |
Devi | -0.251 |
iaz | -0.239 |
ouri | -0.239 |
Token | all |
Token ID | 477 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
init | +0.998 |
ipal | +0.994 |
actory | +0.953 |
shift | +0.945 |
selector | +0.909 |
Neg logit contributions | |
Dent | -1.039 |
Nadu | -0.990 |
Devi | -0.966 |
Equity | -0.893 |
Benefit | -0.891 |
Token | New |
Token ID | 968 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
Dent | +0.211 |
Nadu | +0.206 |
Devi | +0.198 |
iaz | +0.186 |
Equity | +0.181 |
Neg logit contributions | |
ipal | -0.281 |
init | -0.279 |
shift | -0.266 |
actory | -0.263 |
ounge | -0.256 |
Token | York |
Token ID | 1971 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
init | +0.415 |
ipal | +0.407 |
shift | +0.391 |
actory | +0.382 |
photo | +0.361 |
Neg logit contributions | |
Dent | -0.606 |
Nadu | -0.590 |
Devi | -0.585 |
iaz | -0.545 |
ouri | -0.538 |
Token | Times |
Token ID | 3782 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
init | +1.164 |
ipal | +1.161 |
shift | +1.100 |
actory | +1.097 |
selector | +1.066 |
Neg logit contributions | |
Dent | -0.757 |
Nadu | -0.729 |
Devi | -0.718 |
iaz | -0.661 |
merce | -0.659 |
Token | newsletters |
Token ID | 16983 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
init | +1.302 |
ipal | +1.252 |
shift | +1.154 |
actory | +1.150 |
photo | +1.137 |
Neg logit contributions | |
Dent | -3.087 |
Nadu | -3.002 |
Devi | -2.966 |
iaz | -2.866 |
Benefit | -2.812 |
Token | . |
Token ID | 13 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
init | +2.904 |
ipal | +2.699 |
shift | +2.644 |
actory | +2.563 |
photo | +2.525 |
Neg logit contributions | |
Dent | -4.918 |
eleph | -4.826 |
Nadu | -4.792 |
Devi | -4.715 |
merce | -4.644 |
Token |
|
Token ID | 198 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
init | +0.593 |
ipal | +0.578 |
shift | +0.553 |
actory | +0.536 |
photo | +0.518 |
Neg logit contributions | |
Dent | -0.804 |
Nadu | -0.783 |
Devi | -0.767 |
iaz | -0.724 |
merce | -0.716 |
Token |
|
Token ID | 198 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
init | +0.529 |
ipal | +0.513 |
shift | +0.494 |
actory | +0.479 |
photo | +0.464 |
Neg logit contributions | |
Dent | -0.736 |
Nadu | -0.719 |
Devi | -0.703 |
iaz | -0.659 |
Equity | -0.653 |
Token | For |
Token ID | 1890 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
ipal | +0.455 |
init | +0.453 |
shift | +0.427 |
actory | +0.420 |
ounge | +0.407 |
Neg logit contributions | |
Dent | -0.580 |
Nadu | -0.556 |
Devi | -0.545 |
Equity | -0.509 |
Benefit | -0.509 |
Token | its |
Token ID | 663 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
Dent | +0.322 |
Nadu | +0.309 |
Devi | +0.300 |
Equity | +0.280 |
iaz | +0.279 |
Neg logit contributions | |
ipal | -0.312 |
init | -0.307 |
shift | -0.291 |
actory | -0.290 |
ounge | -0.281 |
Token | 20 |
Token ID | 1160 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
ipal | +0.045 |
init | +0.045 |
shift | +0.041 |
actory | +0.041 |
ounge | +0.039 |
Neg logit contributions | |
Dent | -0.082 |
Nadu | -0.081 |
Devi | -0.079 |
iaz | -0.075 |
Equity | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
init | +0.206 |
ipal | +0.206 |
shift | +0.192 |
actory | +0.190 |
photo | +0.179 |
Neg logit contributions | |
Dent | -0.279 |
Nadu | -0.270 |
Devi | -0.263 |
iaz | -0.249 |
Equity | -0.247 |
Token | 2015 |
Token ID | 1853 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Dent | +0.174 |
Nadu | +0.166 |
Devi | +0.161 |
Equity | +0.149 |
Benefit | +0.148 |
Neg logit contributions | |
ipal | -0.196 |
init | -0.193 |
shift | -0.183 |
actory | -0.183 |
ounge | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Dent | +0.432 |
Nadu | +0.408 |
Devi | +0.402 |
Benefit | +0.377 |
Equity | +0.376 |
Neg logit contributions | |
ipal | -0.419 |
init | -0.408 |
shift | -0.390 |
actory | -0.390 |
ounge | -0.381 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Dent | +0.130 |
Nadu | +0.125 |
Devi | +0.122 |
iaz | +0.114 |
Equity | +0.114 |
Neg logit contributions | |
ipal | -0.115 |
init | -0.114 |
shift | -0.107 |
actory | -0.106 |
ounge | -0.103 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
ipal | +0.456 |
init | +0.451 |
shift | +0.404 |
actory | +0.387 |
photo | +0.373 |
Neg logit contributions | |
Dent | -1.338 |
Nadu | -1.305 |
Devi | -1.289 |
iaz | -1.227 |
merce | -1.218 |
Token | 8 |
Token ID | 807 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
init | +2.283 |
ipal | +2.234 |
shift | +2.001 |
actory | +1.926 |
photo | +1.913 |
Neg logit contributions | |
Dent | -5.411 |
Nadu | -5.299 |
Devi | -5.156 |
merce | -5.116 |
iaz | -4.985 |
Token | of |
Token ID | 286 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
init | +0.111 |
ipal | +0.110 |
shift | +0.104 |
actory | +0.101 |
photo | +0.098 |
Neg logit contributions | |
Dent | -0.161 |
Nadu | -0.157 |
Devi | -0.153 |
Equity | -0.143 |
iaz | -0.142 |
Token | 15 |
Token ID | 1315 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
Dent | +0.120 |
Nadu | +0.118 |
Devi | +0.116 |
iaz | +0.111 |
ouri | +0.109 |
Neg logit contributions | |
init | -0.058 |
ipal | -0.056 |
shift | -0.052 |
actory | -0.052 |
itual | -0.048 |
Token | Photos |
Token ID | 9434 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
init | +0.270 |
ipal | +0.266 |
shift | +0.243 |
actory | +0.241 |
photo | +0.236 |
Neg logit contributions | |
Dent | -0.554 |
Nadu | -0.545 |
Devi | -0.531 |
iaz | -0.508 |
merce | -0.506 |
Token | : |
Token ID | 25 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
init | +1.585 |
ipal | +1.471 |
shift | +1.442 |
actory | +1.327 |
photo | +1.319 |
Neg logit contributions | |
Dent | -4.233 |
Nadu | -4.194 |
Devi | -4.113 |
eleph | -4.077 |
merce | -4.055 |
Token | and |
Token ID | 290 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
ipal | +0.177 |
init | +0.173 |
shift | +0.164 |
actory | +0.163 |
ounge | +0.158 |
Neg logit contributions | |
Dent | -0.206 |
Nadu | -0.198 |
Devi | -0.193 |
Equity | -0.181 |
Benefit | -0.180 |
Token | stem |
Token ID | 10717 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
ipal | +0.057 |
init | +0.055 |
shift | +0.053 |
actory | +0.052 |
ounge | +0.051 |
Neg logit contributions | |
Dent | -0.066 |
Nadu | -0.064 |
Devi | -0.063 |
Equity | -0.059 |
iaz | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Dent | +0.430 |
Nadu | +0.411 |
Devi | +0.403 |
Equity | +0.377 |
Benefit | +0.376 |
Neg logit contributions | |
ipal | -0.367 |
init | -0.360 |
actory | -0.340 |
shift | -0.340 |
ounge | -0.329 |
Token | View |
Token ID | 3582 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
ipal | +0.344 |
init | +0.339 |
shift | +0.325 |
actory | +0.321 |
ounge | +0.313 |
Neg logit contributions | |
Dent | -0.290 |
Nadu | -0.279 |
Devi | -0.270 |
iaz | -0.251 |
Equity | -0.249 |
Token | Full |
Token ID | 6462 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ipal | +0.378 |
init | +0.373 |
actory | +0.355 |
shift | +0.355 |
ounge | +0.341 |
Neg logit contributions | |
Dent | -0.421 |
Nadu | -0.404 |
Devi | -0.394 |
Equity | -0.367 |
iaz | -0.366 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
Dent | +0.084 |
Nadu | +0.081 |
Devi | +0.078 |
Equity | +0.072 |
Benefit | +0.072 |
Neg logit contributions | |
ipal | -0.101 |
init | -0.100 |
shift | -0.095 |
actory | -0.095 |
ounge | -0.092 |
Token | Adam |
Token ID | 7244 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ipal | +3.148 |
init | +3.072 |
shift | +2.897 |
actory | +2.872 |
photo | +2.751 |
Neg logit contributions | |
Dent | -4.453 |
Nadu | -4.413 |
Devi | -4.256 |
iaz | -4.126 |
merce | -4.033 |
Token | Glenn |
Token ID | 17551 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ipal | +0.882 |
init | +0.871 |
shift | +0.827 |
actory | +0.827 |
ounge | +0.801 |
Neg logit contributions | |
Dent | -0.737 |
Nadu | -0.708 |
Devi | -0.687 |
Equity | -0.636 |
Benefit | -0.631 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ipal | +0.905 |
init | +0.897 |
shift | +0.844 |
actory | +0.842 |
ounge | +0.817 |
Neg logit contributions | |
Dent | -0.935 |
Nadu | -0.898 |
Devi | -0.875 |
Equity | -0.816 |
Benefit | -0.813 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
init | +0.199 |
ipal | +0.195 |
shift | +0.187 |
actory | +0.182 |
photo | +0.176 |
Neg logit contributions | |
Dent | -0.260 |
Nadu | -0.252 |
Devi | -0.246 |
iaz | -0.230 |
Equity | -0.229 |
Token | C |
Token ID | 34 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ipal | +0.094 |
init | +0.092 |
actory | +0.086 |
shift | +0.086 |
ounge | +0.083 |
Neg logit contributions | |
Dent | -0.140 |
Nadu | -0.135 |
Devi | -0.132 |
Equity | -0.125 |
Benefit | -0.124 |
Token | community |
Token ID | 2055 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
Dent | +0.024 |
Nadu | +0.023 |
Devi | +0.022 |
Equity | +0.021 |
Benefit | +0.021 |
Neg logit contributions | |
ipal | -0.024 |
init | -0.024 |
shift | -0.022 |
actory | -0.022 |
ounge | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
ipal | +0.489 |
init | +0.481 |
shift | +0.454 |
actory | +0.453 |
ounge | +0.439 |
Neg logit contributions | |
Dent | -0.566 |
Nadu | -0.543 |
Devi | -0.531 |
Equity | -0.497 |
Benefit | -0.495 |
Token | ( |
Token ID | 357 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ipal | +0.628 |
init | +0.624 |
shift | +0.588 |
actory | +0.584 |
ounge | +0.567 |
Neg logit contributions | |
Dent | -0.622 |
Nadu | -0.604 |
Devi | -0.584 |
iaz | -0.548 |
Benefit | -0.539 |
Token | Photo |
Token ID | 6191 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
ipal | +0.134 |
init | +0.132 |
shift | +0.124 |
actory | +0.123 |
ounge | +0.119 |
Neg logit contributions | |
Dent | -0.192 |
Nadu | -0.185 |
Devi | -0.181 |
Equity | -0.170 |
Benefit | -0.170 |
Token | by |
Token ID | 416 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
ipal | +2.402 |
init | +2.363 |
shift | +2.219 |
actory | +2.215 |
ounge | +2.124 |
Neg logit contributions | |
Dent | -3.201 |
Nadu | -3.112 |
Devi | -3.038 |
iaz | -2.842 |
Equity | -2.837 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
Dent | +0.067 |
Nadu | +0.064 |
Devi | +0.063 |
Equity | +0.058 |
Benefit | +0.058 |
Neg logit contributions | |
ipal | -0.066 |
init | -0.065 |
shift | -0.062 |
actory | -0.062 |
ounge | -0.060 |
Token | / |
Token ID | 14 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ipal | +3.424 |
init | +3.380 |
shift | +3.178 |
actory | +3.172 |
ounge | +3.071 |
Neg logit contributions | |
Dent | -4.072 |
Nadu | -3.936 |
Devi | -3.826 |
iaz | -3.569 |
Equity | -3.552 |
Token | John |
Token ID | 7554 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
ipal | +1.915 |
init | +1.914 |
shift | +1.738 |
actory | +1.712 |
photo | +1.685 |
Neg logit contributions | |
Dent | -2.846 |
Nadu | -2.770 |
Devi | -2.675 |
Benefit | -2.516 |
iaz | -2.514 |
Token | S |
Token ID | 311 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
init | +0.615 |
ipal | +0.601 |
actory | +0.577 |
shift | +0.567 |
itual | +0.555 |
Neg logit contributions | |
Nadu | -0.639 |
Dent | -0.638 |
Devi | -0.601 |
iaz | -0.574 |
Equity | -0.561 |
Token | omm |
Token ID | 2002 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
ipal | +0.437 |
init | +0.429 |
shift | +0.405 |
actory | +0.404 |
ounge | +0.391 |
Neg logit contributions | |
Dent | -0.492 |
Nadu | -0.472 |
Devi | -0.461 |
Equity | -0.432 |
Benefit | -0.429 |
Token | ers |
Token ID | 364 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
ipal | +0.055 |
init | +0.055 |
actory | +0.051 |
shift | +0.051 |
ounge | +0.049 |
Neg logit contributions | |
Dent | -0.064 |
Nadu | -0.062 |
Devi | -0.061 |
Equity | -0.057 |
Benefit | -0.056 |
Token | her |
Token ID | 607 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
ipal | +0.391 |
init | +0.386 |
actory | +0.366 |
shift | +0.365 |
ounge | +0.354 |
Neg logit contributions | |
Dent | -0.366 |
Nadu | -0.354 |
Devi | -0.340 |
Benefit | -0.319 |
iaz | -0.317 |
Token | . |
Token ID | 13 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
Dent | +0.033 |
Nadu | +0.032 |
Devi | +0.031 |
iaz | +0.029 |
Benefit | +0.029 |
Neg logit contributions | |
ipal | -0.029 |
init | -0.028 |
shift | -0.027 |
actory | -0.027 |
ounge | -0.026 |
Token | ( |
Token ID | 357 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ipal | +0.655 |
init | +0.650 |
shift | +0.610 |
actory | +0.608 |
ounge | +0.590 |
Neg logit contributions | |
Dent | -0.631 |
Nadu | -0.618 |
Devi | -0.593 |
iaz | -0.558 |
Benefit | -0.546 |
Token | Photo |
Token ID | 6191 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
ipal | +0.130 |
init | +0.126 |
shift | +0.115 |
actory | +0.115 |
ounge | +0.109 |
Neg logit contributions | |
Dent | -0.313 |
Nadu | -0.303 |
Devi | -0.298 |
Equity | -0.284 |
Benefit | -0.283 |
Token | by |
Token ID | 416 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ipal | +2.669 |
init | +2.621 |
shift | +2.471 |
actory | +2.466 |
ounge | +2.383 |
Neg logit contributions | |
Dent | -3.292 |
Nadu | -3.165 |
Devi | -3.097 |
Equity | -2.900 |
Benefit | -2.890 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
ipal | +0.088 |
init | +0.086 |
shift | +0.081 |
actory | +0.081 |
ounge | +0.078 |
Neg logit contributions | |
Dent | -0.100 |
Nadu | -0.096 |
Devi | -0.094 |
Equity | -0.088 |
iaz | -0.087 |
Token | / |
Token ID | 14 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
init | +2.750 |
ipal | +2.676 |
photo | +2.565 |
shift | +2.541 |
actory | +2.410 |
Neg logit contributions | |
Dent | -4.499 |
Nadu | -4.457 |
Devi | -4.305 |
merce | -4.240 |
eleph | -4.186 |
Token | Car |
Token ID | 9914 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ipal | +1.953 |
init | +1.945 |
shift | +1.795 |
actory | +1.759 |
photo | +1.707 |
Neg logit contributions | |
Dent | -2.731 |
Nadu | -2.666 |
Devi | -2.573 |
iaz | -2.412 |
Benefit | -2.407 |
Token | lo |
Token ID | 5439 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ipal | +0.998 |
init | +0.978 |
actory | +0.898 |
shift | +0.885 |
ounge | +0.841 |
Neg logit contributions | |
Dent | -2.160 |
Nadu | -2.100 |
Devi | -2.054 |
Equity | -1.951 |
Benefit | -1.933 |
Token | Alleg |
Token ID | 26326 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Dent | +1.171 |
Nadu | +1.126 |
Devi | +1.077 |
Equity | +0.987 |
Benefit | +0.986 |
Neg logit contributions | |
ipal | -1.709 |
init | -1.691 |
actory | -1.614 |
shift | -1.611 |
ounge | -1.574 |
Token | ri |
Token ID | 380 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ipal | +0.258 |
init | +0.253 |
shift | +0.239 |
actory | +0.238 |
ounge | +0.231 |
Neg logit contributions | |
Dent | -0.314 |
Nadu | -0.301 |
Devi | -0.295 |
Equity | -0.276 |
Benefit | -0.275 |
Token | by |
Token ID | 416 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ipal | +2.767 |
init | +2.716 |
shift | +2.559 |
actory | +2.555 |
ounge | +2.467 |
Neg logit contributions | |
Dent | -3.447 |
Nadu | -3.320 |
Devi | -3.248 |
Equity | -3.040 |
Benefit | -3.028 |
Token | John |
Token ID | 1757 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Dent | +0.146 |
Nadu | +0.140 |
Devi | +0.137 |
Equity | +0.128 |
Benefit | +0.128 |
Neg logit contributions | |
ipal | -0.125 |
init | -0.122 |
shift | -0.116 |
actory | -0.115 |
ounge | -0.112 |
Token | Moore |
Token ID | 8877 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
init | +0.114 |
ipal | +0.114 |
actory | +0.109 |
shift | +0.107 |
itual | +0.104 |
Neg logit contributions | |
Dent | -0.107 |
Nadu | -0.105 |
Devi | -0.100 |
iaz | -0.094 |
Equity | -0.093 |
Token | / |
Token ID | 14 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Dent | +0.328 |
Nadu | +0.317 |
Devi | +0.310 |
Equity | +0.289 |
iaz | +0.288 |
Neg logit contributions | |
ipal | -0.275 |
init | -0.270 |
shift | -0.254 |
actory | -0.253 |
ounge | -0.245 |
Token | Getty |
Token ID | 6633 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
ipal | +1.373 |
init | +1.351 |
shift | +1.241 |
actory | +1.214 |
photo | +1.173 |
Neg logit contributions | |
Dent | -2.625 |
Nadu | -2.546 |
Devi | -2.530 |
iaz | -2.372 |
Benefit | -2.365 |
Token | Images |
Token ID | 5382 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
ipal | +2.919 |
init | +2.902 |
actory | +2.742 |
shift | +2.713 |
ounge | +2.672 |
Neg logit contributions | |
Dent | -3.322 |
Nadu | -3.209 |
Devi | -3.147 |
iaz | -2.905 |
Benefit | -2.903 |
Token | ) |
Token ID | 8 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ipal | +3.833 |
init | +3.792 |
actory | +3.598 |
shift | +3.593 |
ounge | +3.509 |
Neg logit contributions | |
Dent | -3.557 |
Nadu | -3.425 |
Devi | -3.346 |
iaz | -3.077 |
Equity | -3.070 |
Token | Jeff |
Token ID | 5502 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ipal | +1.454 |
init | +1.448 |
shift | +1.361 |
actory | +1.351 |
ounge | +1.316 |
Neg logit contributions | |
Dent | -1.363 |
Nadu | -1.340 |
Devi | -1.286 |
iaz | -1.216 |
ouri | -1.186 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Dent | +0.304 |
Nadu | +0.299 |
Devi | +0.282 |
Benefit | +0.252 |
iaz | +0.249 |
Neg logit contributions | |
ipal | -0.575 |
init | -0.575 |
shift | -0.549 |
actory | -0.549 |
ounge | -0.538 |
Token | Sen |
Token ID | 2311 |
Feature activation | +2.93e-03 |
Pos logit contributions | |
Dent | +0.360 |
Nadu | +0.343 |
Devi | +0.335 |
Equity | +0.305 |
iaz | +0.305 |
Neg logit contributions | |
ipal | -0.475 |
init | -0.469 |
shift | -0.447 |
actory | -0.446 |
ounge | -0.435 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
ipal | +0.002 |
init | +0.002 |
shift | +0.002 |
actory | +0.002 |
ounge | +0.002 |
Neg logit contributions | |
Dent | -0.003 |
Nadu | -0.002 |
Devi | -0.002 |
Equity | -0.002 |
iaz | -0.002 |
Token | View |
Token ID | 3582 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ipal | +0.184 |
init | +0.178 |
shift | +0.164 |
actory | +0.163 |
photo | +0.156 |
Neg logit contributions | |
Dent | -0.312 |
Nadu | -0.306 |
Devi | -0.298 |
iaz | -0.282 |
ouri | -0.282 |
Token | all |
Token ID | 477 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
init | +0.808 |
ipal | +0.804 |
actory | +0.770 |
shift | +0.764 |
selector | +0.732 |
Neg logit contributions | |
Dent | -0.827 |
Nadu | -0.790 |
Devi | -0.771 |
Equity | -0.713 |
Benefit | -0.713 |
Token | New |
Token ID | 968 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
Dent | +0.191 |
Nadu | +0.186 |
Devi | +0.180 |
iaz | +0.168 |
Equity | +0.164 |
Neg logit contributions | |
ipal | -0.258 |
init | -0.257 |
shift | -0.244 |
actory | -0.241 |
ounge | -0.235 |
Token | York |
Token ID | 1971 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
init | +0.420 |
ipal | +0.414 |
shift | +0.395 |
actory | +0.387 |
photo | +0.367 |
Neg logit contributions | |
Dent | -0.607 |
Nadu | -0.592 |
Devi | -0.587 |
iaz | -0.546 |
Equity | -0.540 |
Token | Times |
Token ID | 3782 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
init | +1.173 |
