Token | , |
Token ID | 11 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
bys | +0.501 |
dx | +0.418 |
Interstitial | +0.404 |
oho | +0.397 |
ttes | +0.390 |
Neg logit contributions | |
Dill | -0.394 |
rimp | -0.381 |
Rivals | -0.379 |
Switch | -0.366 |
rans | -0.363 |
Token | vital |
Token ID | 9204 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
bys | +0.368 |
dx | +0.313 |
Interstitial | +0.303 |
oho | +0.300 |
ttes | +0.294 |
Neg logit contributions | |
Dill | -0.231 |
rimp | -0.222 |
Rivals | -0.221 |
Switch | -0.212 |
rans | -0.210 |
Token | sources |
Token ID | 4237 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
Dill | +0.263 |
Rivals | +0.252 |
rimp | +0.251 |
Switch | +0.243 |
rans | +0.240 |
Neg logit contributions | |
bys | -0.387 |
dx | -0.328 |
Interstitial | -0.317 |
oho | -0.312 |
ttes | -0.307 |
Token | of |
Token ID | 286 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Dill | +0.977 |
rimp | +0.942 |
Rivals | +0.939 |
replace | +0.913 |
Switch | +0.912 |
Neg logit contributions | |
bys | -1.314 |
dx | -1.121 |
Interstitial | -1.084 |
oho | -1.066 |
ttes | -1.029 |
Token | web |
Token ID | 3992 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
bys | +0.311 |
dx | +0.265 |
Interstitial | +0.257 |
oho | +0.254 |
ttes | +0.249 |
Neg logit contributions | |
Dill | -0.191 |
rimp | -0.183 |
Rivals | -0.182 |
Switch | -0.175 |
rans | -0.174 |
Token | traffic |
Token ID | 4979 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
bys | +0.321 |
dx | +0.271 |
Interstitial | +0.260 |
oho | +0.256 |
ttes | +0.252 |
Neg logit contributions | |
Dill | -0.251 |
rimp | -0.242 |
Rivals | -0.240 |
rans | -0.234 |
Switch | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
bys | +4.192 |
dx | +3.527 |
Interstitial | +3.396 |
oho | +3.383 |
ttes | +3.317 |
Neg logit contributions | |
Dill | -2.843 |
rimp | -2.773 |
Rivals | -2.727 |
Switch | -2.615 |
rans | -2.608 |
Token | In |
Token ID | 554 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
bys | +0.589 |
dx | +0.490 |
Interstitial | +0.471 |
oho | +0.466 |
ttes | +0.456 |
Neg logit contributions | |
Dill | -0.486 |
rimp | -0.472 |
Rivals | -0.468 |
Switch | -0.452 |
rans | -0.449 |
Token | August |
Token ID | 2932 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
bys | +0.070 |
dx | +0.060 |
Interstitial | +0.059 |
oho | +0.058 |
ttes | +0.057 |
Neg logit contributions | |
Dill | -0.041 |
Rivals | -0.039 |
rimp | -0.039 |
Switch | -0.038 |
Ames | -0.037 |
Token | of |
Token ID | 286 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
Dill | +0.355 |
Rivals | +0.341 |
rimp | +0.337 |
Switch | +0.328 |
Ames | +0.324 |
Neg logit contributions | |
bys | -0.520 |
dx | -0.442 |
Interstitial | -0.428 |
oho | -0.420 |
ttes | -0.411 |
Token | last |
Token ID | 938 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
bys | +0.158 |
dx | +0.136 |
Interstitial | +0.133 |
oho | +0.130 |
ttes | +0.128 |
Neg logit contributions | |
Dill | -0.085 |
Rivals | -0.081 |
rimp | -0.080 |
Switch | -0.078 |
Ames | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Dill | +0.489 |
Rivals | +0.467 |
rimp | +0.466 |
Switch | +0.455 |
rans | +0.454 |
Neg logit contributions | |
bys | -0.691 |
dx | -0.579 |
Interstitial | -0.568 |
oho | -0.549 |
ttes | -0.540 |
Token | and |
Token ID | 290 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
bys | +0.377 |
dx | +0.318 |
Interstitial | +0.308 |
oho | +0.304 |
ttes | +0.299 |
Neg logit contributions | |
Dill | -0.255 |
Rivals | -0.244 |
rimp | -0.242 |
Switch | -0.236 |
rans | -0.233 |
Token | as |
Token ID | 355 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
bys | +0.163 |
dx | +0.138 |
Interstitial | +0.134 |
oho | +0.131 |
ttes | +0.129 |
Neg logit contributions | |