ipal | +1.172 |
shift | +1.108 |
actory | +1.106 |
selector | +1.073 |
Neg logit contributions | |
Dent | -0.758 |
Nadu | -0.729 |
Devi | -0.718 |
iaz | -0.660 |
merce | -0.656 |
Token | newsletters |
Token ID | 16983 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
init | +1.245 |
ipal | +1.211 |
shift | +1.111 |
actory | +1.105 |
photo | +1.086 |
Neg logit contributions | |
Dent | -2.942 |
Nadu | -2.867 |
Devi | -2.829 |
iaz | -2.723 |
Benefit | -2.683 |
Token | . |
Token ID | 13 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
init | +2.735 |
ipal | +2.555 |
shift | +2.483 |
actory | +2.419 |
photo | +2.372 |
Neg logit contributions | |
Dent | -4.625 |
Nadu | -4.490 |
eleph | -4.449 |
Devi | -4.417 |
merce | -4.321 |
Token |
|
Token ID | 198 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
init | +0.534 |
ipal | +0.521 |
shift | +0.497 |
actory | +0.483 |
photo | +0.466 |
Neg logit contributions | |
Dent | -0.715 |
Nadu | -0.696 |
Devi | -0.681 |
iaz | -0.643 |
merce | -0.633 |
Token |
|
Token ID | 198 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
init | +0.441 |
ipal | +0.429 |
shift | +0.411 |
actory | +0.401 |
photo | +0.386 |
Neg logit contributions | |
Dent | -0.608 |
Nadu | -0.594 |
Devi | -0.579 |
iaz | -0.543 |
Equity | -0.540 |
Token | � |
Token ID | 447 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
ipal | +0.376 |
init | +0.373 |
shift | +0.350 |
actory | +0.346 |
ounge | +0.334 |
Neg logit contributions | |
Dent | -0.493 |
Nadu | -0.474 |
Devi | -0.465 |
Equity | -0.436 |
Benefit | -0.435 |
Token | � |
Token ID | 250 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
ipal | +0.034 |
init | +0.034 |
actory | +0.031 |
shift | +0.031 |
itual | +0.029 |
Neg logit contributions | |
Dent | -0.075 |
Nadu | -0.073 |
Devi | -0.071 |
Equity | -0.068 |
iaz | -0.068 |
Token | issues |
Token ID | 2428 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ipal | +0.150 |
init | +0.148 |
shift | +0.140 |
actory | +0.140 |
ounge | +0.136 |
Neg logit contributions | |
Dent | -0.128 |
Nadu | -0.122 |
Devi | -0.119 |
Equity | -0.110 |
Benefit | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Dent | +1.338 |
Nadu | +1.280 |
Devi | +1.251 |
Equity | +1.166 |
Benefit | +1.161 |
Neg logit contributions | |
ipal | -1.280 |
init | -1.259 |
shift | -1.193 |
actory | -1.191 |
ounge | -1.155 |
Token | ( |
Token ID | 357 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
ipal | +0.287 |
init | +0.285 |
shift | +0.269 |
actory | +0.267 |
ounge | +0.260 |
Neg logit contributions | |
Dent | -0.283 |
Nadu | -0.276 |
Devi | -0.267 |
iaz | -0.250 |
Equity | -0.246 |
Token | Photo |
Token ID | 6191 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
ipal | +0.019 |
init | +0.018 |
actory | +0.017 |
shift | +0.017 |
ounge | +0.016 |
Neg logit contributions | |
Dent | -0.052 |
Nadu | -0.050 |
Devi | -0.049 |
Equity | -0.047 |
Benefit | -0.047 |
Token | by |
Token ID | 416 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
ipal | +2.551 |
init | +2.505 |
shift | +2.362 |
actory | +2.357 |
ounge | +2.279 |
Neg logit contributions | |
Dent | -3.127 |
Nadu | -3.002 |
Devi | -2.939 |
Equity | -2.753 |
Benefit | -2.744 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
Dent | +0.067 |
Nadu | +0.064 |
Devi | +0.063 |
Equity | +0.059 |
Benefit | +0.059 |
Neg logit contributions | |
ipal | -0.054 |
init | -0.053 |
shift | -0.050 |
actory | -0.050 |
ounge | -0.048 |
Token | / |
Token ID | 14 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
init | +2.700 |
ipal | +2.613 |
photo | +2.521 |
shift | +2.495 |
actory | +2.358 |
Neg logit contributions | |
Dent | -4.439 |
Nadu | -4.403 |
Devi | -4.263 |
eleph | -4.192 |
merce | -4.186 |
Token | Gary |
Token ID | 33820 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
ipal | +1.885 |
init | +1.872 |
shift | +1.719 |
actory | +1.697 |
photo | +1.652 |
Neg logit contributions | |
Dent | -2.715 |
Nadu | -2.659 |
Devi | -2.579 |
Benefit | -2.413 |
iaz | -2.410 |
Token | Cameron |
Token ID | 10821 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
init | +0.496 |
ipal | +0.479 |
actory | +0.456 |
photo | +0.456 |
shift | +0.452 |
Neg logit contributions | |
Nadu | -0.672 |
Dent | -0.646 |
Devi | -0.622 |
merce | -0.605 |
ouri | -0.605 |
Token | / |
Token ID | 14 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ipal | +0.646 |
init | +0.636 |
shift | +0.606 |
actory | +0.605 |
ounge | +0.587 |
Neg logit contributions | |
Dent | -0.578 |
Nadu | -0.549 |
Devi | -0.536 |
Equity | -0.497 |
Benefit | -0.495 |
Token | File |
Token ID | 8979 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
ipal | +1.810 |
init | +1.779 |
actory | +1.663 |
shift | +1.659 |
ounge | +1.591 |
Neg logit contributions | |
Dent | -2.438 |
Nadu | -2.339 |
Devi | -2.327 |
Benefit | -2.153 |
iaz | -2.146 |
Token | View |
Token ID | 3582 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ipal | +0.112 |
init | +0.108 |
shift | +0.100 |
actory | +0.099 |
photo | +0.095 |
Neg logit contributions | |
Dent | -0.191 |
Nadu | -0.188 |
Devi | -0.182 |
iaz | -0.173 |
ouri | -0.173 |
Token | all |
Token ID | 477 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
init | +0.786 |
ipal | +0.783 |
actory | +0.750 |
shift | +0.744 |
selector | +0.713 |
Neg logit contributions | |
Dent | -0.808 |
Nadu | -0.770 |
Devi | -0.752 |
Equity | -0.695 |
Benefit | -0.695 |
Token | New |
Token ID | 968 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
Dent | +0.289 |
Nadu | +0.281 |
Devi | +0.271 |
iaz | +0.253 |
Equity | +0.247 |
Neg logit contributions | |
ipal | -0.389 |
init | -0.387 |
shift | -0.369 |
actory | -0.364 |
ounge | -0.355 |
Token | York |
Token ID | 1971 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
init | +0.347 |
ipal | +0.341 |
shift | +0.326 |
actory | +0.319 |
photo | +0.303 |
Neg logit contributions | |
Dent | -0.502 |
Nadu | -0.489 |
Devi | -0.484 |
iaz | -0.451 |
ouri | -0.445 |
Token | Times |
Token ID | 3782 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
init | +1.020 |
ipal | +1.018 |
shift | +0.964 |
actory | +0.962 |
selector | +0.932 |
Neg logit contributions | |
Dent | -0.656 |
Nadu | -0.630 |
Devi | -0.620 |
iaz | -0.568 |
merce | -0.563 |
Token | newsletters |
Token ID | 16983 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
init | +1.194 |
ipal | +1.160 |
shift | +1.068 |
actory | +1.061 |
photo | +1.041 |
Neg logit contributions | |
Dent | -2.813 |
Nadu | -2.737 |
Devi | -2.706 |
iaz | -2.597 |
Benefit | -2.562 |
Token | . |
Token ID | 13 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
init | +2.681 |
ipal | +2.520 |
shift | +2.441 |
actory | +2.384 |
photo | +2.331 |
Neg logit contributions | |
Dent | -4.479 |
Nadu | -4.355 |
Devi | -4.287 |
eleph | -4.286 |
merce | -4.168 |
Token |
|
Token ID | 198 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
init | +0.485 |
ipal | +0.473 |
shift | +0.452 |
actory | +0.439 |
photo | +0.423 |
Neg logit contributions | |
Dent | -0.649 |
Nadu | -0.632 |
Devi | -0.619 |
iaz | -0.584 |
merce | -0.576 |
Token |
|
Token ID | 198 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
init | +0.434 |
ipal | +0.421 |
shift | +0.404 |
actory | +0.393 |
photo | +0.379 |
Neg logit contributions | |
Dent | -0.600 |
Nadu | -0.585 |
Devi | -0.572 |
iaz | -0.535 |
Equity | -0.533 |
Token | The |
Token ID | 464 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ipal | +0.364 |
init | +0.360 |
shift | +0.337 |
actory | +0.334 |
ounge | +0.322 |
Neg logit contributions | |
Dent | -0.487 |
Nadu | -0.468 |
Devi | -0.460 |
Equity | -0.431 |
Benefit | -0.430 |
Token | White |
Token ID | 2635 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
Dent | +0.215 |
Nadu | +0.206 |
Devi | +0.201 |
Equity | +0.188 |
Benefit | +0.187 |
Neg logit contributions | |
ipal | -0.193 |
init | -0.190 |
shift | -0.179 |
actory | -0.179 |
ounge | -0.173 |
Token | / |
Token ID | 14 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ipal | +1.827 |
init | +1.809 |
shift | +1.703 |
actory | +1.698 |
ounge | +1.650 |
Neg logit contributions | |
Dent | -1.912 |
Nadu | -1.834 |
Devi | -1.783 |
Equity | -1.660 |
Benefit | -1.659 |
Token | T |
Token ID | 51 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ipal | +0.950 |
init | +0.946 |
shift | +0.872 |
actory | +0.865 |
ounge | +0.827 |
Neg logit contributions | |
Dent | -1.516 |
Nadu | -1.467 |
Devi | -1.433 |
iaz | -1.350 |
Benefit | -1.350 |
Token | NS |
Token ID | 8035 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ipal | +0.574 |
init | +0.568 |
actory | +0.519 |
shift | +0.514 |
ounge | +0.498 |
Neg logit contributions | |
Dent | -1.030 |
Nadu | -0.996 |
Devi | -0.983 |
Equity | -0.924 |
Benefit | -0.924 |
Token | via |
Token ID | 2884 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ipal | +0.330 |
init | +0.324 |
shift | +0.307 |
actory | +0.307 |
ounge | +0.297 |
Neg logit contributions | |
Dent | -0.348 |
Nadu | -0.333 |
Devi | -0.325 |
Equity | -0.303 |
Benefit | -0.302 |
Token | Getty |
Token ID | 7136 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ipal | +0.500 |
init | +0.484 |
shift | +0.444 |
actory | +0.439 |
ounge | +0.414 |
Neg logit contributions | |
Dent | -1.155 |
Nadu | -1.121 |
Devi | -1.099 |
Equity | -1.044 |
iaz | -1.044 |
Token | Images |
Token ID | 5382 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
init | +3.182 |
ipal | +3.165 |
actory | +2.986 |
shift | +2.947 |
ounge | +2.888 |
Neg logit contributions | |
Dent | -3.684 |
Nadu | -3.605 |
Devi | -3.539 |
iaz | -3.258 |
Equity | -3.244 |
Token | ) |
Token ID | 8 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ipal | +3.592 |
init | +3.568 |
shift | +3.374 |
actory | +3.367 |
ounge | +3.288 |
Neg logit contributions | |
Dent | -3.422 |
Nadu | -3.315 |
Devi | -3.222 |
iaz | -2.971 |
Equity | -2.948 |
Token | Indiana |
Token ID | 10278 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ipal | +1.335 |
init | +1.327 |
shift | +1.249 |
actory | +1.244 |
ounge | +1.207 |
Neg logit contributions | |
Dent | -1.198 |
Nadu | -1.166 |
Devi | -1.119 |
iaz | -1.047 |
Equity | -1.035 |
Token | Gov |
Token ID | 10964 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ipal | +0.146 |
init | +0.144 |
actory | +0.138 |
shift | +0.137 |
ounge | +0.134 |
Neg logit contributions | |
Dent | -0.095 |
Nadu | -0.091 |
Devi | -0.088 |
Equity | -0.080 |
Benefit | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Dent | +0.242 |
Nadu | +0.230 |
Devi | +0.226 |
Equity | +0.211 |
Benefit | +0.210 |
Neg logit contributions | |
ipal | -0.220 |
init | -0.216 |
shift | -0.207 |
actory | -0.206 |
ounge | -0.199 |
Token | Mike |
Token ID | 4995 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
ipal | +0.109 |
init | +0.106 |
shift | +0.103 |
actory | +0.102 |
itual | +0.098 |
Neg logit contributions | |
Dent | -0.125 |
Nadu | -0.117 |
Devi | -0.116 |
Equity | -0.110 |
Benefit | -0.109 |
Token | ow |
Token ID | 322 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Dent | +3.255 |
Nadu | +3.111 |
Devi | +3.047 |
Equity | +2.839 |
Benefit | +2.820 |
Neg logit contributions | |
ipal | -3.021 |
init | -2.962 |
shift | -2.807 |
actory | -2.803 |
ounge | -2.717 |
Token | support |
Token ID | 1104 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ipal | +1.413 |
init | +1.405 |
actory | +1.324 |
shift | +1.316 |
ounge | +1.280 |
Neg logit contributions | |
Dent | -1.311 |
Nadu | -1.292 |
Devi | -1.229 |
iaz | -1.140 |
Benefit | -1.140 |
Token | from |
Token ID | 422 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Dent | +1.328 |
Nadu | +1.250 |
Devi | +1.232 |
Equity | +1.143 |
Benefit | +1.137 |
Neg logit contributions | |
ipal | -1.453 |
init | -1.424 |
shift | -1.359 |
actory | -1.354 |
ounge | -1.319 |
Token | former |
Token ID | 1966 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Dent | +0.353 |
Nadu | +0.341 |
Devi | +0.331 |
Equity | +0.306 |
Benefit | +0.306 |
Neg logit contributions | |
ipal | -0.377 |
init | -0.372 |
shift | -0.353 |
actory | -0.352 |
ounge | -0.342 |
Token | Ku |
Token ID | 12554 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
Dent | +0.111 |
Nadu | +0.107 |
Devi | +0.104 |
iaz | +0.096 |
Benefit | +0.095 |
Neg logit contributions | |
ipal | -0.120 |
init | -0.119 |
shift | -0.113 |
actory | -0.112 |
ounge | -0.109 |
Token | Klux |
Token ID | 45092 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
Dent | +1.767 |
Nadu | +1.676 |
Devi | +1.647 |
Equity | +1.526 |
Benefit | +1.503 |
Neg logit contributions | |
ipal | -2.252 |
init | -2.226 |
shift | -2.108 |
actory | -2.105 |
itual | -2.038 |
Token | Klan |
Token ID | 31151 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Dent | +3.034 |
Nadu | +2.854 |
Devi | +2.766 |
Equity | +2.488 |
Benefit | +2.468 |
Neg logit contributions | |
ipal | -5.328 |
init | -5.258 |
actory | -5.043 |
shift | -5.017 |
ounge | -4.917 |
Token | leader |
Token ID | 3554 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
Dent | +1.737 |
Nadu | +1.655 |
Devi | +1.616 |
Equity | +1.493 |
Benefit | +1.487 |
Neg logit contributions | |
ipal | -1.945 |
init | -1.915 |
shift | -1.820 |
actory | -1.818 |
ounge | -1.767 |
Token | David |
Token ID | 3271 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Dent | +0.452 |
Nadu | +0.440 |
Devi | +0.428 |
iaz | +0.391 |
Equity | +0.390 |
Neg logit contributions | |
ipal | -0.492 |
init | -0.484 |
actory | -0.458 |
shift | -0.454 |
ounge | -0.444 |
Token | Duke |
Token ID | 11083 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Dent | +0.140 |
Nadu | +0.138 |
Devi | +0.134 |
Benefit | +0.118 |
Equity | +0.118 |
Neg logit contributions | |
ipal | -0.233 |
init | -0.228 |
shift | -0.215 |
actory | -0.214 |
ounge | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
Dent | +1.583 |
Nadu | +1.510 |
Devi | +1.478 |
Equity | +1.383 |
Benefit | +1.377 |
Neg logit contributions | |
ipal | -1.443 |
init | -1.415 |
shift | -1.346 |
actory | -1.340 |
ounge | -1.298 |
Token | Feed |
Token ID | 18272 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
Dent | +0.087 |
Nadu | +0.084 |
Devi | +0.081 |
iaz | +0.075 |
Equity | +0.075 |
Neg logit contributions | |
ipal | -0.100 |
init | -0.098 |
shift | -0.095 |
actory | -0.094 |
ounge | -0.091 |
Token | books |
Token ID | 12106 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Dent | +0.574 |
Nadu | +0.550 |
Devi | +0.538 |
Equity | +0.504 |
Benefit | +0.503 |
Neg logit contributions | |
ipal | -0.477 |
init | -0.467 |
shift | -0.441 |
actory | -0.440 |
ounge | -0.426 |
Token | , |
Token ID | 11 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Dent | +0.133 |
Nadu | +0.128 |
Devi | +0.125 |
Equity | +0.116 |
Benefit | +0.116 |
Neg logit contributions | |
ipal | -0.121 |
init | -0.119 |
shift | -0.113 |
actory | -0.113 |
ounge | -0.109 |
Token | try |
Token ID | 1949 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Dent | +0.188 |
Nadu | +0.181 |
Devi | +0.176 |
Equity | +0.164 |
iaz | +0.164 |
Neg logit contributions | |
ipal | -0.182 |
init | -0.180 |
shift | -0.172 |
actory | -0.171 |
ounge | -0.165 |
Token | Project |
Token ID | 4935 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
Dent | +1.150 |
Nadu | +1.104 |
Devi | +1.078 |
Equity | +1.008 |
Benefit | +1.003 |
Neg logit contributions | |
ipal | -1.035 |
init | -1.018 |
shift | -0.966 |
actory | -0.961 |
ounge | -0.931 |
Token | Gutenberg |
Token ID | 20336 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
Dent | +0.490 |
Nadu | +0.463 |
Devi | +0.448 |
Equity | +0.408 |
iaz | +0.407 |
Neg logit contributions | |
ipal | -0.753 |
init | -0.745 |
shift | -0.715 |
actory | -0.713 |
ounge | -0.693 |
Token | ( |
Token ID | 357 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Dent | +3.928 |
Nadu | +3.752 |
Devi | +3.665 |
Benefit | +3.441 |
Equity | +3.422 |
Neg logit contributions | |
ipal | -3.490 |
init | -3.420 |
shift | -3.238 |
actory | -3.233 |
ounge | -3.143 |
Token | www |
Token ID | 2503 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Dent | +0.264 |
Nadu | +0.253 |
Devi | +0.248 |
Equity | +0.233 |
Benefit | +0.232 |
Neg logit contributions | |
ipal | -0.197 |
init | -0.193 |
shift | -0.181 |
actory | -0.181 |
ounge | -0.175 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Dent | +1.038 |
Nadu | +0.994 |
Devi | +0.974 |
Equity | +0.917 |
Benefit | +0.906 |
Neg logit contributions | |
ipal | -0.841 |
init | -0.832 |
shift | -0.783 |
actory | -0.780 |
ounge | -0.749 |
Token | g |
Token ID | 70 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
ipal | +0.115 |
init | +0.113 |
shift | +0.106 |
actory | +0.106 |
ounge | +0.102 |
Neg logit contributions | |
Dent | -0.154 |
Nadu | -0.148 |
Devi | -0.145 |
Equity | -0.137 |
Benefit | -0.136 |
Token | utenberg |
Token ID | 19028 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Dent | +0.504 |
Nadu | +0.486 |
Devi | +0.476 |
iaz | +0.454 |
Benefit | +0.451 |
Neg logit contributions | |
ipal | -0.295 |
init | -0.287 |
actory | -0.267 |
shift | -0.266 |
ounge | -0.256 |
Token | comments |
Token ID | 3651 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Dent | +0.174 |
Nadu | +0.167 |
Devi | +0.164 |
Equity | +0.153 |
Benefit | +0.153 |
Neg logit contributions | |
ipal | -0.144 |
init | -0.142 |
shift | -0.134 |
actory | -0.134 |
ounge | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Dent | +1.284 |
Nadu | +1.230 |
Devi | +1.203 |
Equity | +1.126 |
Benefit | +1.122 |
Neg logit contributions | |
ipal | -1.147 |
init | -1.125 |
shift | -1.063 |
actory | -1.062 |
ounge | -1.028 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Dent | +0.138 |
Nadu | +0.132 |
Devi | +0.129 |
Equity | +0.119 |
iaz | +0.119 |
Neg logit contributions | |
ipal | -0.144 |
init | -0.142 |
shift | -0.135 |
actory | -0.134 |
ounge | -0.130 |
Token |
|
Token ID | 198 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Dent | +0.130 |
Nadu | +0.124 |
Devi | +0.122 |
Equity | +0.114 |
Benefit | +0.113 |
Neg logit contributions | |
ipal | -0.112 |
init | -0.111 |
shift | -0.105 |
actory | -0.104 |
ounge | -0.100 |
Token | High |
Token ID | 11922 |
Feature activation | -5.53e-03 |
Pos logit contributions | |
Dent | +0.215 |
Nadu | +0.206 |
Devi | +0.202 |
Equity | +0.190 |
Benefit | +0.189 |
Neg logit contributions | |
ipal | -0.161 |
init | -0.158 |
shift | -0.149 |
actory | -0.148 |
ounge | -0.143 |
Token | lights |
Token ID | 8091 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
Dent | +0.004 |
Nadu | +0.004 |
Devi | +0.004 |
iaz | +0.004 |
Equity | +0.004 |
Neg logit contributions | |
ipal | -0.004 |
init | -0.004 |
shift | -0.004 |
actory | -0.004 |
ounge | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
Dent | +3.865 |
Nadu | +3.626 |
Devi | +3.614 |
Benefit | +3.393 |
Equity | +3.373 |
Neg logit contributions | |
ipal | -3.492 |
init | -3.424 |
actory | -3.263 |
shift | -3.224 |
ounge | -3.167 |
Token | this |