Dill | -0.107 |
Rivals | -0.102 |
rimp | -0.102 |
Switch | -0.099 |
replace | -0.097 |
Token | I |
Token ID | 314 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
bys | +0.646 |
dx | +0.550 |
Interstitial | +0.533 |
oho | +0.526 |
ttes | +0.517 |
Neg logit contributions | |
Dill | -0.402 |
rimp | -0.386 |
Rivals | -0.384 |
Switch | -0.369 |
rans | -0.366 |
Token | am |
Token ID | 716 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Dill | +0.016 |
rimp | +0.015 |
Rivals | +0.015 |
replace | +0.015 |
Switch | +0.015 |
Neg logit contributions | |
bys | -0.023 |
dx | -0.019 |
Interstitial | -0.019 |
oho | -0.018 |
ttes | -0.018 |
Token | apt |
Token ID | 15409 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
bys | +0.262 |
dx | +0.223 |
Interstitial | +0.216 |
oho | +0.214 |
ttes | +0.210 |
Neg logit contributions | |
Dill | -0.158 |
rimp | -0.152 |
Rivals | -0.150 |
Switch | -0.145 |
rans | -0.144 |
Token | to |
Token ID | 284 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
bys | +3.421 |
dx | +2.780 |
Interstitial | +2.686 |
oho | +2.639 |
ttes | +2.579 |
Neg logit contributions | |
Dill | -3.226 |
rimp | -3.131 |
Rivals | -3.115 |
Switch | -3.000 |
Marsh | -2.974 |
Token | do |
Token ID | 466 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
bys | +0.176 |
dx | +0.152 |
Interstitial | +0.148 |
oho | +0.145 |
ttes | +0.142 |
Neg logit contributions | |
Dill | -0.087 |
rimp | -0.084 |
Rivals | -0.082 |
replace | -0.080 |
Switch | -0.079 |
Token | when |
Token ID | 618 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
Dill | +0.389 |
rimp | +0.370 |
Rivals | +0.368 |
Switch | +0.360 |
replace | +0.356 |
Neg logit contributions | |
bys | -0.550 |
dx | -0.462 |
Interstitial | -0.447 |
oho | -0.439 |
ttes | -0.428 |
Token | I |
Token ID | 314 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
Dill | +0.783 |
Rivals | +0.745 |
rimp | +0.740 |
Switch | +0.717 |
rans | +0.708 |
Neg logit contributions | |
bys | -1.253 |
dx | -1.065 |
Interstitial | -1.035 |
oho | -1.023 |
ttes | -0.998 |
Token | have |
Token ID | 423 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
bys | +0.196 |
dx | +0.168 |
Interstitial | +0.163 |
oho | +0.159 |
ttes | +0.156 |
Neg logit contributions | |
Dill | -0.110 |
rimp | -0.107 |
Rivals | -0.105 |
Switch | -0.102 |
replace | -0.101 |
Token | 30 |
Token ID | 1542 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
bys | +0.215 |
dx | +0.183 |
Interstitial | +0.180 |
oho | +0.175 |
ttes | +0.171 |
Neg logit contributions | |
Dill | -0.133 |
Rivals | -0.127 |
rimp | -0.124 |
Switch | -0.123 |
Ames | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
Dill | +0.248 |
rimp | +0.237 |
Rivals | +0.235 |
Switch | +0.229 |
rans | +0.227 |
Neg logit contributions | |
bys | -0.323 |
dx | -0.270 |
Interstitial | -0.264 |
oho | -0.258 |
ttes | -0.253 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Dill | +0.019 |
rimp | +0.019 |
Rivals | +0.018 |
Switch | +0.018 |
rans | +0.018 |
Neg logit contributions | |
bys | -0.029 |
dx | -0.024 |
Interstitial | -0.023 |
oho | -0.023 |
ttes | -0.023 |
Token | its |
Token ID | 663 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Dill | +0.131 |
Rivals | +0.126 |
rimp | +0.124 |
Switch | +0.121 |
replace | +0.119 |
Neg logit contributions | |
bys | -0.211 |
dx | -0.180 |
Interstitial | -0.174 |
oho | -0.173 |
ttes | -0.168 |
Token | web |
Token ID | 3992 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Dill | +0.337 |
Rivals | +0.326 |
rimp | +0.323 |
Switch | +0.315 |
transgender | +0.310 |
Neg logit contributions | |
bys | -0.485 |
dx | -0.411 |
Interstitial | -0.396 |
oho | -0.390 |
ttes | -0.383 |
Token | traffic |
Token ID | 4979 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
bys | +0.529 |