Token ID | 428 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Dent | +0.419 |
Nadu | +0.402 |
Devi | +0.390 |
iaz | +0.362 |
Equity | +0.362 |
Neg logit contributions | |
ipal | -0.438 |
init | -0.432 |
shift | -0.410 |
actory | -0.409 |
ounge | -0.396 |
Token | new |
Token ID | 649 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
ipal | +0.240 |
init | +0.237 |
shift | +0.225 |
actory | +0.222 |
ounge | +0.213 |
Neg logit contributions | |
Dent | -0.302 |
Nadu | -0.292 |
Devi | -0.284 |
iaz | -0.267 |
Equity | -0.265 |
Token | release |
Token ID | 2650 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
ipal | +0.561 |
init | +0.556 |
shift | +0.527 |
actory | +0.522 |
ounge | +0.501 |
Neg logit contributions | |
Dent | -0.677 |
Nadu | -0.652 |
Devi | -0.635 |
iaz | -0.594 |
Equity | -0.593 |
Token | , |
Token ID | 11 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
ipal | +0.345 |
init | +0.339 |
shift | +0.320 |
actory | +0.316 |
ounge | +0.305 |
Neg logit contributions | |
Dent | -0.470 |
Nadu | -0.452 |
Devi | -0.442 |
Equity | -0.415 |
iaz | -0.415 |
Token | subway |
Token ID | 19612 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
Dent | +0.160 |
Nadu | +0.154 |
Devi | +0.150 |
Equity | +0.139 |
iaz | +0.139 |
Neg logit contributions | |
ipal | -0.161 |
init | -0.159 |
shift | -0.152 |
actory | -0.150 |
ounge | -0.146 |
Token | gr |
Token ID | 1036 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Dent | +0.814 |
Nadu | +0.781 |
Devi | +0.765 |
Equity | +0.718 |
Benefit | +0.715 |
Neg logit contributions | |
ipal | -0.650 |
init | -0.638 |
shift | -0.601 |
actory | -0.600 |
ounge | -0.580 |
Token | ates |
Token ID | 689 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ipal | +0.078 |
init | +0.077 |
shift | +0.073 |
actory | +0.073 |
ounge | +0.071 |
Neg logit contributions | |
Dent | -0.073 |
Nadu | -0.069 |
Devi | -0.068 |
Equity | -0.063 |
Benefit | -0.062 |
Token | or |
Token ID | 393 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ipal | +0.244 |
init | +0.241 |
shift | +0.228 |
actory | +0.226 |
ounge | +0.219 |
Neg logit contributions | |
Dent | -0.287 |
Nadu | -0.276 |
Devi | -0.270 |
Equity | -0.253 |
Benefit | -0.251 |
Token | on |
Token ID | 319 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
ipal | +0.165 |
init | +0.163 |
shift | +0.155 |
actory | +0.153 |
ounge | +0.148 |
Neg logit contributions | |
Dent | -0.195 |
Nadu | -0.188 |
Devi | -0.184 |
Equity | -0.172 |
iaz | -0.172 |
Token | sto |
Token ID | 3995 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
ipal | +0.061 |
init | +0.060 |
shift | +0.057 |
actory | +0.056 |
ounge | +0.055 |
Neg logit contributions | |
Dent | -0.066 |
Nadu | -0.063 |
Devi | -0.062 |
Equity | -0.057 |
iaz | -0.057 |
Token | ops |
Token ID | 2840 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
Dent | +3.293 |
Nadu | +3.111 |
Devi | +3.060 |
iaz | +2.816 |
Benefit | +2.798 |
Neg logit contributions | |
ipal | -3.892 |
init | -3.783 |
shift | -3.669 |
actory | -3.657 |
itual | -3.519 |
Token | or |
Token ID | 393 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Dent | +0.206 |
Nadu | +0.198 |
Devi | +0.193 |
Equity | +0.181 |
Benefit | +0.180 |
Neg logit contributions | |
ipal | -0.177 |
init | -0.174 |
shift | -0.164 |
actory | -0.163 |
ounge | -0.158 |
Token | in |
Token ID | 287 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ipal | +0.099 |
init | +0.097 |
shift | +0.092 |
actory | +0.092 |
ounge | +0.089 |
Neg logit contributions | |
Dent | -0.121 |
Nadu | -0.116 |
Devi | -0.114 |
Equity | -0.106 |
Benefit | -0.106 |
Token | encamp |
Token ID | 48020 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Dent | +0.139 |
Nadu | +0.134 |
Devi | +0.131 |
Equity | +0.122 |
Benefit | +0.122 |
Neg logit contributions | |
ipal | -0.125 |
init | -0.123 |
shift | -0.116 |
actory | -0.116 |
ounge | -0.112 |
Token | ments |
Token ID | 902 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Dent | +0.899 |
Nadu | +0.856 |
Devi | +0.836 |
Equity | +0.767 |
Benefit | +0.765 |
Neg logit contributions | |
ipal | -1.058 |
init | -1.048 |
actory | -0.998 |
shift | -0.998 |
ounge | -0.966 |
Token | � |
Token ID | 119 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Dent | +0.104 |
Nadu | +0.100 |
Devi | +0.098 |
Benefit | +0.093 |
Equity | +0.093 |
Neg logit contributions | |
ipal | -0.062 |
init | -0.061 |
actory | -0.056 |
shift | -0.056 |
itual | -0.053 |
Token | o |
Token ID | 78 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Dent | +0.098 |
Nadu | +0.093 |
Devi | +0.091 |
Equity | +0.085 |
Benefit | +0.084 |
Neg logit contributions | |
ipal | -0.105 |
init | -0.103 |
shift | -0.098 |
actory | -0.098 |
ounge | -0.095 |
Token | Hal |
Token ID | 11023 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
Dent | +0.380 |
Nadu | +0.363 |
Devi | +0.355 |
Equity | +0.330 |
Benefit | +0.329 |
Neg logit contributions | |
ipal | -0.381 |
init | -0.375 |
shift | -0.356 |
actory | -0.355 |
ounge | -0.344 |
Token | ep |
Token ID | 538 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
ipal | +0.534 |
init | +0.526 |
shift | +0.502 |
actory | +0.501 |
ounge | +0.488 |
Neg logit contributions | |
Dent | -0.429 |
Nadu | -0.408 |
Devi | -0.397 |
Equity | -0.366 |
Benefit | -0.364 |
Token | ā |
Token ID | 10235 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
ipal | +0.134 |
init | +0.132 |
shift | +0.125 |
actory | +0.124 |
ounge | +0.120 |
Neg logit contributions | |
Dent | -0.152 |
Nadu | -0.146 |
Devi | -0.142 |
Equity | -0.133 |
Benefit | -0.133 |
Token | nih |
Token ID | 37373 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
ipal | +0.337 |
init | +0.332 |
shift | +0.314 |
actory | +0.313 |
ounge | +0.304 |
Neg logit contributions | |
Dent | -0.357 |
Nadu | -0.340 |
Devi | -0.333 |
Equity | -0.311 |
Benefit | -0.309 |
Token | o |
Token ID | 78 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
Dent | +3.932 |
Nadu | +3.824 |
Devi | +3.748 |
iaz | +3.542 |
ouri | +3.514 |
Neg logit contributions | |
ipal | -3.129 |
init | -3.051 |
shift | -2.964 |
actory | -2.934 |
itual | -2.839 |
Token | m |
Token ID | 285 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Dent | +0.760 |
Nadu | +0.728 |
Devi | +0.711 |
Equity | +0.662 |
Benefit | +0.660 |
Neg logit contributions | |
ipal | -0.727 |
init | -0.714 |
shift | -0.678 |
actory | -0.677 |
ounge | -0.656 |
Token | ai |
Token ID | 1872 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Dent | +1.356 |
Nadu | +1.307 |
Devi | +1.280 |
Equity | +1.202 |
iaz | +1.201 |
Neg logit contributions | |
ipal | -0.967 |
init | -0.947 |
shift | -0.892 |
actory | -0.890 |
ounge | -0.858 |
Token | , |
Token ID | 11 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
ipal | +0.907 |
init | +0.896 |
shift | +0.840 |
actory | +0.838 |
ounge | +0.815 |
Neg logit contributions | |
Dent | -0.932 |
Nadu | -0.883 |
Devi | -0.869 |
Equity | -0.811 |
Benefit | -0.806 |
Token | n |
Token ID | 299 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
Dent | +0.318 |
Nadu | +0.303 |
Devi | +0.297 |
Equity | +0.276 |
Benefit | +0.274 |
Neg logit contributions | |
ipal | -0.327 |
init | -0.321 |
shift | -0.304 |
actory | -0.303 |
ounge | -0.295 |
Token | announced |
Token ID | 3414 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Dent | +0.438 |
Nadu | +0.421 |
Devi | +0.410 |
iaz | +0.383 |
Benefit | +0.381 |
Neg logit contributions | |
ipal | -0.389 |
init | -0.383 |
shift | -0.361 |
actory | -0.358 |
ounge | -0.347 |
Token | an |
Token ID | 281 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
ipal | +0.402 |
init | +0.394 |
shift | +0.374 |
actory | +0.373 |
ounge | +0.361 |
Neg logit contributions | |
Dent | -0.401 |
Nadu | -0.385 |
Devi | -0.375 |
iaz | -0.347 |
Equity | -0.347 |
Token | alliance |
Token ID | 12801 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Dent | +0.474 |
Nadu | +0.450 |
Devi | +0.441 |
Benefit | +0.409 |
iaz | +0.408 |
Neg logit contributions | |
ipal | -0.466 |
init | -0.459 |
shift | -0.430 |
actory | -0.429 |
ounge | -0.419 |
Token | with |
Token ID | 351 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
Dent | +1.108 |
Nadu | +1.062 |
Devi | +1.036 |
Equity | +0.979 |
Benefit | +0.972 |
Neg logit contributions | |
ipal | -1.083 |
init | -1.057 |
shift | -1.008 |
actory | -0.996 |
itual | -0.984 |
Token | B |
Token ID | 347 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
Dent | +0.030 |
Nadu | +0.029 |
Devi | +0.028 |
iaz | +0.026 |
Equity | +0.026 |
Neg logit contributions | |
ipal | -0.036 |
init | -0.035 |
actory | -0.033 |
shift | -0.033 |
ounge | -0.032 |
Token | ibli |
Token ID | 29142 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
ipal | +0.068 |
init | +0.067 |
shift | +0.063 |
actory | +0.063 |
ounge | +0.061 |
Neg logit contributions | |
Dent | -0.077 |
Nadu | -0.074 |
Devi | -0.073 |
Equity | -0.068 |
Benefit | -0.068 |
Token | othe |
Token ID | 20388 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Dent | +3.096 |
Nadu | +2.928 |
Devi | +2.859 |
Equity | +2.649 |
Benefit | +2.646 |
Neg logit contributions | |
ipal | -3.972 |
init | -3.882 |
shift | -3.733 |
actory | -3.696 |
ounge | -3.625 |
Token | ca |
Token ID | 6888 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Dent | +0.933 |
Nadu | +0.899 |
Devi | +0.878 |
Equity | +0.820 |
Benefit | +0.814 |
Neg logit contributions | |
ipal | -0.807 |
init | -0.795 |
shift | -0.753 |
actory | -0.749 |
ounge | -0.722 |
Token | to |
Token ID | 284 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ipal | +0.109 |
init | +0.107 |
shift | +0.102 |
actory | +0.101 |
ounge | +0.098 |
Neg logit contributions | |
Dent | -0.100 |
Nadu | -0.097 |
Devi | -0.093 |
iaz | -0.086 |
Equity | -0.086 |
Token | directly |
Token ID | 3264 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Dent | +0.185 |
Nadu | +0.179 |
Devi | +0.174 |
Equity | +0.161 |
iaz | +0.160 |
Neg logit contributions | |
ipal | -0.168 |
init | -0.166 |
shift | -0.157 |
actory | -0.156 |
ounge | -0.150 |
Token | sell |
Token ID | 3677 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Dent | +2.078 |
Nadu | +1.990 |
Devi | +1.947 |
Equity | +1.806 |
Benefit | +1.794 |
Neg logit contributions | |
ipal | -1.976 |
init | -1.946 |
shift | -1.847 |
actory | -1.840 |
ounge | -1.781 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Dent | +0.272 |
Nadu | +0.264 |
Devi | +0.254 |
iaz | +0.237 |
Equity | +0.237 |
Neg logit contributions | |
ipal | -0.272 |
init | -0.269 |
shift | -0.256 |
actory | -0.254 |
ounge | -0.246 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Dent | +1.078 |
Nadu | +1.029 |
Devi | +1.006 |
Equity | +0.934 |
Benefit | +0.931 |
Neg logit contributions | |
ipal | -1.097 |
init | -1.079 |
shift | -1.025 |
actory | -1.023 |
ounge | -0.994 |
Token | — |
Token ID | 851 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Dent | +0.232 |
Nadu | +0.222 |
Devi | +0.217 |
Equity | +0.203 |
Benefit | +0.202 |
Neg logit contributions | |
ipal | -0.211 |
init | -0.208 |
shift | -0.197 |
actory | -0.196 |
ounge | -0.190 |
Token | and |
Token ID | 290 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
Dent | +0.273 |
Nadu | +0.262 |
Devi | +0.255 |
Equity | +0.238 |
iaz | +0.238 |
Neg logit contributions | |
ipal | -0.260 |
init | -0.257 |
shift | -0.243 |
actory | -0.242 |
ounge | -0.234 |
Token | were |
Token ID | 547 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
ipal | +0.055 |
init | +0.055 |
shift | +0.052 |
actory | +0.052 |
ounge | +0.050 |
Neg logit contributions | |
Dent | -0.056 |
Nadu | -0.054 |
Devi | -0.052 |
iaz | -0.049 |
Equity | -0.049 |
Token | silenced |
Token ID | 38086 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
ipal | +0.015 |
init | +0.015 |
shift | +0.015 |
actory | +0.014 |
ounge | +0.014 |
Neg logit contributions | |
Dent | -0.017 |
Nadu | -0.017 |
Devi | -0.016 |
Equity | -0.015 |
iaz | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
Dent | +3.590 |
Nadu | +3.420 |
Devi | +3.359 |
Equity | +3.105 |
Benefit | +3.092 |
Neg logit contributions | |
ipal | -3.448 |
init | -3.362 |
shift | -3.218 |
actory | -3.203 |
ounge | -3.152 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Dent | +0.063 |
Nadu | +0.061 |
Devi | +0.058 |
iaz | +0.056 |
ouri | +0.054 |
Neg logit contributions | |
ipal | -0.072 |
init | -0.072 |
shift | -0.068 |
actory | -0.067 |
itual | -0.065 |
Token | : |
Token ID | 25 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ipal | +0.141 |
init | +0.139 |
shift | +0.132 |
actory | +0.131 |
ounge | +0.126 |
Neg logit contributions | |
Dent | -0.155 |
Nadu | -0.149 |
Devi | -0.145 |
Equity | -0.136 |
Benefit | -0.135 |
Token | You |
Token ID | 921 |
Feature activation | -7.95e-03 |
Pos logit contributions | |
ipal | +0.162 |
init | +0.161 |
shift | +0.150 |
actory | +0.148 |
itual | +0.141 |
Neg logit contributions | |
Dent | -0.272 |
Nadu | -0.266 |
Devi | -0.259 |
iaz | -0.246 |
Equity | -0.244 |
Token | have |
Token ID | 423 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Dent | +0.006 |
Nadu | +0.006 |
Devi | +0.006 |
Equity | +0.005 |
iaz | +0.005 |
Neg logit contributions | |
ipal | -0.006 |
init | -0.006 |
shift | -0.005 |
actory | -0.005 |
itual | -0.005 |
Token | called |
Token ID | 1444 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ipal | +0.227 |
init | +0.224 |
shift | +0.211 |
actory | +0.210 |
itual | +0.201 |
Neg logit contributions | |
Dent | -0.277 |
Nadu | -0.265 |
Devi | -0.259 |
Equity | -0.244 |
iaz | -0.243 |
Token | by |
Token ID | 416 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Dent | +0.141 |
Nadu | +0.134 |
Devi | +0.131 |
iaz | +0.123 |
Benefit | +0.123 |
Neg logit contributions | |
ipal | -0.128 |
init | -0.126 |
shift | -0.119 |
actory | -0.119 |
itual | -0.114 |
Token | Chief |
Token ID | 5953 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Dent | +0.187 |
Nadu | +0.177 |
Devi | +0.172 |
iaz | +0.160 |
Benefit | +0.160 |
Neg logit contributions | |
ipal | -0.231 |
init | -0.226 |
shift | -0.215 |
actory | -0.215 |
ounge | -0.208 |
Token | Minister |
Token ID | 4139 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Dent | +0.935 |
Nadu | +0.879 |
Devi | +0.849 |
iaz | +0.765 |
Equity | +0.765 |
Neg logit contributions | |
ipal | -1.585 |
init | -1.559 |
shift | -1.497 |
actory | -1.495 |
ounge | -1.458 |
Token | Ar |
Token ID | 943 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Dent | +0.840 |
Nadu | +0.794 |
Devi | +0.766 |
Equity | +0.695 |
Benefit | +0.693 |
Neg logit contributions | |
ipal | -1.389 |
init | -1.368 |
actory | -1.309 |
shift | -1.309 |
ounge | -1.275 |
Token | vind |
Token ID | 50172 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
Dent | +0.099 |
Nadu | +0.096 |
Devi | +0.092 |
iaz | +0.087 |
Equity | +0.086 |
Neg logit contributions | |
ipal | -0.097 |
init | -0.095 |
shift | -0.091 |
actory | -0.089 |
ounge | -0.086 |
Token | Kejriwal |
Token ID | 42792 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Dent | +1.496 |
Nadu | +1.341 |
Devi | +1.266 |
Equity | +1.038 |
Benefit | +1.025 |
Neg logit contributions | |
ipal | -5.430 |
init | -5.370 |
shift | -5.196 |
actory | -5.190 |
ounge | -5.104 |
Token | . |
Token ID | 13 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
Dent | +1.516 |
Nadu | +1.452 |
Devi | +1.421 |
Equity | +1.327 |
Benefit | +1.323 |
Neg logit contributions | |
ipal | -1.354 |
init | -1.330 |
shift | -1.258 |
actory | -1.256 |
ounge | -1.217 |
Token |
|
Token ID | 198 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Dent | +0.558 |
Nadu | +0.532 |
Devi | +0.517 |
iaz | +0.479 |
Equity | +0.477 |
Neg logit contributions | |
ipal | -0.669 |
init | -0.660 |
shift | -0.628 |
actory | -0.625 |
ounge | -0.607 |
Token |
|
Token ID | 198 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
Dent | +0.437 |
Nadu | +0.424 |
Devi | +0.413 |
iaz | +0.389 |
Equity | +0.386 |
Neg logit contributions | |
init | -0.330 |
ipal | -0.325 |
shift | -0.310 |
actory | -0.302 |
photo | -0.290 |
Token | " |
Token ID | 1 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Dent | +0.467 |
Nadu | +0.448 |
Devi | +0.440 |
Equity | +0.412 |
Benefit | +0.411 |
Neg logit contributions | |
ipal | -0.366 |
init | -0.360 |
shift | -0.339 |
actory | -0.337 |
ounge | -0.326 |
Token | invent |
Token ID | 8067 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
Dent | +0.651 |
Nadu | +0.627 |
Devi | +0.614 |
Equity | +0.578 |
Benefit | +0.576 |
Neg logit contributions | |
ipal | -0.449 |
init | -0.440 |
shift | -0.413 |
actory | -0.412 |
ounge | -0.396 |
Token | ories |
Token ID | 1749 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Dent | +1.319 |
Nadu | +1.191 |
Devi | +1.149 |
iaz | +0.917 |
Equity | +0.911 |
Neg logit contributions | |
ipal | -5.278 |
init | -5.232 |
shift | -5.072 |
actory | -5.037 |
itual | -5.004 |
Token | , |
Token ID | 11 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
ipal | +0.161 |
init | +0.159 |
shift | +0.150 |
actory | +0.149 |
ounge | +0.145 |
Neg logit contributions | |
Dent | -0.189 |
Nadu | -0.181 |
Devi | -0.177 |
Equity | -0.166 |
Benefit | -0.165 |
Token | two |
Token ID | 734 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
Dent | +0.340 |
Nadu | +0.325 |
Devi | +0.318 |
Equity | +0.296 |
Benefit | +0.295 |
Neg logit contributions | |
ipal | -0.319 |
init | -0.314 |
shift | -0.298 |
actory | -0.297 |
ounge | -0.288 |
Token | product |
Token ID | 1720 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
Dent | +0.057 |
Nadu | +0.055 |
Devi | +0.054 |
Equity | +0.050 |
Benefit | +0.050 |
Neg logit contributions | |
ipal | -0.045 |
init | -0.044 |
shift | -0.042 |
actory | -0.041 |
ounge | -0.040 |
Token | catalog |
Token ID | 18388 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
ipal | +0.381 |
init | +0.376 |
shift | +0.353 |
actory | +0.351 |
ounge | +0.339 |
Neg logit contributions | |
Dent | -0.522 |
Nadu | -0.501 |
Devi | -0.491 |
Equity | -0.460 |
Benefit | -0.459 |
Token | s |
Token ID | 82 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Dent | +2.740 |
Nadu | +2.582 |
Devi | +2.517 |
Equity | +2.284 |
Benefit | +2.279 |
Neg logit contributions | |
ipal | -4.086 |
init | -4.009 |
actory | -3.852 |
shift | -3.837 |
itual | -3.768 |
Token | , |
Token ID | 11 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Dent | +0.388 |
Nadu | +0.371 |
Devi | +0.364 |
Equity | +0.339 |
Benefit | +0.338 |
Neg logit contributions | |
ipal | -0.363 |
init | -0.356 |
actory | -0.337 |
shift | -0.337 |
itual | -0.326 |
Token | and |
Token ID | 290 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Dent | +0.398 |
Nadu | +0.381 |
Devi | +0.373 |
Equity | +0.348 |
Benefit | +0.346 |
Neg logit contributions | |
ipal | -0.369 |
init | -0.362 |
shift | -0.344 |
actory | -0.343 |
ounge | -0.332 |
Token | two |
Token ID | 734 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Dent | +0.262 |