dx | +0.448 |
Interstitial | +0.431 |
oho | +0.422 |
ttes | +0.417 |
Neg logit contributions | |
Dill | -0.382 |
rimp | -0.369 |
Rivals | -0.369 |
rans | -0.356 |
Switch | -0.355 |
Token | jumped |
Token ID | 11687 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
bys | +3.674 |
dx | +3.058 |
Interstitial | +2.931 |
oho | +2.897 |
ttes | +2.838 |
Neg logit contributions | |
Dill | -2.989 |
rimp | -2.921 |
Rivals | -2.881 |
rans | -2.776 |
Switch | -2.773 |
Token | to |
Token ID | 284 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
Dill | +0.479 |
Rivals | +0.457 |
rimp | +0.453 |
Switch | +0.442 |
replace | +0.437 |
Neg logit contributions | |
bys | -0.675 |
dx | -0.573 |
Interstitial | -0.565 |
oho | -0.555 |
ttes | -0.542 |
Token | about |
Token ID | 546 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Dill | +0.061 |
Rivals | +0.059 |
rimp | +0.058 |
Switch | +0.057 |
replace | +0.056 |
Neg logit contributions | |
bys | -0.106 |
dx | -0.090 |
Interstitial | -0.089 |
oho | -0.087 |
ttes | -0.085 |
Token | 16 |
Token ID | 1467 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
Dill | +0.236 |
Rivals | +0.227 |
rimp | +0.222 |
Switch | +0.220 |
rans | +0.214 |
Neg logit contributions | |
bys | -0.381 |
dx | -0.324 |
Interstitial | -0.317 |
oho | -0.311 |
ttes | -0.304 |
Token | million |
Token ID | 1510 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Dill | +0.125 |
rimp | +0.121 |
Rivals | +0.120 |
Switch | +0.116 |
rans | +0.116 |
Neg logit contributions | |
bys | -0.209 |
dx | -0.178 |
Interstitial | -0.172 |
oho | -0.170 |
ttes | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
bys | +0.339 |
dx | +0.283 |
Interstitial | +0.276 |
oho | +0.270 |
ttes | +0.265 |
Neg logit contributions | |
Dill | -0.265 |
rimp | -0.256 |
Rivals | -0.253 |
Switch | -0.248 |
rans | -0.245 |
Token | � |
Token ID | 447 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
bys | +0.198 |
dx | +0.165 |
Interstitial | +0.160 |
oho | +0.158 |
ttes | +0.154 |
Neg logit contributions | |
Dill | -0.150 |
rimp | -0.144 |
Rivals | -0.144 |
Switch | -0.140 |
rans | -0.138 |
Token | � |
Token ID | 251 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
bys | +0.900 |
dx | +0.760 |
Interstitial | +0.735 |
oho | +0.726 |
ttes | +0.713 |
Neg logit contributions | |
Dill | -0.593 |
rimp | -0.573 |
Rivals | -0.568 |
Switch | -0.547 |
rans | -0.543 |
Token | � |
Token ID | 564 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
bys | +0.297 |
dx | +0.253 |
Interstitial | +0.246 |
oho | +0.244 |
ttes | +0.239 |
Neg logit contributions | |
Dill | -0.170 |
rimp | -0.162 |
Rivals | -0.161 |
Switch | -0.156 |
rans | -0.153 |
Token | � |
Token ID | 250 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
bys | +0.363 |
dx | +0.309 |
Interstitial | +0.300 |
oho | +0.297 |
ttes | +0.292 |
Neg logit contributions | |
Dill | -0.205 |
rimp | -0.199 |
Rivals | -0.196 |
Switch | -0.188 |
rans | -0.188 |
Token | Ah |
Token ID | 10910 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Dill | +0.028 |
rimp | +0.027 |
Rivals | +0.026 |
Marsh | +0.026 |
Switch | +0.026 |
Neg logit contributions | |
bys | -0.040 |
dx | -0.033 |
Interstitial | -0.032 |
oho | -0.032 |
ttes | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
bys | +3.392 |
dx | +2.784 |
Interstitial | +2.669 |
oho | +2.667 |
ttes | +2.557 |
Neg logit contributions | |
Dill | -3.219 |
rimp | -3.133 |
Rivals | -3.120 |
Switch | -2.994 |
rans | -2.967 |
Token | � |
Token ID | 447 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
bys | +0.702 |
dx | +0.593 |
Interstitial | +0.573 |
oho | +0.566 |
ttes | +0.555 |
Neg logit contributions | |
Dill | -0.475 |
rimp | -0.455 |
Rivals | -0.454 |
Switch | -0.439 |
rans | -0.434 |
Token | � |