Nadu | +0.251 |
Devi | +0.245 |
Equity | +0.228 |
Benefit | +0.228 |
Neg logit contributions | |
ipal | -0.238 |
init | -0.234 |
shift | -0.222 |
actory | -0.221 |
ounge | -0.214 |
Token | payment |
Token ID | 6074 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ipal | +0.102 |
init | +0.100 |
shift | +0.094 |
actory | +0.094 |
ounge | +0.091 |
Neg logit contributions | |
Dent | -0.132 |
Nadu | -0.127 |
Devi | -0.124 |
Equity | -0.116 |
iaz | -0.116 |
Token | track |
Token ID | 2610 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ipal | +1.247 |
init | +1.221 |
shift | +1.159 |
actory | +1.141 |
ounge | +1.097 |
Neg logit contributions | |
Dent | -1.810 |
Nadu | -1.731 |
Devi | -1.690 |
Equity | -1.602 |
iaz | -1.601 |
Token | of |
Token ID | 286 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
Dent | +0.105 |
Nadu | +0.100 |
Devi | +0.099 |
iaz | +0.092 |
Benefit | +0.092 |
Neg logit contributions | |
ipal | -0.103 |
init | -0.101 |
actory | -0.095 |
shift | -0.095 |
itual | -0.093 |
Token | two |
Token ID | 734 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
Dent | +0.324 |
Nadu | +0.310 |
Devi | +0.303 |
Equity | +0.283 |
Benefit | +0.282 |
Neg logit contributions | |
ipal | -0.287 |
init | -0.282 |
shift | -0.267 |
actory | -0.266 |
ounge | -0.258 |
Token | sets |
Token ID | 5621 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
Dent | +0.011 |
Nadu | +0.011 |
Devi | +0.011 |
Equity | +0.010 |
Benefit | +0.010 |
Neg logit contributions | |
ipal | -0.010 |
init | -0.009 |
shift | -0.009 |
actory | -0.009 |
ounge | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
Dent | +0.453 |
Nadu | +0.435 |
Devi | +0.426 |
Equity | +0.398 |
Benefit | +0.398 |
Neg logit contributions | |
ipal | -0.362 |
init | -0.357 |
shift | -0.338 |
actory | -0.334 |
ounge | -0.323 |
Token | invent |
Token ID | 8067 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
Dent | +0.651 |
Nadu | +0.627 |
Devi | +0.614 |
Equity | +0.578 |
Benefit | +0.576 |
Neg logit contributions | |
ipal | -0.449 |
init | -0.440 |
shift | -0.413 |
actory | -0.412 |
ounge | -0.396 |
Token | ories |
Token ID | 1749 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Dent | +1.319 |
Nadu | +1.191 |
Devi | +1.149 |
iaz | +0.917 |
Equity | +0.911 |
Neg logit contributions | |
ipal | -5.278 |
init | -5.232 |
shift | -5.072 |
actory | -5.037 |
itual | -5.004 |
Token | , |
Token ID | 11 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
ipal | +0.161 |
init | +0.159 |
shift | +0.150 |
actory | +0.149 |
ounge | +0.145 |
Neg logit contributions | |
Dent | -0.189 |
Nadu | -0.181 |
Devi | -0.177 |
Equity | -0.166 |
Benefit | -0.165 |
Token | two |
Token ID | 734 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
Dent | +0.340 |
Nadu | +0.325 |
Devi | +0.318 |
Equity | +0.296 |
Benefit | +0.295 |
Neg logit contributions | |
ipal | -0.319 |
init | -0.314 |
shift | -0.298 |
actory | -0.297 |
ounge | -0.288 |
Token | product |
Token ID | 1720 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
Dent | +0.057 |
Nadu | +0.055 |
Devi | +0.054 |
Equity | +0.050 |
Benefit | +0.050 |
Neg logit contributions | |
ipal | -0.045 |
init | -0.044 |
shift | -0.042 |
actory | -0.041 |
ounge | -0.040 |
Token | catalog |
Token ID | 18388 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
ipal | +0.381 |
init | +0.376 |
shift | +0.353 |
actory | +0.351 |
ounge | +0.339 |
Neg logit contributions | |
Dent | -0.522 |
Nadu | -0.501 |
Devi | -0.491 |
Equity | -0.460 |
Benefit | -0.459 |
Token | Greenland |
Token ID | 30155 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Dent | +0.636 |
Nadu | +0.609 |
Devi | +0.596 |
Equity | +0.555 |
Benefit | +0.554 |
Neg logit contributions | |
ipal | -0.588 |
init | -0.578 |
shift | -0.547 |
actory | -0.546 |
ounge | -0.530 |
Token | � |
Token ID | 447 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Dent | +0.269 |
Nadu | +0.258 |
Devi | +0.251 |
Equity | +0.231 |
Benefit | +0.231 |
Neg logit contributions | |
ipal | -0.283 |
init | -0.279 |
shift | -0.266 |
actory | -0.265 |
ounge | -0.259 |
Token | � |
Token ID | 247 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ipal | +0.204 |
init | +0.200 |
actory | +0.190 |
shift | +0.187 |
ounge | +0.181 |
Neg logit contributions | |
Dent | -0.224 |
Nadu | -0.214 |
Devi | -0.211 |
Equity | -0.196 |
Benefit | -0.194 |
Token | s |
Token ID | 82 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
Dent | +0.201 |
Nadu | +0.190 |
Devi | +0.189 |
Equity | +0.173 |
iaz | +0.171 |
Neg logit contributions | |
init | -0.219 |
ipal | -0.218 |
shift | -0.208 |
actory | -0.205 |
itual | -0.198 |
Token | ice |
Token ID | 4771 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
ipal | +0.043 |
init | +0.042 |
shift | +0.040 |
actory | +0.040 |
ounge | +0.038 |
Neg logit contributions | |
Dent | -0.051 |
Nadu | -0.049 |
Devi | -0.048 |
Equity | -0.045 |
Benefit | -0.045 |
Token | sheet |
Token ID | 9629 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
Dent | +0.383 |
Nadu | +0.362 |
Devi | +0.351 |
Equity | +0.321 |
Benefit | +0.320 |
Neg logit contributions | |
ipal | -0.554 |
init | -0.546 |
shift | -0.523 |
actory | -0.522 |
ounge | -0.509 |
Token | to |
Token ID | 284 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
Dent | +3.001 |
Nadu | +2.955 |
Devi | +2.814 |
Benefit | +2.560 |
Equity | +2.555 |
Neg logit contributions | |
ipal | -3.619 |
init | -3.529 |
actory | -3.409 |
shift | -3.349 |
itual | -3.331 |
Token | start |
Token ID | 923 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ipal | +0.056 |
init | +0.055 |
shift | +0.053 |
actory | +0.052 |
ounge | +0.050 |
Neg logit contributions | |
Dent | -0.068 |
Nadu | -0.065 |
Devi | -0.064 |
Equity | -0.060 |
Benefit | -0.059 |
Token | losing |
Token ID | 6078 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Dent | +0.224 |
Nadu | +0.215 |
Devi | +0.210 |
Equity | +0.196 |
Benefit | +0.196 |
Neg logit contributions | |
ipal | -0.195 |
init | -0.192 |
shift | -0.181 |
actory | -0.181 |
ounge | -0.175 |
Token | more |
Token ID | 517 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ipal | +0.702 |
init | +0.691 |
shift | +0.650 |
actory | +0.645 |
ounge | +0.616 |
Neg logit contributions | |
Dent | -0.969 |
Nadu | -0.933 |
Devi | -0.913 |
Equity | -0.862 |
iaz | -0.860 |
Token | ice |
Token ID | 4771 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
ipal | +0.069 |
init | +0.068 |
shift | +0.064 |
actory | +0.064 |
ounge | +0.061 |
Neg logit contributions | |
Dent | -0.098 |
Nadu | -0.095 |
Devi | -0.093 |
Equity | -0.087 |
Benefit | -0.087 |
Token | ice |
Token ID | 4771 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Dent | +0.856 |
Nadu | +0.820 |
Devi | +0.803 |
Equity | +0.752 |
Benefit | +0.749 |
Neg logit contributions | |
ipal | -0.725 |
init | -0.712 |
shift | -0.672 |
actory | -0.671 |
ounge | -0.649 |
Token | from |
Token ID | 422 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
Dent | +0.284 |
Nadu | +0.271 |
Devi | +0.266 |
Equity | +0.250 |
iaz | +0.249 |
Neg logit contributions | |
ipal | -0.233 |
init | -0.230 |
shift | -0.217 |
actory | -0.216 |
itual | -0.208 |
Token | the |
Token ID | 262 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Dent | +0.386 |
Nadu | +0.369 |
Devi | +0.360 |
Equity | +0.336 |
Benefit | +0.335 |
Neg logit contributions | |
ipal | -0.371 |
init | -0.365 |
shift | -0.346 |
actory | -0.345 |
ounge | -0.334 |
Token | central |
Token ID | 4318 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ipal | +0.204 |
init | +0.203 |
shift | +0.191 |
actory | +0.190 |
ounge | +0.182 |
Neg logit contributions | |
Dent | -0.253 |
Nadu | -0.242 |
Devi | -0.237 |
Equity | -0.224 |
iaz | -0.223 |
Token | ice |
Token ID | 4771 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
ipal | +1.103 |
init | +1.097 |
shift | +1.038 |
actory | +1.024 |
ounge | +0.986 |
Neg logit contributions | |
Dent | -1.349 |
Nadu | -1.289 |
Devi | -1.264 |
Equity | -1.186 |
iaz | -1.186 |
Token | sheet |
Token ID | 9629 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
Dent | +0.272 |
Nadu | +0.252 |
Devi | +0.244 |
Equity | +0.218 |
Benefit | +0.215 |
Neg logit contributions | |
ipal | -0.559 |
init | -0.556 |
shift | -0.536 |
actory | -0.531 |
ounge | -0.519 |
Token | ; |
Token ID | 26 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
Dent | +3.354 |
Nadu | +3.214 |
Devi | +3.146 |
Benefit | +2.903 |
Equity | +2.892 |
Neg logit contributions | |
ipal | -3.257 |
init | -3.174 |
actory | -3.031 |
shift | -3.010 |
ounge | -2.960 |
Token | but |
Token ID | 475 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
ipal | +0.368 |
init | +0.364 |
shift | +0.345 |
actory | +0.342 |
itual | +0.330 |
Neg logit contributions | |
Dent | -0.401 |
Nadu | -0.383 |
Devi | -0.374 |
iaz | -0.352 |
Equity | -0.352 |
Token | even |
Token ID | 772 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
Dent | +0.386 |
Nadu | +0.369 |
Devi | +0.361 |
Equity | +0.338 |
iaz | +0.336 |
Neg logit contributions | |
ipal | -0.359 |
init | -0.354 |
shift | -0.336 |
actory | -0.334 |
itual | -0.322 |
Token | in |
Token ID | 287 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ipal | +0.049 |
init | +0.048 |
shift | +0.045 |
actory | +0.045 |
itual | +0.043 |
Neg logit contributions | |
Dent | -0.055 |
Nadu | -0.052 |
Devi | -0.051 |
iaz | -0.048 |
Equity | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
ipal | +0.088 |
init | +0.087 |
shift | +0.082 |
actory | +0.082 |
itual | +0.079 |
Neg logit contributions | |
Dent | -0.089 |
Nadu | -0.085 |
Devi | -0.083 |
Equity | -0.078 |
iaz | -0.077 |
Token | refused |
Token ID | 6520 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Dent | +0.083 |
Nadu | +0.080 |
Devi | +0.079 |
Equity | +0.074 |
iaz | +0.074 |
Neg logit contributions | |
ipal | -0.064 |
init | -0.063 |
shift | -0.059 |
actory | -0.059 |
ounge | -0.057 |
Token | one |
Token ID | 530 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ipal | +0.149 |
init | +0.147 |
shift | +0.140 |
actory | +0.139 |
itual | +0.135 |
Neg logit contributions | |
Dent | -0.144 |
Nadu | -0.139 |
Devi | -0.136 |
iaz | -0.125 |
Equity | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Dent | +0.341 |
Nadu | +0.327 |
Devi | +0.320 |
Equity | +0.299 |
Benefit | +0.298 |
Neg logit contributions | |
ipal | -0.295 |
init | -0.290 |
shift | -0.274 |
actory | -0.273 |
ounge | -0.264 |
Token | From |
Token ID | 3574 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Dent | +0.140 |
Nadu | +0.137 |
Devi | +0.132 |
iaz | +0.124 |
Benefit | +0.120 |
Neg logit contributions | |
ipal | -0.165 |
init | -0.164 |
shift | -0.156 |
actory | -0.154 |
itual | -0.150 |
Token | Ed |
Token ID | 1717 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
Dent | +0.790 |
Nadu | +0.760 |
Devi | +0.742 |
Equity | +0.686 |
iaz | +0.686 |
Neg logit contributions | |
ipal | -0.790 |
init | -0.781 |
shift | -0.742 |
actory | -0.738 |
ounge | -0.713 |
Token | Koch |
Token ID | 17009 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
ipal | +0.766 |
init | +0.762 |
shift | +0.719 |
actory | +0.715 |
itual | +0.691 |
Neg logit contributions | |
Dent | -0.684 |
Nadu | -0.660 |
Devi | -0.644 |
Equity | -0.592 |
Benefit | -0.589 |
Token | on |
Token ID | 319 |
Feature activation | +2.84e-03 |
Pos logit contributions | |
Dent | +3.326 |
Nadu | +3.158 |
Devi | +3.080 |
Equity | +2.887 |
iaz | +2.874 |
Neg logit contributions | |
ipal | -3.226 |
init | -3.178 |
actory | -3.024 |
shift | -3.011 |
ounge | -2.950 |
Token | down |
Token ID | 866 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
ipal | +0.002 |
init | +0.002 |
shift | +0.002 |
actory | +0.002 |
ounge | +0.002 |
Neg logit contributions | |
Dent | -0.002 |
Nadu | -0.002 |
Devi | -0.002 |
Equity | -0.002 |
Benefit | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
Dent | +0.501 |
Nadu | +0.479 |
Devi | +0.465 |
Equity | +0.436 |
Benefit | +0.434 |
Neg logit contributions | |
ipal | -0.477 |
init | -0.468 |
actory | -0.445 |
shift | -0.441 |
ounge | -0.433 |
Token | every |
Token ID | 790 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
Dent | +0.047 |
Nadu | +0.045 |
Devi | +0.044 |
iaz | +0.041 |
Equity | +0.041 |
Neg logit contributions | |
ipal | -0.047 |
init | -0.047 |
shift | -0.044 |
actory | -0.044 |
itual | -0.043 |
Token | mayor |
Token ID | 9591 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
ipal | +0.530 |
init | +0.522 |
shift | +0.498 |
actory | +0.491 |
ounge | +0.471 |
Neg logit contributions | |
Dent | -0.596 |
Nadu | -0.577 |
Devi | -0.563 |
Equity | -0.522 |
Benefit | -0.520 |
Token | the |
Token ID | 262 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
Dent | +0.114 |
Nadu | +0.110 |
Devi | +0.107 |
Equity | +0.099 |
iaz | +0.098 |
Neg logit contributions | |
ipal | -0.127 |
init | -0.125 |
shift | -0.119 |
actory | -0.119 |
ounge | -0.116 |
Token | new |
Token ID | 649 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Dent | +0.030 |
Nadu | +0.029 |
Devi | +0.029 |
iaz | +0.026 |
Equity | +0.026 |
Neg logit contributions | |
ipal | -0.030 |
init | -0.030 |
shift | -0.028 |
actory | -0.028 |
ounge | -0.027 |
Token | search |
Token ID | 2989 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ipal | +0.805 |
init | +0.800 |
shift | +0.756 |
actory | +0.747 |
ounge | +0.731 |
Neg logit contributions | |
Dent | -0.842 |
Nadu | -0.810 |
Devi | -0.792 |
iaz | -0.731 |
Benefit | -0.728 |
Token | deal |
Token ID | 1730 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Dent | +1.948 |
Nadu | +1.870 |
Devi | +1.828 |
Equity | +1.729 |
Benefit | +1.721 |
Neg logit contributions | |
ipal | -1.625 |
init | -1.586 |
actory | -1.506 |
shift | -1.501 |
itual | -1.454 |
Token | with |
Token ID | 351 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
Dent | +0.893 |
Nadu | +0.856 |
Devi | +0.840 |
Equity | +0.784 |
Benefit | +0.780 |
Neg logit contributions | |
ipal | -0.760 |
init | -0.750 |
shift | -0.709 |
actory | -0.705 |
ounge | -0.683 |
Token | Google |
Token ID | 3012 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
Dent | +0.005 |
Nadu | +0.005 |
Devi | +0.004 |
iaz | +0.004 |
Equity | +0.004 |
Neg logit contributions | |
ipal | -0.005 |
init | -0.005 |
shift | -0.005 |
actory | -0.005 |
ounge | -0.004 |
Token | aren |
Token ID | 3588 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Dent | +3.451 |
Nadu | +3.308 |
Devi | +3.217 |
Equity | +3.028 |
Benefit | +3.028 |
Neg logit contributions | |
ipal | -3.130 |
init | -3.057 |
actory | -2.900 |
shift | -2.895 |
itual | -2.810 |
Token | 't |
Token ID | 470 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
init | +0.243 |
ipal | +0.239 |
shift | +0.221 |
actory | +0.215 |
itual | +0.198 |
Neg logit contributions | |
Dent | -0.575 |
Nadu | -0.558 |
Devi | -0.553 |
Equity | -0.521 |
iaz | -0.518 |
Token | yet |
Token ID | 1865 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
ipal | +0.099 |
init | +0.098 |
actory | +0.093 |
shift | +0.092 |
ounge | +0.089 |
Neg logit contributions | |
Dent | -0.122 |
Nadu | -0.117 |
Devi | -0.115 |
iaz | -0.108 |
Equity | -0.107 |
Token | clear |
Token ID | 1598 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ipal | +0.164 |
init | +0.162 |
actory | +0.154 |
shift | +0.152 |
ounge | +0.147 |
Neg logit contributions | |
Dent | -0.219 |
Nadu | -0.211 |
Devi | -0.206 |
Benefit | -0.194 |
Equity | -0.194 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ipal | +0.218 |
init | +0.214 |
shift | +0.202 |
actory | +0.202 |
ounge | +0.196 |
Neg logit contributions | |
Dent | -0.247 |
Nadu | -0.237 |
Devi | -0.232 |
Equity | -0.217 |
Benefit | -0.216 |
Token | a |
Token ID | 257 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
Dent | +0.724 |
Nadu | +0.691 |
Devi | +0.676 |
Equity | +0.627 |
Benefit | +0.624 |
Neg logit contributions | |
ipal | -0.747 |
init | -0.735 |
shift | -0.699 |
actory | -0.695 |
ounge | -0.675 |
Token | loophole |
Token ID | 35723 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Dent | +0.502 |
Nadu | +0.482 |
Devi | +0.472 |
Equity | +0.442 |
iaz | +0.440 |
Neg logit contributions | |
ipal | -0.400 |
init | -0.392 |
shift | -0.372 |
actory | -0.369 |
ounge | -0.356 |
Token | that |
Token ID | 326 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
Dent | +1.404 |
Nadu | +1.344 |
Devi | +1.314 |
Equity | +1.225 |
Benefit | +1.221 |
Neg logit contributions | |
ipal | -1.312 |
init | -1.290 |
shift | -1.222 |
actory | -1.220 |
ounge | -1.183 |
Token | could |
Token ID | 714 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Dent | +0.408 |
Nadu | +0.390 |
Devi | +0.382 |
Equity | +0.357 |
iaz | +0.356 |
Neg logit contributions | |
ipal | -0.359 |
init | -0.355 |
shift | -0.337 |
actory | -0.334 |
ounge | -0.323 |
Token | guarantee |
Token ID | 9149 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
Dent | +0.412 |
Nadu | +0.395 |
Devi | +0.387 |
Equity | +0.362 |
iaz | +0.358 |
Neg logit contributions | |
ipal | -0.359 |
init | -0.354 |
shift | -0.337 |
actory | -0.334 |
ounge | -0.322 |
Token | fossil |
Token ID | 12584 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
Dent | +0.712 |
Nadu | +0.681 |
Devi | +0.666 |
Equity | +0.621 |
Benefit | +0.619 |
Neg logit contributions | |
ipal | -0.677 |
init | -0.665 |
shift | -0.631 |
actory | -0.629 |
ounge | -0.610 |
Token | fuel |
Token ID | 5252 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Dent | +3.231 |
Nadu | +3.134 |
Devi | +3.039 |
Benefit | +2.839 |
Equity | +2.823 |
Neg logit contributions | |
ipal | -3.248 |
init | -3.184 |
shift | -3.024 |
actory | -2.999 |
ounge | -2.954 |
Token | production |
Token ID | 3227 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
Dent | +2.011 |
Nadu | +1.942 |
Devi | +1.894 |
Equity | +1.781 |
Benefit | +1.780 |
Neg logit contributions | |
ipal | -1.537 |
init | -1.502 |
shift | -1.415 |
actory | -1.408 |
ounge | -1.367 |
Token | past |
Token ID | 1613 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Dent | +2.221 |
Nadu | +2.128 |
Devi | +2.079 |
Equity | +1.946 |
Benefit | +1.942 |
Neg logit contributions | |
ipal | -2.061 |
init | -2.021 |
shift | -1.913 |
actory | -1.909 |
ounge | -1.855 |
Token | 20 |
Token ID | 1160 |
Feature activation | -4.30e-03 |
Pos logit contributions | |
Dent | +1.154 |
Nadu | +1.099 |
Devi | +1.071 |
Equity | +0.987 |
iaz | +0.984 |
Neg logit contributions | |
ipal | -1.336 |
init | -1.315 |
actory | -1.254 |
shift | -1.254 |
ounge | -1.213 |
Token | 45 |
Token ID | 2231 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Dent | +0.004 |
Nadu | +0.004 |
Devi | +0.004 |
Equity | +0.004 |
Benefit | +0.004 |
Neg logit contributions | |
ipal | -0.003 |
init | -0.002 |
shift | -0.002 |
actory | -0.002 |
ounge | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ipal | +0.958 |
init | +0.944 |
actory | +0.877 |
shift | +0.877 |
ounge | +0.842 |
Neg logit contributions | |
Dent | -1.429 |
Nadu | -1.373 |
Devi | -1.350 |
Equity | -1.269 |
Benefit | -1.266 |
Token | , |
Token ID | 11 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ipal | +0.389 |
init | +0.383 |
shift | +0.362 |
actory | +0.360 |
ounge | +0.348 |
Neg logit contributions | |
Dent | -0.434 |
Nadu | -0.416 |
Devi | -0.407 |
Equity | -0.380 |
Benefit | -0.378 |
Token | then |
Token ID | 788 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
Dent | +0.199 |
Nadu | +0.190 |
Devi | +0.186 |
Equity | +0.174 |
Benefit | +0.173 |
Neg logit contributions | |
ipal | -0.189 |
init | -0.186 |
shift | -0.176 |
actory | -0.176 |
ounge | -0.171 |
Token | open |
Token ID | 1280 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
ipal | +0.411 |
init | +0.404 |
shift | +0.385 |
actory | +0.382 |
ounge | +0.369 |
Neg logit contributions | |
Dent | -0.456 |
Nadu | -0.438 |
Devi | -0.428 |
Equity | -0.400 |
iaz | -0.397 |
Token | the |
Token ID | 262 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ipal | +0.306 |
init | +0.301 |
shift | +0.287 |
actory | +0.285 |
ounge | +0.277 |
Neg logit contributions | |
Dent | -0.302 |
Nadu | -0.289 |
Devi | -0.282 |
Equity | -0.262 |
iaz | -0.261 |
Token | catalog |
Token ID | 18388 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
Dent | +0.146 |
Nadu | +0.139 |
Devi | +0.136 |
Equity | +0.125 |
iaz | +0.125 |
Neg logit contributions | |
ipal | -0.175 |
init | -0.172 |
shift | -0.164 |
actory | -0.164 |
ounge | -0.159 |
Token | like |
Token ID | 588 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
Dent | +3.289 |
Nadu | +3.121 |
Devi | +3.070 |
Benefit | +2.868 |
Equity | +2.849 |
Neg logit contributions | |
ipal | -3.165 |
init | -3.121 |
actory | -2.935 |
shift | -2.922 |
itual | -2.847 |
Token | you |
Token ID | 345 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Dent | +0.063 |
Nadu | +0.060 |
Devi | +0.058 |
Equity | +0.055 |
iaz | +0.054 |
Neg logit contributions | |
ipal | -0.061 |
init | -0.061 |
shift | -0.057 |
actory | -0.057 |
ounge | -0.055 |
Token | would |
Token ID | 561 |
Feature activation | +7.06e-03 |
Pos logit contributions | |
ipal | +0.101 |
init | +0.100 |
shift | +0.093 |
actory | +0.093 |
ounge | +0.089 |
Neg logit contributions | |
Dent | -0.152 |
Nadu | -0.146 |
Devi | -0.143 |
Equity | -0.135 |
Benefit | -0.135 |
Token | any |
Token ID | 597 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
ipal | +0.005 |
init | +0.005 |
shift | +0.005 |
actory | +0.005 |
ounge | +0.005 |
Neg logit contributions | |
Dent | -0.006 |
Nadu | -0.005 |
Devi | -0.005 |
Equity | -0.005 |
Benefit | -0.005 |
Token | ebook |
Token ID | 47179 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
ipal | +0.679 |
init | +0.670 |
shift | +0.642 |
actory | +0.639 |
ounge | +0.619 |
Neg logit contributions | |
Dent | -0.682 |
Nadu | -0.661 |
Devi | -0.639 |
iaz | -0.594 |
Equity | -0.594 |
Token | In |
Token ID | 818 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Dent | +0.275 |
Nadu | +0.264 |
Devi | +0.259 |
Equity | +0.243 |
Benefit | +0.242 |
Neg logit contributions | |
ipal | -0.207 |
init | -0.205 |
shift | -0.193 |
actory | -0.190 |
ounge | -0.184 |
Token | all |
Token ID | 477 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Dent | +0.193 |
Nadu | +0.185 |
Devi | +0.181 |
Equity | +0.169 |
iaz | +0.169 |
Neg logit contributions | |
ipal | -0.165 |
init | -0.163 |
shift | -0.154 |
actory | -0.153 |
ounge | -0.148 |
Token | , |
Token ID | 11 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Dent | +1.317 |
Nadu | +1.255 |
Devi | +1.228 |
Equity | +1.146 |
Benefit | +1.133 |
Neg logit contributions | |
ipal | -1.312 |
init | -1.285 |
shift | -1.223 |
actory | -1.220 |
ounge | -1.191 |
Token | the |
Token ID | 262 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
Dent | +0.330 |
Nadu | +0.316 |
Devi | +0.310 |
Equity | +0.288 |
Benefit | +0.288 |
Neg logit contributions | |
ipal | -0.308 |
init | -0.304 |
shift | -0.287 |
actory | -0.286 |
ounge | -0.277 |
Token | ice |
Token ID | 4771 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
Dent | +0.456 |
Nadu | +0.438 |
Devi | +0.428 |
Equity | +0.401 |
Benefit | +0.400 |
Neg logit contributions | |
ipal | -0.392 |
init | -0.386 |
shift | -0.365 |
actory | -0.363 |
ounge | -0.351 |
Token | sheet |
Token ID | 9629 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
Dent | +0.550 |
Nadu | +0.523 |
Devi | +0.513 |
Equity | +0.478 |
Benefit | +0.475 |
Neg logit contributions | |
ipal | -0.531 |
init | -0.524 |
shift | -0.498 |
actory | -0.494 |
ounge | -0.479 |
Token | contains |
Token ID | 4909 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Dent | +3.343 |
Nadu | +3.228 |
Devi | +3.122 |
Benefit | +2.900 |
Equity | +2.893 |
Neg logit contributions | |
ipal | -3.126 |
init | -3.048 |
actory | -2.916 |
shift | -2.873 |
ounge | -2.830 |
Token | enough |
Token ID | 1576 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
Dent | +1.076 |
Nadu | +1.034 |
Devi | +1.013 |
Equity | +0.951 |
Benefit | +0.948 |
Neg logit contributions | |
ipal | -0.826 |
init | -0.810 |
shift | -0.762 |
actory | -0.761 |
ounge | -0.735 |
Token | water |
Token ID | 1660 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
Dent | +0.322 |
Nadu | +0.309 |
Devi | +0.303 |
Equity | +0.285 |
Benefit | +0.284 |
Neg logit contributions | |
ipal | -0.240 |
init | -0.235 |
shift | -0.221 |
actory | -0.221 |
ounge | -0.213 |
Token | to |
Token ID | 284 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ipal | +0.438 |
init | +0.431 |
shift | +0.410 |
actory | +0.406 |
ounge | +0.394 |
Neg logit contributions | |
Dent | -0.450 |
Nadu | -0.430 |
Devi | -0.421 |
Equity | -0.392 |
Benefit | -0.391 |
Token | raise |
Token ID | 5298 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ipal | +0.105 |
init | +0.103 |
shift | +0.098 |
actory | +0.097 |
ounge | +0.094 |
Neg logit contributions | |
Dent | -0.115 |
Nadu | -0.110 |
Devi | -0.108 |
Equity | -0.101 |
iaz | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ipal | +0.092 |
init | +0.090 |
shift | +0.085 |
actory | +0.085 |
ounge | +0.083 |
Neg logit contributions | |
Dent | -0.105 |
Nadu | -0.101 |
Devi | -0.099 |
Equity | -0.092 |
Benefit | -0.092 |
Token | evolve |
Token ID | 18101 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
ipal | +0.173 |
init | +0.171 |
shift | +0.162 |
actory | +0.161 |
ounge | +0.156 |
Neg logit contributions | |
Dent | -0.183 |
Nadu | -0.175 |
Devi | -0.171 |
Equity | -0.159 |
iaz | -0.159 |
Token | to |
Token ID | 284 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
Dent | +0.570 |
Nadu | +0.546 |
Devi | +0.535 |
Equity | +0.501 |
Benefit | +0.499 |
Neg logit contributions | |
ipal | -0.485 |
init | -0.476 |
actory | -0.449 |
shift | -0.448 |
ounge | -0.435 |
Token | fill |
Token ID | 6070 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
ipal | +0.036 |
init | +0.035 |
shift | +0.034 |
actory | +0.034 |
ounge | +0.032 |
Neg logit contributions | |
Dent | -0.039 |
Nadu | -0.037 |
Devi | -0.036 |
Equity | -0.034 |
Benefit | -0.034 |
Token | ecological |
Token ID | 25047 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Dent | +0.638 |
Nadu | +0.610 |
Devi | +0.594 |
Equity | +0.554 |
Benefit | +0.551 |
Neg logit contributions | |
ipal | -0.634 |
init | -0.624 |
shift | -0.590 |
actory | -0.590 |
ounge | -0.574 |
Token | nic |
Token ID | 9200 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
ipal | +0.342 |
init | +0.338 |
shift | +0.326 |
actory | +0.325 |
ounge | +0.316 |
Neg logit contributions | |
Dent | -0.239 |
Nadu | -0.226 |
Devi | -0.222 |
iaz | -0.201 |
Benefit | -0.200 |
Token | hes |
Token ID | 956 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
Dent | +3.537 |
Nadu | +3.387 |
Devi | +3.321 |
iaz | +3.126 |
Equity | +3.119 |
Neg logit contributions | |
ipal | -2.880 |
init | -2.840 |
shift | -2.679 |
actory | -2.663 |
ounge | -2.586 |
Token | left |
Token ID | 1364 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ipal | +0.005 |
init | +0.005 |
shift | +0.004 |
actory | +0.004 |
ounge | +0.004 |
Neg logit contributions | |
Dent | -0.006 |
Nadu | -0.005 |
Devi | -0.005 |
Equity | -0.005 |
Benefit | -0.005 |
Token | vacant |
Token ID | 23957 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Dent | +0.913 |
Nadu | +0.874 |
Devi | +0.856 |
Equity | +0.800 |
Benefit | +0.797 |
Neg logit contributions | |
ipal | -0.843 |
init | -0.832 |
shift | -0.788 |
actory | -0.787 |
ounge | -0.758 |
Token | after |
Token ID | 706 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
Dent | +0.861 |
Nadu | +0.827 |
Devi | +0.810 |
Equity | +0.758 |
Benefit | +0.755 |
Neg logit contributions | |
ipal | -0.732 |
init | -0.720 |
shift | -0.679 |
actory | -0.679 |
ounge | -0.655 |
Token | the |
Token ID | 262 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ipal | +0.460 |
init | +0.453 |
shift | +0.429 |
actory | +0.429 |
ounge | +0.411 |
Neg logit contributions | |
Dent | -0.477 |
Nadu | -0.460 |
Devi | -0.452 |
Equity | -0.419 |
iaz | -0.418 |
Token | partnerships |
Token ID | 22867 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Dent | +0.336 |
Nadu | +0.324 |
Devi | +0.316 |
iaz | +0.293 |
Benefit | +0.292 |
Neg logit contributions | |
ipal | -0.315 |
init | -0.313 |
actory | -0.295 |
shift | -0.295 |
ounge | -0.287 |
Token | with |
Token ID | 351 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Dent | +1.022 |
Nadu | +0.981 |
Devi | +0.960 |
Equity | +0.894 |
Benefit | +0.892 |
Neg logit contributions | |
ipal | -0.883 |
init | -0.872 |
shift | -0.821 |
actory | -0.820 |
ounge | -0.796 |
Token | search |
Token ID | 2989 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
ipal | +0.171 |
init | +0.170 |
shift | +0.160 |
actory | +0.160 |
ounge | +0.154 |
Neg logit contributions | |
Dent | -0.199 |
Nadu | -0.192 |
Devi | -0.187 |
iaz | -0.175 |
Benefit | -0.174 |
Token | engines |
Token ID | 11874 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Dent | +2.479 |
Nadu | +2.371 |
Devi | +2.316 |
Equity | +2.190 |
Benefit | +2.174 |
Neg logit contributions | |
ipal | -2.190 |
init | -2.142 |
shift | -2.030 |
actory | -2.023 |
itual | -1.956 |
Token | like |
Token ID | 588 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Dent | +1.660 |
Nadu | +1.584 |
Devi | +1.548 |
Equity | +1.441 |
Benefit | +1.436 |
Neg logit contributions | |
ipal | -1.676 |
init | -1.647 |
shift | -1.564 |
actory | -1.562 |
ounge | -1.514 |
Token | Google |
Token ID | 3012 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
Dent | +0.123 |
Nadu | +0.121 |
Devi | +0.115 |
iaz | +0.106 |
ouri | +0.104 |
Neg logit contributions | |
ipal | -0.166 |
init | -0.165 |
shift | -0.158 |
actory | -0.156 |
ounge | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
Dent | +3.238 |
Nadu | +3.086 |
Devi | +3.014 |
Equity | +2.831 |
Benefit | +2.812 |
Neg logit contributions | |
ipal | -3.208 |
init | -3.153 |
shift | -3.001 |
actory | -2.997 |
itual | -2.899 |
Token | Yahoo |
Token ID | 16551 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
Dent | +0.033 |
Nadu | +0.032 |
Devi | +0.031 |
iaz | +0.029 |
Equity | +0.028 |
Neg logit contributions | |
ipal | -0.035 |
init | -0.035 |
shift | -0.033 |
actory | -0.033 |
ounge | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
Dent | +2.299 |
Nadu | +2.158 |
Devi | +2.098 |
Equity | +1.992 |
Benefit | +1.966 |
Neg logit contributions | |
ipal | -2.464 |
init | -2.373 |
actory | -2.292 |
shift | -2.289 |
itual | -2.234 |
Token | Duck |
Token ID | 21867 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Dent | +0.050 |
Nadu | +0.049 |
Devi | +0.047 |
iaz | +0.044 |
Equity | +0.043 |
Neg logit contributions | |
ipal | -0.055 |
init | -0.054 |
shift | -0.052 |
actory | -0.051 |
ounge | -0.050 |
Token | D |
Token ID | 35 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Dent | +0.798 |
Nadu | +0.758 |
Devi | +0.739 |
Equity | +0.690 |
Benefit | +0.686 |
Neg logit contributions | |
ipal | -0.826 |
init | -0.810 |
actory | -0.770 |
shift | -0.768 |
ounge | -0.749 |
Token | don |
Token ID | 836 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ipal | +0.523 |
init | +0.521 |
shift | +0.499 |
actory | +0.490 |
ounge | +0.474 |
Neg logit contributions | |
Dent | -0.602 |
Nadu | -0.578 |
Devi | -0.568 |
iaz | -0.529 |
Equity | -0.528 |
Token | 't |
Token ID | 470 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
init | +0.086 |
ipal | +0.086 |
shift | +0.079 |
actory | +0.076 |
itual | +0.071 |
Neg logit contributions | |
Dent | -0.204 |
Nadu | -0.198 |
Devi | -0.196 |
Equity | -0.185 |
iaz | -0.184 |
Token | know |
Token ID | 760 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
init | +0.311 |
ipal | +0.311 |
shift | +0.299 |
actory | +0.294 |
selector | +0.282 |
Neg logit contributions | |
Dent | -0.371 |
Nadu | -0.357 |
Devi | -0.350 |
Equity | -0.327 |
iaz | -0.325 |
Token | who |
Token ID | 508 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ipal | +0.127 |
init | +0.125 |
shift | +0.118 |
actory | +0.117 |
ounge | +0.114 |
Neg logit contributions | |
Dent | -0.145 |
Nadu | -0.142 |
Devi | -0.137 |
iaz | -0.129 |
Equity | -0.128 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ipal | +0.117 |
init | +0.115 |
actory | +0.107 |
shift | +0.107 |
ounge | +0.103 |
Neg logit contributions | |
Dent | -0.122 |
Nadu | -0.118 |
Devi | -0.115 |
iaz | -0.107 |
Equity | -0.106 |
Token | Koch |
Token ID | 17009 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
Dent | +0.120 |
Nadu | +0.116 |
Devi | +0.114 |
Equity | +0.106 |
Benefit | +0.106 |
Neg logit contributions | |
ipal | -0.103 |
init | -0.101 |
shift | -0.095 |
actory | -0.095 |
ounge | -0.092 |
Token | brothers |
Token ID | 9397 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Dent | +3.119 |
Nadu | +2.980 |
Devi | +2.881 |
Benefit | +2.736 |
Equity | +2.730 |
Neg logit contributions | |
ipal | -3.173 |
init | -3.125 |
shift | -2.992 |
actory | -2.955 |
ounge | -2.914 |
Token | are |
Token ID | 389 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
Dent | +0.675 |
Nadu | +0.642 |
Devi | +0.623 |
Equity | +0.578 |
Benefit | +0.576 |
Neg logit contributions | |
ipal | -0.830 |
init | -0.819 |
shift | -0.781 |
actory | -0.780 |
ounge | -0.760 |
Token | ." |
Token ID | 526 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
ipal | +0.032 |
init | +0.032 |
shift | +0.030 |
actory | +0.030 |
ounge | +0.029 |
Neg logit contributions | |
Dent | -0.035 |
Nadu | -0.034 |
Devi | -0.033 |
Equity | -0.031 |
Benefit | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Dent | +0.612 |
Nadu | +0.586 |
Devi | +0.572 |
Equity | +0.532 |
Benefit | +0.530 |
Neg logit contributions | |
ipal | -0.606 |
init | -0.596 |
shift | -0.566 |
actory | -0.564 |
ounge | -0.547 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Dent | +0.130 |
Nadu | +0.126 |
Devi | +0.123 |
Equity | +0.115 |
iaz | +0.115 |
Neg logit contributions | |
init | -0.099 |
ipal | -0.097 |
shift | -0.093 |
actory | -0.091 |
photo | -0.087 |
Token |
|
Token ID | 198 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
init | +0.292 |
ipal | +0.284 |
shift | +0.273 |
actory | +0.266 |
photo | +0.255 |
Neg logit contributions | |
Dent | -0.398 |
Nadu | -0.388 |
Devi | -0.379 |
iaz | -0.354 |
Equity | -0.353 |
Token | Ford |
Token ID | 37308 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ipal | +0.144 |
init | +0.142 |
shift | +0.133 |
actory | +0.133 |
ounge | +0.128 |
Neg logit contributions | |
Dent | -0.196 |
Nadu | -0.189 |
Devi | -0.185 |
Equity | -0.174 |
Benefit | -0.173 |
Token | , |
Token ID | 11 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
Dent | +0.721 |
Nadu | +0.687 |
Devi | +0.671 |
Equity | +0.622 |
Benefit | +0.619 |
Neg logit contributions | |
ipal | -0.788 |
init | -0.775 |
shift | -0.738 |
actory | -0.736 |
ounge | -0.716 |
Token | America |
Token ID | 2253 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Dent | +0.251 |
Nadu | +0.241 |
Devi | +0.235 |
iaz | +0.217 |
Equity | +0.217 |
Neg logit contributions | |
ipal | -0.250 |
init | -0.247 |
shift | -0.234 |
actory | -0.234 |
ounge | -0.226 |
Token | 's |
Token ID | 338 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
ipal | +0.226 |
init | +0.222 |
shift | +0.211 |
actory | +0.210 |
ounge | +0.205 |
Neg logit contributions | |
Dent | -0.211 |
Nadu | -0.201 |
Devi | -0.196 |
Equity | -0.182 |
Benefit | -0.182 |
Token | truck |
Token ID | 7779 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
ipal | +0.524 |
init | +0.518 |
actory | +0.487 |
shift | +0.485 |
ounge | +0.468 |
Neg logit contributions | |
Dent | -0.631 |
Nadu | -0.607 |
Devi | -0.596 |
iaz | -0.560 |
Equity | -0.554 |
Token | leader |
Token ID | 3554 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
ipal | +2.056 |
init | +2.033 |
actory | +1.921 |
shift | +1.915 |
ounge | +1.850 |
Neg logit contributions | |
Dent | -2.267 |
Nadu | -2.168 |
Devi | -2.128 |
Equity | -1.983 |
Benefit | -1.973 |
Token | , |
Token ID | 11 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ipal | +0.336 |
init | +0.331 |
shift | +0.313 |
actory | +0.312 |
ounge | +0.302 |
Neg logit contributions | |
Dent | -0.377 |
Nadu | -0.361 |
Devi | -0.353 |
Equity | -0.329 |
Benefit | -0.329 |
Token | today |
Token ID | 1909 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Dent | +0.244 |
Nadu | +0.233 |
Devi | +0.228 |
Equity | +0.212 |
Benefit | +0.212 |
Neg logit contributions | |
ipal | -0.227 |
init | -0.223 |
shift | -0.211 |
actory | -0.211 |
ounge | -0.204 |
Token | introduced |
Token ID | 5495 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ipal | +0.961 |
init | +0.953 |
shift | +0.897 |
actory | +0.896 |
ounge | +0.864 |
Neg logit contributions | |
Dent | -0.893 |
Nadu | -0.861 |
Devi | -0.829 |
Equity | -0.770 |
iaz | -0.770 |
Token | the |
Token ID | 262 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
Dent | +0.415 |
Nadu | +0.396 |
Devi | +0.386 |
Equity | +0.358 |
Benefit | +0.356 |
Neg logit contributions | |
ipal | -0.461 |
init | -0.454 |
shift | -0.432 |
actory | -0.431 |
ounge | -0.419 |
Token | � |
Token ID | 247 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Dent | +0.090 |
Nadu | +0.086 |
Devi | +0.084 |
Equity | +0.078 |
Benefit | +0.077 |
Neg logit contributions | |
ipal | -0.094 |
init | -0.093 |
actory | -0.088 |
shift | -0.088 |
ounge | -0.085 |
Token | s |
Token ID | 82 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
Dent | +0.190 |
Nadu | +0.181 |
Devi | +0.176 |
Equity | +0.163 |
Benefit | +0.162 |
Neg logit contributions | |
ipal | -0.221 |
init | -0.218 |
shift | -0.207 |
actory | -0.207 |
ounge | -0.201 |
Token | punches |
Token ID | 25495 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ipal | +0.021 |
init | +0.021 |
actory | +0.020 |
shift | +0.020 |
ounge | +0.019 |
Neg logit contributions | |
Dent | -0.024 |
Nadu | -0.023 |
Devi | -0.023 |
Equity | -0.021 |
Benefit | -0.021 |
Token | had |
Token ID | 550 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
Dent | +0.872 |
Nadu | +0.836 |
Devi | +0.818 |
Equity | +0.764 |
Benefit | +0.762 |
Neg logit contributions | |
ipal | -0.765 |
init | -0.751 |
shift | -0.710 |
actory | -0.708 |
ounge | -0.686 |
Token | blown |
Token ID | 16318 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Dent | +0.613 |
Nadu | +0.590 |
Devi | +0.576 |
Equity | +0.540 |
iaz | +0.537 |
Neg logit contributions | |
ipal | -0.546 |
init | -0.539 |
shift | -0.510 |
actory | -0.507 |
ounge | -0.490 |
Token | Brook |
Token ID | 7590 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ipal | +0.087 |
init | +0.087 |
shift | +0.082 |
actory | +0.082 |
ounge | +0.079 |
Neg logit contributions | |
Dent | -0.087 |
Nadu | -0.084 |
Devi | -0.082 |
Equity | -0.077 |
iaz | -0.076 |
Token | � |
Token ID | 447 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ipal | +2.368 |
init | +2.341 |
shift | +2.221 |
actory | +2.188 |
scrambled | +2.104 |
Neg logit contributions | |
Dent | -2.199 |
Nadu | -2.139 |
Devi | -2.073 |
Equity | -1.945 |
Benefit | -1.910 |
Token | � |
Token ID | 247 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
Dent | +0.137 |
Nadu | +0.132 |
Devi | +0.129 |
Equity | +0.120 |
Benefit | +0.120 |
Neg logit contributions | |
ipal | -0.136 |
init | -0.134 |
actory | -0.127 |
shift | -0.126 |
ounge | -0.122 |
Token | s |
Token ID | 82 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
Dent | +0.464 |
Nadu | +0.443 |
Devi | +0.433 |
Equity | +0.398 |
Benefit | +0.396 |
Neg logit contributions | |
ipal | -0.570 |
init | -0.563 |
shift | -0.535 |
actory | -0.535 |
ounge | -0.519 |
Token | eye |
Token ID | 4151 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
Dent | +0.026 |
Nadu | +0.025 |
Devi | +0.025 |
Equity | +0.023 |
iaz | +0.023 |
Neg logit contributions | |
ipal | -0.019 |
init | -0.019 |
shift | -0.018 |
actory | -0.018 |
ounge | -0.017 |
Token | up |
Token ID | 510 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
ipal | +0.698 |
init | +0.689 |
shift | +0.656 |
actory | +0.654 |
ounge | +0.635 |
Neg logit contributions | |
Dent | -0.630 |
Nadu | -0.601 |
Devi | -0.586 |
Equity | -0.543 |
Benefit | -0.540 |
Token | and |
Token ID | 290 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
ipal | +0.177 |
init | +0.173 |
shift | +0.164 |
actory | +0.163 |
ounge | +0.158 |
Neg logit contributions | |
Dent | -0.206 |
Nadu | -0.198 |
Devi | -0.193 |
Equity | -0.181 |
Benefit | -0.180 |
Token | stem |
Token ID | 10717 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
ipal | +0.057 |
init | +0.055 |
shift | +0.053 |
actory | +0.052 |
ounge | +0.051 |
Neg logit contributions | |
Dent | -0.066 |
Nadu | -0.064 |
Devi | -0.063 |
Equity | -0.059 |
iaz | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Dent | +0.430 |
Nadu | +0.411 |
Devi | +0.403 |
Equity | +0.377 |
Benefit | +0.376 |
Neg logit contributions | |
ipal | -0.367 |
init | -0.360 |
actory | -0.340 |
shift | -0.340 |
ounge | -0.329 |
Token | View |
Token ID | 3582 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
ipal | +0.344 |
init | +0.339 |
shift | +0.325 |
actory | +0.321 |
ounge | +0.313 |
Neg logit contributions | |
Dent | -0.290 |
Nadu | -0.279 |
Devi | -0.270 |
iaz | -0.251 |
Equity | -0.249 |
Token | Full |
Token ID | 6462 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ipal | +0.378 |
init | +0.373 |
actory | +0.355 |
shift | +0.355 |
ounge | +0.341 |
Neg logit contributions | |
Dent | -0.421 |
Nadu | -0.404 |
Devi | -0.394 |
Equity | -0.367 |
iaz | -0.366 |
Token | Caption |
Token ID | 11260 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
Dent | +0.084 |
Nadu | +0.081 |
Devi | +0.078 |
Equity | +0.072 |
Benefit | +0.072 |
Neg logit contributions | |
ipal | -0.101 |
init | -0.100 |
shift | -0.095 |
actory | -0.095 |
ounge | -0.092 |
Token | Adam |
Token ID | 7244 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ipal | +3.148 |
init | +3.072 |
shift | +2.897 |
actory | +2.872 |
photo | +2.751 |
Neg logit contributions | |
Dent | -4.453 |
Nadu | -4.413 |
Devi | -4.256 |
iaz | -4.126 |
merce | -4.033 |
Token | Glenn |
Token ID | 17551 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ipal | +0.882 |
init | +0.871 |
shift | +0.827 |
actory | +0.827 |
ounge | +0.801 |
Neg logit contributions | |
Dent | -0.737 |
Nadu | -0.708 |
Devi | -0.687 |
Equity | -0.636 |
Benefit | -0.631 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ipal | +0.905 |
init | +0.897 |
shift | +0.844 |
actory | +0.842 |
ounge | +0.817 |
Neg logit contributions | |
Dent | -0.935 |
Nadu | -0.898 |
Devi | -0.875 |
Equity | -0.816 |
Benefit | -0.813 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
init | +0.199 |
ipal | +0.195 |
shift | +0.187 |
actory | +0.182 |
photo | +0.176 |
Neg logit contributions | |
Dent | -0.260 |
Nadu | -0.252 |
Devi | -0.246 |
iaz | -0.230 |
Equity | -0.229 |
Token | C |
Token ID | 34 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ipal | +0.094 |
init | +0.092 |
actory | +0.086 |
shift | +0.086 |
ounge | +0.083 |
Neg logit contributions | |
Dent | -0.140 |
Nadu | -0.135 |
Devi | -0.132 |
Equity | -0.125 |
Benefit | -0.124 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Dent | +0.051 |
Nadu | +0.049 |
Devi | +0.048 |
iaz | +0.044 |
Equity | +0.044 |
Neg logit contributions | |
ipal | -0.049 |
init | -0.049 |
shift | -0.046 |
actory | -0.046 |
itual | -0.044 |
Token | doctor |
Token ID | 6253 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Dent | +0.102 |
Nadu | +0.098 |
Devi | +0.095 |
Equity | +0.089 |
iaz | +0.089 |
Neg logit contributions | |
ipal | -0.092 |
init | -0.091 |
shift | -0.086 |
actory | -0.086 |
ounge | -0.083 |
Token | of |
Token ID | 286 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Dent | +0.132 |
Nadu | +0.127 |
Devi | +0.124 |
Equity | +0.116 |
Benefit | +0.115 |
Neg logit contributions | |
ipal | -0.117 |
init | -0.115 |
shift | -0.108 |
actory | -0.108 |
ounge | -0.105 |
Token | Catholic |
Token ID | 7835 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ipal | +0.151 |
init | +0.149 |
actory | +0.140 |
shift | +0.140 |
ounge | +0.136 |
Neg logit contributions | |
Dent | -0.149 |
Nadu | -0.143 |
Devi | -0.139 |
iaz | -0.129 |
Benefit | -0.129 |
Token | truth |
Token ID | 3872 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
ipal | +0.114 |
init | +0.113 |
shift | +0.105 |
actory | +0.105 |
itual | +0.102 |
Neg logit contributions | |
Dent | -0.129 |
Nadu | -0.125 |
Devi | -0.122 |
iaz | -0.114 |
Benefit | -0.113 |
Token | ought |
Token ID | 10783 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Dent | +0.049 |
Nadu | +0.047 |
Devi | +0.046 |
Equity | +0.043 |
Benefit | +0.043 |
Neg logit contributions | |
ipal | -0.044 |
init | -0.043 |
shift | -0.041 |
actory | -0.041 |
ounge | -0.039 |
Token | not |
Token ID | 407 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ipal | +2.177 |
init | +2.146 |
shift | +2.033 |
actory | +2.030 |
ounge | +1.969 |
Neg logit contributions | |
Dent | -2.176 |
Nadu | -2.082 |
Devi | -2.032 |
Equity | -1.888 |
Benefit | -1.882 |
Token | only |
Token ID | 691 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Dent | +0.381 |
Nadu | +0.364 |
Devi | +0.353 |
Equity | +0.329 |
Benefit | +0.327 |
Neg logit contributions | |
ipal | -0.421 |
init | -0.412 |
shift | -0.392 |
actory | -0.392 |
ounge | -0.382 |
Token | to |
Token ID | 284 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Dent | +0.161 |
Nadu | +0.153 |
Devi | +0.150 |
Equity | +0.139 |
Benefit | +0.138 |
Neg logit contributions | |
ipal | -0.176 |
init | -0.172 |
shift | -0.164 |
actory | -0.164 |
ounge | -0.159 |
Token | teach |
Token ID | 4545 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
Dent | +0.133 |
Nadu | +0.128 |
Devi | +0.125 |
Equity | +0.117 |
iaz | +0.116 |
Neg logit contributions | |
ipal | -0.121 |
init | -0.120 |
shift | -0.113 |
actory | -0.113 |
ounge | -0.109 |
Token | the |
Token ID | 262 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
ipal | +0.504 |
init | +0.499 |
shift | +0.470 |
actory | +0.467 |
itual | +0.454 |
Neg logit contributions | |
Dent | -0.551 |
Nadu | -0.536 |
Devi | -0.517 |
iaz | -0.485 |
Equity | -0.481 |
Token | income |
Token ID | 3739 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
ipal | +0.013 |
init | +0.013 |
shift | +0.012 |
actory | +0.012 |
ounge | +0.012 |
Neg logit contributions | |
Dent | -0.017 |
Nadu | -0.016 |
Devi | -0.016 |
iaz | -0.015 |
Equity | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
ipal | +0.039 |
init | +0.039 |
shift | +0.036 |
actory | +0.036 |
ounge | +0.035 |
Neg logit contributions | |
Dent | -0.048 |
Nadu | -0.046 |
Devi | -0.045 |
Equity | -0.042 |
iaz | -0.042 |
Token | his |
Token ID | 465 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
ipal | +0.601 |
init | +0.593 |
shift | +0.560 |
actory | +0.560 |
ounge | +0.545 |
Neg logit contributions | |
Dent | -0.636 |
Nadu | -0.622 |
Devi | -0.604 |
iaz | -0.565 |
Equity | -0.556 |
Token | spouse |
Token ID | 16731 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
ipal | +0.392 |
init | +0.385 |
shift | +0.363 |
actory | +0.361 |
ounge | +0.352 |
Neg logit contributions | |
Dent | -0.460 |
Nadu | -0.448 |
Devi | -0.436 |
iaz | -0.409 |
Equity | -0.404 |
Token | , |
Token ID | 11 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
ipal | +0.287 |
init | +0.284 |
shift | +0.267 |
actory | +0.265 |
ounge | +0.259 |
Neg logit contributions | |
Dent | -0.316 |
Nadu | -0.304 |
Devi | -0.296 |
iaz | -0.277 |
Equity | -0.276 |
Token | according |
Token ID | 1864 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ipal | +0.341 |
init | +0.337 |
shift | +0.318 |
actory | +0.316 |
ounge | +0.309 |
Neg logit contributions | |
Dent | -0.371 |
Nadu | -0.360 |
Devi | -0.348 |
iaz | -0.328 |
Equity | -0.324 |
Token | to |
Token ID | 284 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
ipal | +1.902 |
init | +1.900 |
shift | +1.770 |
actory | +1.741 |
itual | +1.669 |
Neg logit contributions | |
Dent | -2.450 |
Nadu | -2.415 |
Devi | -2.349 |
iaz | -2.206 |
ouri | -2.185 |
Token | his |
Token ID | 465 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
ipal | +0.484 |
init | +0.475 |
shift | +0.449 |
actory | +0.449 |
ounge | +0.435 |
Neg logit contributions | |
Dent | -0.532 |
Nadu | -0.516 |
Devi | -0.500 |
iaz | -0.465 |
Equity | -0.463 |
Token | disclosure |
Token ID | 13019 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ipal | +0.327 |
init | +0.320 |
shift | +0.302 |
actory | +0.301 |
ounge | +0.293 |
Neg logit contributions | |
Dent | -0.388 |
Nadu | -0.376 |
Devi | -0.365 |
iaz | -0.341 |
Benefit | -0.338 |
Token | statement |
Token ID | 2643 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Dent | +0.282 |
Nadu | +0.272 |
Devi | +0.267 |
Equity | +0.252 |
Benefit | +0.251 |
Neg logit contributions | |
ipal | -0.173 |
init | -0.170 |
shift | -0.158 |
actory | -0.158 |
ounge | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ipal | +1.402 |
init | +1.384 |
shift | +1.299 |
actory | +1.297 |
ounge | +1.253 |
Neg logit contributions | |
Dent | -1.696 |
Nadu | -1.642 |
Devi | -1.588 |
Equity | -1.491 |
Benefit | -1.486 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ipal | +0.693 |
init | +0.678 |
shift | +0.641 |
actory | +0.634 |
ounge | +0.612 |
Neg logit contributions | |
Dent | -0.928 |
Nadu | -0.899 |
Devi | -0.877 |
iaz | -0.824 |
Benefit | -0.823 |
Token | though |
Token ID | 996 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
ipal | +0.112 |
init | +0.111 |
shift | +0.104 |
actory | +0.103 |
ounge | +0.100 |
Neg logit contributions | |
Dent | -0.134 |
Nadu | -0.129 |
Devi | -0.126 |
iaz | -0.118 |
Benefit | -0.118 |
Token | : |
Token ID | 25 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
ipal | +0.938 |
init | +0.916 |
shift | +0.857 |
actory | +0.854 |
ounge | +0.823 |
Neg logit contributions | |
Dent | -1.456 |
Nadu | -1.400 |
Devi | -1.375 |
Equity | -1.298 |
Benefit | -1.293 |
Token | Would |
Token ID | 10928 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
ipal | +0.534 |
init | +0.529 |
shift | +0.504 |
actory | +0.502 |
ounge | +0.489 |
Neg logit contributions | |
Dent | -0.459 |
Nadu | -0.446 |
Devi | -0.430 |
iaz | -0.402 |
ouri | -0.393 |
Token | Os |
Token ID | 8834 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
Dent | +0.277 |
Nadu | +0.267 |
Devi | +0.259 |
iaz | +0.242 |
Equity | +0.241 |
Neg logit contributions | |
ipal | -0.265 |
init | -0.261 |
shift | -0.247 |
actory | -0.246 |
ounge | -0.239 |
Token | we |
Token ID | 732 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
ipal | +0.404 |
init | +0.399 |
shift | +0.381 |
actory | +0.372 |
ounge | +0.358 |
Neg logit contributions | |
Dent | -0.609 |
Nadu | -0.583 |
Devi | -0.570 |
Equity | -0.537 |
Benefit | -0.534 |
Token | iler |
Token ID | 5329 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
ipal | +0.314 |
init | +0.313 |
actory | +0.292 |
shift | +0.285 |
ounge | +0.264 |
Neg logit contributions | |
Dent | -0.688 |
Nadu | -0.655 |
Devi | -0.646 |
Equity | -0.620 |
Benefit | -0.607 |
Token | , |
Token ID | 11 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
ipal | +0.626 |
init | +0.618 |
shift | +0.588 |
actory | +0.582 |
ounge | +0.564 |
Neg logit contributions | |
Dent | -0.732 |
Nadu | -0.706 |
Devi | -0.692 |
Equity | -0.643 |
iaz | -0.639 |
Token | as |
Token ID | 355 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
ipal | +0.061 |
init | +0.061 |
shift | +0.057 |
actory | +0.056 |
ounge | +0.055 |
Neg logit contributions | |
Dent | -0.069 |
Nadu | -0.067 |
Devi | -0.065 |
iaz | -0.061 |
Equity | -0.061 |
Token | unprepared |
Token ID | 45102 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ipal | +0.383 |
init | +0.381 |
shift | +0.361 |
actory | +0.360 |
ounge | +0.349 |
Neg logit contributions | |
Dent | -0.353 |
Nadu | -0.346 |
Devi | -0.333 |
iaz | -0.309 |
Equity | -0.309 |
Token | as |
Token ID | 355 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
Dent | +0.959 |
Nadu | +0.917 |
Devi | +0.897 |
Equity | +0.836 |
Benefit | +0.833 |
Neg logit contributions | |
ipal | -0.905 |
init | -0.890 |
shift | -0.843 |
actory | -0.841 |
ounge | -0.816 |
Token | The |
Token ID | 383 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ipal | +0.295 |
init | +0.292 |
shift | +0.277 |
actory | +0.273 |
ounge | +0.266 |
Neg logit contributions | |
Dent | -0.262 |
Nadu | -0.255 |
Devi | -0.245 |
iaz | -0.230 |
Equity | -0.227 |
Token | Company |
Token ID | 5834 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Dent | +0.168 |
Nadu | +0.161 |
Devi | +0.157 |
Equity | +0.145 |
iaz | +0.144 |
Neg logit contributions | |
ipal | -0.187 |
init | -0.184 |
shift | -0.175 |
actory | -0.175 |
ounge | -0.170 |
Token | of |
Token ID | 286 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ipal | +1.255 |
init | +1.248 |
shift | +1.182 |
actory | +1.163 |
ounge | +1.133 |
Neg logit contributions | |
Dent | -1.425 |
Nadu | -1.390 |
Devi | -1.340 |
Equity | -1.255 |
iaz | -1.253 |
Token | the |
Token ID | 262 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
ipal | +0.140 |
init | +0.138 |
shift | +0.132 |
actory | +0.131 |
ounge | +0.127 |
Neg logit contributions | |
Dent | -0.126 |
Nadu | -0.123 |
Devi | -0.118 |
iaz | -0.110 |
Equity | -0.109 |
Token | Ring |
Token ID | 12569 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ipal | +0.536 |
init | +0.532 |
shift | +0.513 |
actory | +0.508 |
ounge | +0.496 |
Neg logit contributions | |
Dent | -0.409 |
Nadu | -0.397 |
Devi | -0.377 |
Equity | -0.349 |
iaz | -0.348 |
Token | are |
Token ID | 389 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
ipal | +0.730 |
init | +0.723 |
shift | +0.686 |
actory | +0.678 |
ounge | +0.659 |
Neg logit contributions | |
Dent | -0.798 |
Nadu | -0.767 |
Devi | -0.747 |
Equity | -0.700 |
iaz | -0.694 |
Token | nine |
Token ID | 5193 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ipal | +0.416 |
init | +0.413 |
shift | +0.386 |
actory | +0.384 |
ounge | +0.368 |
Neg logit contributions | |
Dent | -0.558 |
Nadu | -0.538 |
Devi | -0.526 |
Equity | -0.496 |
iaz | -0.496 |
Token | in |
Token ID | 287 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
ipal | +1.022 |
init | +1.010 |
shift | +0.951 |
actory | +0.944 |
itual | +0.906 |
Neg logit contributions | |
Dent | -1.226 |
Nadu | -1.181 |
Devi | -1.151 |
Equity | -1.079 |
iaz | -1.079 |
Token | number |
Token ID | 1271 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
ipal | +0.281 |
init | +0.277 |
shift | +0.258 |
actory | +0.256 |
ounge | +0.246 |
Neg logit contributions | |
Dent | -0.442 |
Nadu | -0.427 |
Devi | -0.419 |
Equity | -0.394 |
iaz | -0.394 |
Token | : |
Token ID | 25 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ipal | +0.644 |
init | +0.634 |
shift | +0.598 |
actory | +0.596 |
ounge | +0.577 |
Neg logit contributions | |
Dent | -0.744 |
Nadu | -0.715 |
Devi | -0.699 |
Equity | -0.654 |
Benefit | -0.651 |
Token | Fro |
Token ID | 9734 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ipal | +0.936 |
init | +0.921 |
shift | +0.877 |
actory | +0.872 |
ounge | +0.845 |
Neg logit contributions | |
Dent | -0.791 |
Nadu | -0.764 |
Devi | -0.734 |
iaz | -0.685 |
Equity | -0.684 |
Token | regulating |
Token ID | 26379 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
ipal | +0.095 |
init | +0.093 |
shift | +0.088 |
actory | +0.087 |
ounge | +0.084 |
Neg logit contributions | |
Dent | -0.110 |
Nadu | -0.105 |
Devi | -0.103 |
Equity | -0.096 |
Benefit | -0.096 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
ipal | +0.137 |
init | +0.134 |
shift | +0.127 |
actory | +0.126 |
ounge | +0.121 |
Neg logit contributions | |
Dent | -0.150 |
Nadu | -0.143 |
Devi | -0.140 |
Equity | -0.131 |
Benefit | -0.131 |
Token | use |
Token ID | 779 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
ipal | +0.142 |
init | +0.139 |
shift | +0.131 |
actory | +0.130 |
ounge | +0.125 |
Neg logit contributions | |
Dent | -0.181 |
Nadu | -0.174 |
Devi | -0.170 |
Equity | -0.160 |
Benefit | -0.160 |
Token | of |
Token ID | 286 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Dent | +0.025 |
Nadu | +0.024 |
Devi | +0.024 |
Equity | +0.022 |
Benefit | +0.022 |
Neg logit contributions | |
ipal | -0.023 |
init | -0.023 |
actory | -0.022 |
shift | -0.022 |
ounge | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
ipal | +0.154 |
init | +0.151 |
shift | +0.143 |
actory | +0.142 |
itual | +0.137 |
Neg logit contributions | |
Dent | -0.174 |
Nadu | -0.167 |
Devi | -0.163 |
Benefit | -0.153 |
Equity | -0.153 |
Token | agricultural |
Token ID | 14240 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ipal | +0.275 |
init | +0.269 |
shift | +0.254 |
actory | +0.253 |
ounge | +0.243 |
Neg logit contributions | |
Dent | -0.308 |
Nadu | -0.296 |
Devi | -0.288 |
Benefit | -0.270 |
Equity | -0.270 |
Token | lands |
Token ID | 8604 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ipal | +0.813 |
init | +0.798 |
actory | +0.753 |
shift | +0.751 |
ounge | +0.715 |
Neg logit contributions | |
Dent | -1.052 |
Nadu | -1.008 |
Devi | -0.989 |
Equity | -0.928 |
Benefit | -0.927 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ipal | +0.096 |
init | +0.095 |
shift | +0.089 |
actory | +0.089 |
ounge | +0.086 |
Neg logit contributions | |
Dent | -0.109 |
Nadu | -0.104 |
Devi | -0.102 |
Equity | -0.095 |
Benefit | -0.095 |
Token | Such |
Token ID | 8013 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ipal | +0.210 |
init | +0.207 |
shift | +0.196 |
actory | +0.194 |
itual | +0.188 |
Neg logit contributions | |
Dent | -0.209 |
Nadu | -0.202 |
Devi | -0.196 |
iaz | -0.185 |
Equity | -0.182 |
Token | changes |
Token ID | 2458 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ipal | +0.213 |
init | +0.209 |
shift | +0.199 |
actory | +0.198 |
selector | +0.188 |
Neg logit contributions | |
Dent | -0.244 |
Nadu | -0.229 |
Devi | -0.227 |
iaz | -0.213 |
Benefit | -0.213 |
Token | could |
Token ID | 714 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
Dent | +0.115 |
Nadu | +0.110 |
Devi | +0.108 |
Equity | +0.101 |
Benefit | +0.101 |
Neg logit contributions | |
ipal | -0.100 |
init | -0.098 |
shift | -0.093 |
actory | -0.093 |
ounge | -0.089 |
Token | Turner |
Token ID | 15406 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
ipal | +0.368 |
init | +0.363 |
shift | +0.346 |
actory | +0.345 |
ounge | +0.336 |
Neg logit contributions | |
Dent | -0.305 |
Nadu | -0.290 |
Devi | -0.283 |
Equity | -0.261 |
Benefit | -0.260 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ipal | +0.299 |
init | +0.294 |
shift | +0.277 |
actory | +0.276 |
ounge | +0.267 |
Neg logit contributions | |
Dent | -0.349 |
Nadu | -0.336 |
Devi | -0.327 |
Equity | -0.307 |
iaz | -0.306 |
Token | but |
Token ID | 475 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
Dent | +0.147 |
Nadu | +0.141 |
Devi | +0.136 |
iaz | +0.129 |
Equity | +0.128 |
Neg logit contributions | |
ipal | -0.132 |
init | -0.130 |
shift | -0.122 |
actory | -0.121 |
ounge | -0.118 |
Token | it |
Token ID | 340 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Dent | +0.755 |
Nadu | +0.722 |
Devi | +0.699 |
iaz | +0.656 |
Equity | +0.653 |
Neg logit contributions | |
ipal | -0.721 |
init | -0.712 |
shift | -0.672 |
actory | -0.670 |
ounge | -0.645 |
Token | has |
Token ID | 468 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
Dent | +0.202 |
Nadu | +0.194 |
Devi | +0.189 |
Equity | +0.177 |
Benefit | +0.176 |
Neg logit contributions | |
ipal | -0.175 |
init | -0.172 |
shift | -0.162 |
actory | -0.161 |
ounge | -0.156 |
Token | inexpl |
Token ID | 33199 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Dent | +0.317 |
Nadu | +0.304 |
Devi | +0.295 |
Equity | +0.276 |
iaz | +0.275 |
Neg logit contributions | |
ipal | -0.308 |
init | -0.305 |
shift | -0.288 |
actory | -0.285 |
ounge | -0.277 |
Token | icably |
Token ID | 41685 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
init | +0.243 |
ipal | +0.241 |
actory | +0.222 |
shift | +0.219 |
itual | +0.212 |
Neg logit contributions | |
Dent | -0.379 |
Nadu | -0.368 |
Devi | -0.360 |
Benefit | -0.339 |
Equity | -0.338 |
Token | been |
Token ID | 587 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ipal | +0.416 |
init | +0.413 |
shift | +0.388 |
actory | +0.380 |
scrambled | +0.373 |
Neg logit contributions | |
Dent | -0.463 |
Nadu | -0.448 |
Devi | -0.432 |
Equity | -0.408 |
iaz | -0.406 |
Token | censored |
Token ID | 43847 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ipal | +0.148 |
init | +0.146 |
shift | +0.137 |
actory | +0.134 |
ounge | +0.130 |
Neg logit contributions | |
Dent | -0.235 |
Nadu | -0.227 |
Devi | -0.221 |
Benefit | -0.211 |
Equity | -0.210 |
Token | by |
Token ID | 416 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
Dent | +1.170 |
Nadu | +1.120 |
Devi | +1.096 |
Equity | +1.023 |
Benefit | +1.019 |
Neg logit contributions | |
ipal | -1.061 |
init | -1.042 |
shift | -0.987 |
actory | -0.985 |
ounge | -0.954 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Dent | +0.025 |
Nadu | +0.024 |
Devi | +0.024 |
iaz | +0.022 |
Benefit | +0.022 |
Neg logit contributions | |
ipal | -0.026 |
init | -0.026 |
shift | -0.025 |
actory | -0.024 |
ounge | -0.024 |
Token | of |
Token ID | 286 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
Dent | +0.407 |
Nadu | +0.389 |
Devi | +0.381 |
Equity | +0.355 |
Benefit | +0.354 |
Neg logit contributions | |
ipal | -0.362 |
init | -0.356 |
actory | -0.335 |
shift | -0.335 |
ounge | -0.325 |
Token | debris |
Token ID | 16468 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Dent | +0.061 |
Nadu | +0.058 |
Devi | +0.057 |
Equity | +0.053 |
Benefit | +0.052 |
Neg logit contributions | |
ipal | -0.064 |
init | -0.063 |
shift | -0.059 |
actory | -0.059 |
ounge | -0.058 |
Token | it |
Token ID | 340 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Dent | +0.079 |
Nadu | +0.076 |
Devi | +0.074 |
Equity | +0.070 |
iaz | +0.069 |
Neg logit contributions | |
ipal | -0.075 |
init | -0.074 |
shift | -0.071 |
actory | -0.070 |
ounge | -0.068 |
Token | takes |
Token ID | 2753 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
ipal | +0.107 |
init | +0.106 |
actory | +0.099 |
shift | +0.099 |
ounge | +0.095 |
Neg logit contributions | |
Dent | -0.135 |
Nadu | -0.131 |
Devi | -0.127 |
Equity | -0.121 |
Benefit | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
Dent | +0.578 |
Nadu | +0.552 |
Devi | +0.539 |
Equity | +0.501 |
Benefit | +0.499 |
Neg logit contributions | |
ipal | -0.599 |
init | -0.589 |
shift | -0.560 |
actory | -0.559 |
ounge | -0.542 |
Token | kill |
Token ID | 1494 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ipal | +0.044 |
init | +0.043 |
shift | +0.041 |
actory | +0.041 |
ounge | +0.038 |
Neg logit contributions | |
Dent | -0.065 |
Nadu | -0.063 |
Devi | -0.062 |
Equity | -0.058 |
iaz | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
ipal | +0.186 |
init | +0.184 |
shift | +0.176 |
actory | +0.175 |
ounge | +0.170 |
Neg logit contributions | |
Dent | -0.148 |
Nadu | -0.140 |
Devi | -0.137 |
Equity | -0.127 |
iaz | -0.126 |
Token | turtle |
Token ID | 28699 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
Dent | +0.039 |
Nadu | +0.038 |
Devi | +0.037 |
Equity | +0.035 |
Benefit | +0.034 |
Neg logit contributions | |
ipal | -0.036 |
init | -0.035 |
shift | -0.033 |
actory | -0.033 |
ounge | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Dent | +0.569 |
Nadu | +0.546 |
Devi | +0.534 |
Equity | +0.500 |
Benefit | +0.498 |
Neg logit contributions | |
ipal | -0.496 |
init | -0.487 |
shift | -0.460 |
actory | -0.460 |
ounge | -0.445 |
Token |
|
Token ID | 198 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Dent | +0.232 |
Nadu | +0.222 |
Devi | +0.217 |
Equity | +0.202 |
Benefit | +0.201 |
Neg logit contributions | |
ipal | -0.221 |
init | -0.217 |
shift | -0.206 |
actory | -0.206 |
ounge | -0.199 |
Token |
|
Token ID | 198 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
Dent | +0.228 |
Nadu | +0.222 |
Devi | +0.217 |
iaz | +0.202 |
Equity | +0.202 |
Neg logit contributions | |
init | -0.172 |
ipal | -0.169 |
shift | -0.161 |
actory | -0.157 |
photo | -0.150 |
Token | to |
Token ID | 284 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Dent | +0.945 |
Nadu | +0.895 |
Devi | +0.881 |
Equity | +0.817 |
Benefit | +0.810 |
Neg logit contributions | |
ipal | -0.996 |
init | -0.981 |
actory | -0.938 |
shift | -0.935 |
itual | -0.905 |
Token | ethics |
Token ID | 14458 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ipal | +0.253 |
init | +0.247 |
shift | +0.234 |
actory | +0.233 |
ounge | +0.226 |
Neg logit contributions | |
Dent | -0.297 |
Nadu | -0.285 |
Devi | -0.279 |
iaz | -0.260 |
Benefit | -0.260 |
Token | commissioner |
Token ID | 16248 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
ipal | +0.335 |
init | +0.330 |
shift | +0.314 |
actory | +0.314 |
ounge | +0.305 |
Neg logit contributions | |
Dent | -0.277 |
Nadu | -0.263 |
Devi | -0.257 |
Equity | -0.237 |
Benefit | -0.236 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Dent | +0.245 |
Nadu | +0.234 |
Devi | +0.229 |
Equity | +0.213 |
Benefit | +0.212 |
Neg logit contributions | |
ipal | -0.235 |
init | -0.231 |
shift | -0.219 |
actory | -0.219 |
itual | -0.212 |
Token | would |
Token ID | 561 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Dent | +0.097 |
Nadu | +0.093 |
Devi | +0.091 |
Equity | +0.085 |
Benefit | +0.085 |
Neg logit contributions | |
ipal | -0.080 |
init | -0.078 |
shift | -0.074 |
actory | -0.074 |
ounge | -0.071 |
Token | be |
Token ID | 307 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
Dent | +0.356 |
Nadu | +0.342 |
Devi | +0.335 |
Equity | +0.313 |
Benefit | +0.312 |
Neg logit contributions | |
ipal | -0.293 |
init | -0.289 |
shift | -0.273 |
actory | -0.272 |
ounge | -0.263 |
Token | affected |
Token ID | 5676 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
ipal | +0.032 |
init | +0.031 |
shift | +0.029 |
actory | +0.029 |
ounge | +0.028 |
Neg logit contributions | |
Dent | -0.040 |
Nadu | -0.039 |
Devi | -0.038 |
iaz | -0.036 |
Benefit | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
ipal | +0.420 |
init | +0.414 |
shift | +0.390 |
actory | +0.390 |
ounge | +0.377 |
Neg logit contributions | |
Dent | -0.489 |
Nadu | -0.469 |
Devi | -0.460 |
Equity | -0.430 |
Benefit | -0.428 |
Token |
|
Token ID | 198 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
Dent | +0.382 |
Nadu | +0.366 |
Devi | +0.357 |
iaz | +0.331 |
Equity | +0.330 |
Neg logit contributions | |
ipal | -0.405 |
init | -0.399 |
shift | -0.379 |
actory | -0.377 |
ounge | -0.367 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Dent | +0.054 |
Nadu | +0.053 |
Devi | +0.052 |
iaz | +0.048 |
Equity | +0.048 |
Neg logit contributions | |
init | -0.040 |
ipal | -0.040 |
shift | -0.038 |
actory | -0.037 |
photo | -0.035 |
Token | Par |
Token ID | 10044 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
Dent | +0.178 |
Nadu | +0.171 |
Devi | +0.168 |
Equity | +0.157 |
Benefit | +0.157 |
Neg logit contributions | |
ipal | -0.142 |
init | -0.140 |
shift | -0.132 |
actory | -0.131 |
ounge | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Dent | +0.595 |
Nadu | +0.571 |
Devi | +0.558 |
Equity | +0.522 |
Benefit | +0.520 |
Neg logit contributions | |
ipal | -0.502 |
init | -0.494 |
shift | -0.466 |
actory | -0.465 |
ounge | -0.450 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ipal | +0.080 |
init | +0.079 |
shift | +0.074 |
actory | +0.074 |
ounge | +0.072 |
Neg logit contributions | |
Dent | -0.092 |
Nadu | -0.089 |
Devi | -0.087 |
Equity | -0.081 |
Benefit | -0.081 |
Token | C |
Token ID | 34 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
ipal | +0.780 |
init | +0.771 |
shift | +0.724 |
actory | +0.718 |
ounge | +0.693 |
Neg logit contributions | |
Dent | -1.033 |
Nadu | -0.991 |
Devi | -0.972 |
Equity | -0.912 |
Benefit | -0.909 |
Token | ort |
Token ID | 419 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ipal | +0.358 |
init | +0.353 |
actory | +0.334 |
shift | +0.333 |
ounge | +0.324 |
Neg logit contributions | |
Dent | -0.345 |
Nadu | -0.329 |
Devi | -0.323 |
Equity | -0.298 |
Benefit | -0.296 |
Token | ic |
Token ID | 291 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ipal | +0.479 |
init | +0.470 |
shift | +0.443 |
actory | +0.442 |
ounge | +0.427 |
Neg logit contributions | |
Dent | -0.607 |
Nadu | -0.583 |
Devi | -0.571 |
Equity | -0.535 |
Benefit | -0.534 |
Token | otrop |
Token ID | 34248 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Dent | +0.967 |
Nadu | +0.915 |
Devi | +0.896 |
Equity | +0.816 |
Benefit | +0.814 |
Neg logit contributions | |
ipal | -1.372 |
init | -1.354 |
shift | -1.290 |
actory | -1.288 |
ounge | -1.259 |
Token | in |
Token ID | 259 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Dent | +1.567 |
Nadu | +1.502 |
Devi | +1.469 |
Equity | +1.369 |
Benefit | +1.361 |
Neg logit contributions | |
ipal | -1.490 |
init | -1.467 |
actory | -1.385 |
shift | -1.384 |
ounge | -1.339 |
Token | - |
Token ID | 12 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Dent | +0.466 |
Nadu | +0.447 |
Devi | +0.437 |
Equity | +0.409 |
Benefit | +0.407 |
Neg logit contributions | |
ipal | -0.402 |
init | -0.395 |
shift | -0.373 |
actory | -0.372 |
ounge | -0.360 |
Token | re |
Token ID | 260 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
Dent | +0.088 |
Nadu | +0.084 |
Devi | +0.083 |
Equity | +0.077 |
Benefit | +0.076 |
Neg logit contributions | |
ipal | -0.088 |
init | -0.087 |
shift | -0.083 |
actory | -0.082 |
itual | -0.079 |
Token | leasing |
Token ID | 48764 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Dent | +1.374 |
Nadu | +1.306 |
Devi | +1.281 |
iaz | +1.204 |
Equity | +1.203 |
Neg logit contributions | |
ipal | -1.213 |
init | -1.183 |
shift | -1.130 |
actory | -1.119 |
ounge | -1.102 |
Token | factor |
Token ID | 5766 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Dent | +0.810 |
Nadu | +0.775 |
Devi | +0.759 |
Equity | +0.710 |
Benefit | +0.707 |
Neg logit contributions | |
ipal | -0.697 |
init | -0.683 |
shift | -0.646 |
actory | -0.644 |
ounge | -0.624 |
Token | record |
Token ID | 1700 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ipal | +0.136 |
init | +0.133 |
shift | +0.124 |
actory | +0.123 |
ounge | +0.118 |
Neg logit contributions | |
Dent | -0.232 |
Nadu | -0.224 |
Devi | -0.219 |
Equity | -0.207 |
Benefit | -0.207 |
Token | with |
Token ID | 351 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
ipal | +1.003 |
init | +0.988 |
shift | +0.937 |
actory | +0.934 |
ounge | +0.907 |
Neg logit contributions | |
Dent | -0.998 |
Nadu | -0.957 |
Devi | -0.934 |
Equity | -0.870 |
Benefit | -0.866 |
Token | 18 |
Token ID | 1248 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ipal | +0.425 |
init | +0.418 |
actory | +0.392 |
shift | +0.391 |
ounge | +0.377 |
Neg logit contributions | |
Dent | -0.595 |
Nadu | -0.573 |
Devi | -0.563 |
Equity | -0.529 |
Benefit | -0.529 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ipal | +0.707 |
init | +0.696 |
actory | +0.656 |
shift | +0.655 |
ounge | +0.631 |
Neg logit contributions | |
Dent | -0.896 |
Nadu | -0.860 |
Devi | -0.842 |
Equity | -0.790 |
Benefit | -0.788 |
Token | 355 |
Token ID | 28567 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ipal | +0.139 |
init | +0.136 |
shift | +0.127 |
actory | +0.127 |
ounge | +0.122 |
Neg logit contributions | |
Dent | -0.200 |
Nadu | -0.193 |
Devi | -0.189 |
Equity | -0.178 |
Benefit | -0.177 |
Token | career |
Token ID | 3451 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ipal | +0.111 |
init | +0.109 |
actory | +0.102 |
shift | +0.102 |
ounge | +0.098 |
Neg logit contributions | |
Dent | -0.165 |
Nadu | -0.159 |
Devi | -0.156 |
Equity | -0.147 |
Benefit | -0.147 |
Token | yards |
Token ID | 5695 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
Dent | +0.172 |
Nadu | +0.165 |
Devi | +0.162 |
Equity | +0.152 |
Benefit | +0.152 |
Neg logit contributions | |
ipal | -0.120 |
init | -0.118 |
shift | -0.111 |
actory | -0.111 |
ounge | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
ipal | +0.660 |
init | +0.648 |
actory | +0.611 |
shift | +0.609 |
ounge | +0.588 |
Neg logit contributions | |
Dent | -0.778 |
Nadu | -0.747 |
Devi | -0.730 |
Equity | -0.688 |
Benefit | -0.684 |
Token |
|
Token ID | 198 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ipal | +0.315 |
init | +0.312 |
shift | +0.295 |
actory | +0.293 |
ounge | +0.284 |
Neg logit contributions | |
Dent | -0.340 |
Nadu | -0.329 |
Devi | -0.320 |
Equity | -0.299 |
iaz | -0.298 |
Token |
|
Token ID | 198 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
init | +0.192 |
ipal | +0.188 |
shift | +0.179 |
actory | +0.175 |
photo | +0.168 |
Neg logit contributions | |
Dent | -0.255 |
Nadu | -0.248 |
Devi | -0.242 |
Equity | -0.226 |
iaz | -0.226 |
Token | C |
Token ID | 34 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
ipal | +0.112 |
init | +0.111 |
shift | +0.104 |
actory | +0.103 |
ounge | +0.100 |
Neg logit contributions | |
Dent | -0.151 |
Nadu | -0.145 |
Devi | -0.143 |
Equity | -0.134 |
Benefit | -0.134 |
Token | 're |
Token ID | 821 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
ipal | +0.186 |
init | +0.185 |
shift | +0.175 |
actory | +0.175 |
ounge | +0.168 |
Neg logit contributions | |
Dent | -0.208 |
Nadu | -0.200 |
Devi | -0.196 |
iaz | -0.183 |
Equity | -0.183 |
Token | not |
Token ID | 407 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
ipal | +0.652 |
init | +0.650 |
shift | +0.605 |
actory | +0.603 |
ounge | +0.580 |
Neg logit contributions | |
Dent | -0.826 |
Nadu | -0.796 |
Devi | -0.775 |
iaz | -0.734 |
Benefit | -0.731 |
Token | ready |
Token ID | 3492 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Dent | +0.547 |
Nadu | +0.526 |
Devi | +0.514 |
iaz | +0.483 |
Benefit | +0.481 |
Neg logit contributions | |
ipal | -0.449 |
init | -0.444 |
shift | -0.417 |
actory | -0.417 |
ounge | -0.401 |
Token | to |
Token ID | 284 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
Dent | +1.292 |
Nadu | +1.230 |
Devi | +1.195 |
Equity | +1.113 |
Benefit | +1.105 |
Neg logit contributions | |
ipal | -1.470 |
init | -1.446 |
shift | -1.379 |
actory | -1.376 |
ounge | -1.343 |
Token | show |
Token ID | 905 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Dent | +0.054 |
Nadu | +0.052 |
Devi | +0.051 |
Equity | +0.047 |
iaz | +0.047 |
Neg logit contributions | |
ipal | -0.047 |
init | -0.047 |
actory | -0.044 |
shift | -0.044 |
ounge | -0.042 |
Token | you |
Token ID | 345 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ipal | +0.951 |
init | +0.939 |
shift | +0.892 |
actory | +0.888 |
ounge | +0.853 |
Neg logit contributions | |
Dent | -1.099 |
Nadu | -1.059 |
Devi | -1.029 |
iaz | -0.970 |
Benefit | -0.960 |
Token | what |
Token ID | 644 |
Feature activation | +8.54e-03 |
Pos logit contributions | |
Dent | +0.143 |
Nadu | +0.137 |
Devi | +0.133 |
iaz | +0.125 |
Benefit | +0.123 |
Neg logit contributions | |
ipal | -0.144 |
init | -0.143 |
shift | -0.136 |
actory | -0.135 |
ounge | -0.130 |
Token | we |
Token ID | 356 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
ipal | +0.007 |
init | +0.006 |
shift | +0.006 |
actory | +0.006 |
ounge | +0.006 |
Neg logit contributions | |
Dent | -0.006 |
Nadu | -0.006 |
Devi | -0.006 |
iaz | -0.005 |
Equity | -0.005 |
Token | 've |
Token ID | 1053 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ipal | +0.322 |
init | +0.318 |
actory | +0.303 |
shift | +0.299 |
ounge | +0.287 |
Neg logit contributions | |
Dent | -0.359 |
Nadu | -0.348 |
Devi | -0.339 |
iaz | -0.316 |
Equity | -0.315 |
Token | been |
Token ID | 587 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ipal | +0.324 |
init | +0.322 |
actory | +0.303 |
shift | +0.302 |
ounge | +0.291 |
Neg logit contributions | |
Dent | -0.330 |
Nadu | -0.318 |
Devi | -0.306 |
iaz | -0.288 |
Benefit | -0.287 |
Token | working |
Token ID | 1762 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ipal | +0.143 |
init | +0.142 |
shift | +0.133 |
actory | +0.133 |
ounge | +0.126 |
Neg logit contributions | |
Dent | -0.206 |
Nadu | -0.199 |
Devi | -0.193 |
iaz | -0.183 |
Equity | -0.183 |
Token | Jade |
Token ID | 23386 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Dent | +0.536 |
Nadu | +0.515 |
Devi | +0.504 |
Equity | +0.470 |
Benefit | +0.470 |
Neg logit contributions | |
ipal | -0.449 |
init | -0.442 |
shift | -0.418 |
actory | -0.416 |
ounge | -0.402 |
Token | Helm |
Token ID | 28351 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
ipal | +1.492 |
init | +1.480 |
shift | +1.424 |
actory | +1.411 |
ounge | +1.379 |
Neg logit contributions | |
Dent | -0.982 |
Nadu | -0.922 |
Devi | -0.892 |
Equity | -0.813 |
Benefit | -0.810 |
Token | 15 |
Token ID | 1315 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Dent | +2.966 |
Nadu | +2.820 |
Devi | +2.809 |
Equity | +2.649 |
Benefit | +2.644 |
Neg logit contributions | |
ipal | -2.031 |
init | -1.949 |
actory | -1.842 |
shift | -1.827 |
ounge | -1.795 |
Token | operation |
Token ID | 4905 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
ipal | +0.211 |
init | +0.208 |
shift | +0.196 |
actory | +0.196 |
ounge | +0.188 |
Neg logit contributions | |
Dent | -0.271 |
Nadu | -0.261 |
Devi | -0.255 |
Equity | -0.239 |
Benefit | -0.238 |
Token | across |
Token ID | 1973 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
ipal | +0.428 |
init | +0.424 |
shift | +0.402 |
actory | +0.399 |
ounge | +0.385 |
Neg logit contributions | |
Dent | -0.481 |
Nadu | -0.461 |
Devi | -0.450 |
Equity | -0.420 |
iaz | -0.418 |
Token | the |
Token ID | 262 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
Dent | +0.483 |
Nadu | +0.460 |
Devi | +0.449 |
Equity | +0.416 |
Benefit | +0.414 |
Neg logit contributions | |
ipal | -0.538 |
init | -0.529 |
shift | -0.503 |
actory | -0.502 |
ounge | -0.489 |
Token | southwest |
Token ID | 26283 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ipal | +0.029 |
init | +0.028 |
shift | +0.026 |
actory | +0.026 |
ounge | +0.025 |
Neg logit contributions | |
Dent | -0.036 |
Nadu | -0.035 |
Devi | -0.034 |
Equity | -0.032 |
Benefit | -0.032 |
Token | continue |
Token ID | 2555 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ipal | +1.316 |
init | +1.297 |
shift | +1.232 |
actory | +1.224 |
ounge | +1.184 |
Neg logit contributions | |
Dent | -1.458 |
Nadu | -1.401 |
Devi | -1.366 |
Benefit | -1.269 |
iaz | -1.268 |
Token | to |
Token ID | 284 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ipal | +0.223 |
init | +0.219 |
shift | +0.208 |
actory | +0.207 |
ounge | +0.201 |
Neg logit contributions | |
Dent | -0.223 |
Nadu | -0.213 |
Devi | -0.208 |
Equity | -0.193 |
Benefit | -0.193 |
Token | suggest |
Token ID | 1950 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ipal | +0.008 |
init | +0.008 |
shift | +0.008 |
actory | +0.008 |
ounge | +0.007 |
Neg logit contributions | |
Dent | -0.010 |
Nadu | -0.009 |
Devi | -0.009 |
Equity | -0.008 |
Benefit | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Dent | +0.081 |
Nadu | +0.078 |
Devi | +0.076 |
Equity | +0.071 |
Benefit | +0.070 |
Neg logit contributions | |
ipal | -0.077 |
init | -0.076 |
shift | -0.072 |
actory | -0.072 |
ounge | -0.069 |
Token | first |
Token ID | 717 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Dent | +0.373 |
Nadu | +0.361 |
Devi | +0.353 |
Equity | +0.331 |
Benefit | +0.330 |
Neg logit contributions | |
ipal | -0.280 |
init | -0.276 |
shift | -0.259 |
actory | -0.258 |
ounge | -0.249 |
Token | it |
Token ID | 340 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
Dent | +0.857 |
Nadu | +0.822 |
Devi | +0.800 |
Equity | +0.741 |
Benefit | +0.737 |
Neg logit contributions | |
ipal | -0.946 |
init | -0.935 |
shift | -0.889 |
actory | -0.888 |
ounge | -0.861 |
Token | blew |
Token ID | 17948 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
Dent | +0.504 |
Nadu | +0.484 |
Devi | +0.472 |
Equity | +0.444 |
Benefit | +0.441 |
Neg logit contributions | |
ipal | -0.453 |
init | -0.447 |
shift | -0.421 |
actory | -0.421 |
ounge | -0.407 |
Token | me |
Token ID | 502 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Dent | +0.023 |
Nadu | +0.022 |
Devi | +0.022 |
iaz | +0.021 |
Equity | +0.020 |
Neg logit contributions | |
ipal | -0.020 |
init | -0.020 |
shift | -0.019 |
actory | -0.019 |
ounge | -0.018 |
Token | away |
Token ID | 1497 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
Dent | +0.456 |
Nadu | +0.438 |
Devi | +0.429 |
Equity | +0.402 |
Benefit | +0.400 |
Neg logit contributions | |
ipal | -0.370 |
init | -0.364 |
shift | -0.343 |
actory | -0.342 |
ounge | -0.331 |
Token | ", |
Token ID | 1600 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ipal | +0.023 |
init | +0.023 |
shift | +0.022 |
actory | +0.022 |
ounge | +0.021 |
Neg logit contributions | |
Dent | -0.025 |
Nadu | -0.024 |
Devi | -0.024 |
Equity | -0.022 |
Benefit | -0.022 |
Token | Ms |
Token ID | 6997 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Dent | +2.130 |
Nadu | +2.002 |
Devi | +1.960 |
Equity | +1.815 |
Benefit | +1.811 |
Neg logit contributions | |
ipal | -2.347 |
init | -2.298 |
shift | -2.194 |
actory | -2.185 |
ounge | -2.130 |
Token | Al |
Token ID | 978 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
Dent | +0.358 |
Nadu | +0.341 |
Devi | +0.333 |
Equity | +0.309 |
Benefit | +0.308 |
Neg logit contributions | |
ipal | -0.377 |
init | -0.370 |
shift | -0.352 |
actory | -0.351 |
ounge | -0.342 |
Token | br |
Token ID | 1671 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Dent | +0.798 |
Nadu | +0.770 |
Devi | +0.757 |
Equity | +0.712 |
Benefit | +0.705 |
Neg logit contributions | |
ipal | -0.517 |
init | -0.510 |
shift | -0.478 |
actory | -0.469 |
ounge | -0.451 |
Token | itton |
Token ID | 47304 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
init | +0.509 |
ipal | +0.497 |
shift | +0.428 |
actory | +0.416 |
ounge | +0.400 |
Neg logit contributions | |
Dent | -2.158 |
Devi | -2.100 |
Nadu | -2.097 |
Equity | -2.007 |
Benefit | -1.992 |
Token | said |
Token ID | 531 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
ipal | +0.174 |
init | +0.171 |
shift | +0.161 |
actory | +0.160 |
ounge | +0.156 |
Neg logit contributions | |
Dent | -0.219 |
Nadu | -0.213 |
Devi | -0.206 |
Equity | -0.195 |
Benefit | -0.194 |
Token | was |
Token ID | 373 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
ipal | +0.284 |
init | +0.280 |
shift | +0.263 |
actory | +0.263 |
ounge | +0.253 |
Neg logit contributions | |
Dent | -0.333 |
Nadu | -0.320 |
Devi | -0.312 |
Equity | -0.295 |
Benefit | -0.293 |
Token | as |
Token ID | 355 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Dent | +0.221 |
Nadu | +0.210 |
Devi | +0.205 |
Equity | +0.192 |
Benefit | +0.190 |
Neg logit contributions | |
ipal | -0.232 |
init | -0.228 |
shift | -0.217 |
actory | -0.216 |
itual | -0.210 |
Token | if |
Token ID | 611 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ipal | +0.150 |
init | +0.147 |
actory | +0.139 |
shift | +0.139 |
itual | +0.133 |
Neg logit contributions | |
Dent | -0.171 |
Nadu | -0.164 |
Devi | -0.159 |
Equity | -0.150 |
Benefit | -0.149 |
Token | at |
Token ID | 379 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
Dent | +0.208 |
Nadu | +0.199 |
Devi | +0.193 |
Equity | +0.181 |
iaz | +0.180 |
Neg logit contributions | |
ipal | -0.212 |
init | -0.209 |
shift | -0.199 |
actory | -0.198 |
ounge | -0.191 |
Token | this |
Token ID | 428 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
Dent | +0.392 |
Nadu | +0.375 |
Devi | +0.367 |
Equity | +0.342 |
Benefit | +0.340 |
Neg logit contributions | |
ipal | -0.393 |
init | -0.388 |
shift | -0.367 |
actory | -0.367 |
ounge | -0.356 |
Token | moment |
Token ID | 2589 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
Dent | +0.036 |
Nadu | +0.034 |
Devi | +0.033 |
Equity | +0.030 |
Benefit | +0.030 |
Neg logit contributions | |
ipal | -0.055 |
init | -0.054 |
shift | -0.052 |
actory | -0.052 |
ounge | -0.050 |
Token | they |
Token ID | 484 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
Dent | +2.314 |
Nadu | +2.209 |
Devi | +2.158 |
Equity | +1.990 |
Benefit | +1.983 |
Neg logit contributions | |
ipal | -2.426 |
init | -2.386 |
shift | -2.263 |
actory | -2.259 |
ounge | -2.206 |
Token | shared |
Token ID | 4888 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
Dent | +0.445 |
Nadu | +0.426 |
Devi | +0.417 |
Equity | +0.391 |
Benefit | +0.389 |
Neg logit contributions | |
ipal | -0.379 |
init | -0.373 |
shift | -0.352 |
actory | -0.352 |
ounge | -0.340 |
Token | a |
Token ID | 257 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ipal | +0.052 |
init | +0.052 |
shift | +0.049 |
actory | +0.049 |
ounge | +0.048 |
Neg logit contributions | |
Dent | -0.044 |
Nadu | -0.042 |
Devi | -0.041 |
Equity | -0.038 |
Benefit | -0.037 |
Token | single |
Token ID | 2060 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Dent | +0.084 |
Nadu | +0.080 |
Devi | +0.078 |
Equity | +0.073 |
Benefit | +0.073 |
Neg logit contributions | |
ipal | -0.073 |
init | -0.072 |
shift | -0.068 |
actory | -0.068 |
ounge | -0.065 |
Token | awareness |
Token ID | 9359 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
ipal | +0.235 |
init | +0.231 |
shift | +0.219 |
actory | +0.219 |
ounge | +0.211 |
Neg logit contributions | |
Dent | -0.275 |
Nadu | -0.264 |
Devi | -0.258 |
Equity | -0.241 |
iaz | -0.241 |
Token | Title |
Token ID | 11851 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
Dent | +0.282 |
Nadu | +0.269 |
Devi | +0.263 |
Equity | +0.242 |
Benefit | +0.242 |
Neg logit contributions | |
ipal | -0.308 |
init | -0.303 |
shift | -0.289 |
actory | -0.287 |
ounge | -0.279 |
Token | VI |
Token ID | 13889 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Dent | +0.690 |
Nadu | +0.661 |
Devi | +0.647 |
Equity | +0.603 |
Benefit | +0.602 |
Neg logit contributions | |
ipal | -0.621 |
init | -0.611 |
shift | -0.578 |
actory | -0.576 |
ounge | -0.558 |
Token | of |
Token ID | 286 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
Dent | +0.861 |
Nadu | +0.825 |
Devi | +0.808 |
Equity | +0.756 |
Benefit | +0.753 |
Neg logit contributions | |
ipal | -0.743 |
init | -0.730 |
shift | -0.689 |
actory | -0.689 |
ounge | -0.667 |
Token | the |
Token ID | 262 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
Dent | +0.478 |
Nadu | +0.457 |
Devi | +0.446 |
Benefit | +0.413 |
Equity | +0.412 |
Neg logit contributions | |
ipal | -0.510 |
init | -0.502 |
shift | -0.478 |
actory | -0.475 |
ounge | -0.462 |
Token | Civil |
Token ID | 7511 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
Dent | +0.003 |
Nadu | +0.002 |
Devi | +0.002 |
Benefit | +0.002 |
iaz | +0.002 |
Neg logit contributions | |
ipal | -0.004 |
init | -0.004 |
shift | -0.004 |
actory | -0.004 |
itual | -0.004 |
Token | Rights |
Token ID | 6923 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
Dent | +0.503 |
Nadu | +0.479 |
Devi | +0.465 |
iaz | +0.419 |
ouri | +0.410 |
Neg logit contributions | |
ipal | -0.851 |
init | -0.837 |
actory | -0.798 |
shift | -0.797 |
itual | -0.779 |
Token | Act |
Token ID | 2191 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Dent | +1.441 |
Nadu | +1.335 |
Devi | +1.285 |
iaz | +1.115 |
Benefit | +1.112 |
Neg logit contributions | |
ipal | -3.440 |
init | -3.398 |
shift | -3.270 |
actory | -3.263 |
itual | -3.196 |
Token | of |
Token ID | 286 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
Dent | +1.735 |
Nadu | +1.658 |
Devi | +1.624 |
Equity | +1.524 |
Benefit | +1.510 |
Neg logit contributions | |
ipal | -1.600 |
init | -1.562 |
actory | -1.492 |
shift | -1.486 |
ounge | -1.435 |
Token | 1964 |
Token ID | 17575 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Dent | +0.659 |
Nadu | +0.633 |
Devi | +0.618 |
iaz | +0.559 |
ouri | +0.558 |
Neg logit contributions | |
init | -0.767 |
ipal | -0.766 |
actory | -0.730 |
shift | -0.725 |
ounge | -0.709 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Dent | +1.793 |
Nadu | +1.720 |
Devi | +1.680 |
Equity | +1.570 |
Benefit | +1.562 |
Neg logit contributions | |
ipal | -1.660 |
init | -1.627 |
actory | -1.550 |
shift | -1.547 |
ounge | -1.500 |
Token | It |
Token ID | 632 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Dent | +0.186 |
Nadu | +0.178 |
Devi | +0.173 |
iaz | +0.161 |
Equity | +0.157 |
Neg logit contributions | |
ipal | -0.228 |
init | -0.225 |
shift | -0.216 |
actory | -0.214 |
itual | -0.208 |
Token | available |
Token ID | 1695 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Dent | +0.566 |
Nadu | +0.542 |
Devi | +0.531 |
Equity | +0.496 |
Benefit | +0.494 |
Neg logit contributions | |
ipal | -0.498 |
init | -0.491 |
shift | -0.464 |
actory | -0.464 |
ounge | -0.446 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Dent | +0.835 |
Nadu | +0.799 |
Devi | +0.781 |
Equity | +0.728 |
Benefit | +0.726 |
Neg logit contributions | |
ipal | -0.784 |
init | -0.771 |
shift | -0.731 |
actory | -0.729 |
ounge | -0.707 |
Token |
|
Token ID | 198 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
Dent | +0.093 |
Nadu | +0.089 |
Devi | +0.087 |
iaz | +0.081 |
Equity | +0.080 |
Neg logit contributions | |
ipal | -0.091 |
init | -0.090 |
shift | -0.085 |
actory | -0.085 |
ounge | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
init | +0.050 |
ipal | +0.049 |
shift | +0.047 |
actory | +0.046 |
photo | +0.044 |
Neg logit contributions | |
Dent | -0.067 |
Nadu | -0.065 |
Devi | -0.064 |
Equity | -0.060 |
iaz | -0.059 |
Token | B |
Token ID | 33 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Dent | +0.100 |
Nadu | +0.096 |
Devi | +0.094 |
Equity | +0.088 |
Benefit | +0.087 |
Neg logit contributions | |
ipal | -0.078 |
init | -0.077 |
shift | -0.072 |
actory | -0.072 |
ounge | -0.070 |
Token | ast |
Token ID | 459 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
ipal | +0.450 |
init | +0.444 |
shift | +0.422 |
actory | +0.422 |
ounge | +0.410 |
Neg logit contributions | |
Dent | -0.402 |
Nadu | -0.383 |
Devi | -0.373 |
Equity | -0.345 |
Benefit | -0.344 |
Token | ian |
Token ID | 666 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Dent | +2.077 |
Nadu | +1.982 |
Devi | +1.938 |
Equity | +1.798 |
Benefit | +1.789 |
Neg logit contributions | |
ipal | -2.157 |
init | -2.124 |
shift | -2.014 |
actory | -2.013 |
ounge | -1.953 |
Token | said |
Token ID | 531 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
Dent | +0.266 |
Nadu | +0.255 |
Devi | +0.249 |
Equity | +0.232 |
Benefit | +0.232 |
Neg logit contributions | |
ipal | -0.243 |
init | -0.240 |
shift | -0.226 |
actory | -0.225 |
ounge | -0.219 |
Token | he |
Token ID | 339 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Dent | +0.038 |
Nadu | +0.036 |
Devi | +0.035 |
iaz | +0.033 |
Equity | +0.033 |
Neg logit contributions | |
ipal | -0.039 |
init | -0.039 |
actory | -0.037 |
shift | -0.037 |
ounge | -0.036 |
Token | found |
Token ID | 1043 |
Feature activation | +4.70e-04 |
Pos logit contributions | |
ipal | +0.175 |
init | +0.173 |
actory | +0.162 |
shift | +0.162 |
ounge | +0.156 |
Neg logit contributions | |
Dent | -0.210 |
Nadu | -0.202 |
Devi | -0.197 |
Benefit | -0.185 |
Equity | -0.185 |
Token | it |
Token ID | 340 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
ipal | +0.000 |
init | +0.000 |
actory | +0.000 |
shift | +0.000 |
ounge | +0.000 |
Neg logit contributions | |
Dent | -0.000 |
Nadu | -0.000 |
Devi | -0.000 |
iaz | -0.000 |
Benefit | -0.000 |
Token | he |
Token ID | 339 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
Dent | +0.801 |
Nadu | +0.767 |
Devi | +0.749 |
Equity | +0.699 |
Benefit | +0.696 |
Neg logit contributions | |
ipal | -0.753 |
init | -0.740 |
shift | -0.701 |
actory | -0.700 |
ounge | -0.678 |
Token | fell |
Token ID | 3214 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Dent | +0.530 |
Nadu | +0.510 |
Devi | +0.498 |
Equity | +0.468 |
Benefit | +0.467 |
Neg logit contributions | |
ipal | -0.429 |
init | -0.421 |
shift | -0.396 |
actory | -0.396 |
ounge | -0.383 |
Token | down |
Token ID | 866 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Dent | +0.088 |
Nadu | +0.084 |
Devi | +0.082 |
Equity | +0.078 |
Benefit | +0.077 |
Neg logit contributions | |
ipal | -0.075 |
init | -0.074 |
shift | -0.070 |
actory | -0.069 |
ounge | -0.067 |
Token | on |
Token ID | 319 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Dent | +0.291 |
Nadu | +0.279 |
Devi | +0.273 |
Equity | +0.256 |
Benefit | +0.255 |
Neg logit contributions | |
ipal | -0.250 |
init | -0.246 |
shift | -0.232 |
actory | -0.231 |
ounge | -0.224 |
Token | his |
Token ID | 465 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
Dent | +0.136 |
Nadu | +0.130 |
Devi | +0.127 |
Equity | +0.118 |
Benefit | +0.118 |
Neg logit contributions | |
ipal | -0.135 |
init | -0.133 |
shift | -0.126 |
actory | -0.126 |
ounge | -0.122 |
Token | knees |
Token ID | 14475 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Dent | +0.703 |
Nadu | +0.673 |
Devi | +0.658 |
Equity | +0.613 |
Benefit | +0.611 |
Neg logit contributions | |
ipal | -0.664 |
init | -0.653 |
shift | -0.619 |
actory | -0.618 |
ounge | -0.599 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Dent | +2.270 |
Nadu | +2.159 |
Devi | +2.124 |
Equity | +1.953 |
Benefit | +1.953 |
Neg logit contributions | |
ipal | -2.201 |
init | -2.166 |
actory | -2.064 |
shift | -2.053 |
ounge | -2.004 |
Token | � |
Token ID | 564 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
Dent | +0.100 |
Nadu | +0.096 |
Devi | +0.093 |
iaz | +0.087 |
Equity | +0.087 |
Neg logit contributions | |
ipal | -0.112 |
init | -0.111 |
shift | -0.106 |
actory | -0.105 |
ounge | -0.102 |
Token | � |
Token ID | 250 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Dent | +0.003 |
Nadu | +0.003 |
Devi | +0.003 |
iaz | +0.003 |
Equity | +0.003 |
Neg logit contributions | |
ipal | -0.002 |
init | -0.002 |
actory | -0.001 |
shift | -0.001 |
itual | -0.001 |
Token | For |
Token ID | 1890 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ipal | +0.150 |
init | +0.149 |
shift | +0.141 |
actory | +0.138 |
ounge | +0.133 |
Neg logit contributions | |
Dent | -0.197 |
Nadu | -0.190 |
Devi | -0.186 |
Equity | -0.175 |
Benefit | -0.174 |
Token | give |
Token ID | 26535 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Dent | +0.194 |
Nadu | +0.185 |
Devi | +0.181 |
Equity | +0.169 |
Benefit | +0.167 |
Neg logit contributions | |
ipal | -0.192 |
init | -0.188 |
shift | -0.179 |
actory | -0.178 |
ounge | -0.172 |