Token ID | 251 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
bys | +1.262 |
dx | +1.066 |
Interstitial | +1.032 |
oho | +1.020 |
ttes | +1.001 |
Neg logit contributions | |
Dill | -0.834 |
rimp | -0.807 |
Rivals | -0.798 |
Switch | -0.769 |
rans | -0.764 |
Token | Chad |
Token ID | 19800 |
Feature activation | -5.96e-04 |
Pos logit contributions | |
bys | +0.466 |
dx | +0.398 |
Interstitial | +0.387 |
oho | +0.383 |
ttes | +0.376 |
Neg logit contributions | |
Dill | -0.256 |
rimp | -0.244 |
Rivals | -0.243 |
Switch | -0.234 |
rans | -0.229 |
Token | started |
Token ID | 2067 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Dill | +0.001 |
rimp | +0.001 |
Rivals | +0.001 |
Switch | +0.001 |
rans | +0.001 |
Neg logit contributions | |
bys | -0.001 |
dx | -0.001 |
Interstitial | -0.001 |
oho | -0.001 |
ttes | -0.001 |
Token | Art |
Token ID | 3683 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
Dill | +0.420 |
rimp | +0.401 |
Rivals | +0.399 |
Switch | +0.388 |
rans | +0.386 |
Neg logit contributions | |
bys | -0.561 |
dx | -0.471 |
Interstitial | -0.456 |
oho | -0.446 |
ttes | -0.436 |
Token | Museum |
Token ID | 9594 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
Dill | +0.067 |
rimp | +0.064 |
Rivals | +0.064 |
Switch | +0.062 |
rans | +0.062 |
Neg logit contributions | |
bys | -0.076 |
dx | -0.063 |
Interstitial | -0.061 |
oho | -0.060 |
ttes | -0.058 |
Token | is |
Token ID | 318 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
bys | +0.027 |
dx | +0.023 |
Interstitial | +0.022 |
oho | +0.021 |
ttes | +0.021 |
Neg logit contributions | |
Dill | -0.018 |
rimp | -0.017 |
Rivals | -0.017 |
Switch | -0.016 |
rans | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
bys | +0.710 |
dx | +0.609 |
Interstitial | +0.591 |
oho | +0.581 |
ttes | +0.571 |
Neg logit contributions | |
Dill | -0.394 |
rimp | -0.376 |
Rivals | -0.373 |
Switch | -0.361 |
rans | -0.357 |
Token | museum |
Token ID | 13257 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
bys | +0.826 |
dx | +0.693 |
Interstitial | +0.675 |
oho | +0.655 |
ttes | +0.649 |
Neg logit contributions | |
Dill | -0.606 |
rimp | -0.580 |
Rivals | -0.579 |
Switch | -0.566 |
replace | -0.556 |
Token | devoted |
Token ID | 13378 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
bys | +1.204 |
dx | +1.009 |
Interstitial | +0.983 |
oho | +0.960 |
ttes | +0.939 |
Neg logit contributions | |
Dill | -0.881 |
rimp | -0.846 |
Rivals | -0.840 |
Switch | -0.821 |
rans | -0.816 |
Token | to |
Token ID | 284 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
bys | +3.376 |
dx | +2.740 |
Interstitial | +2.657 |
oho | +2.620 |
ttes | +2.580 |
Neg logit contributions | |
Dill | -3.170 |
rimp | -3.094 |
Rivals | -3.077 |
Switch | -2.963 |
rans | -2.938 |
Token | the |
Token ID | 262 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
bys | +0.709 |
dx | +0.607 |
Interstitial | +0.590 |
oho | +0.577 |
ttes | +0.568 |
Neg logit contributions | |
Dill | -0.423 |
rimp | -0.401 |
Rivals | -0.399 |
Switch | -0.386 |
rans | -0.383 |
Token | original |
Token ID | 2656 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
bys | +0.567 |
dx | +0.482 |
Interstitial | +0.469 |
oho | +0.458 |
ttes | +0.450 |
Neg logit contributions | |
Dill | -0.372 |
rimp | -0.355 |
Rivals | -0.353 |
Switch | -0.342 |
rans | -0.339 |
Token | works |
Token ID | 2499 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
bys | +0.487 |
dx | +0.415 |
Interstitial | +0.404 |
oho | +0.396 |
ttes | +0.389 |
Neg logit contributions | |
Dill | -0.294 |
rimp | -0.282 |
Rivals | -0.279 |
Switch | -0.270 |
rans | -0.269 |
Token | of |
Token ID | 286 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
bys | +0.747 |
dx | +0.621 |
Interstitial | +0.600 |
oho | +0.590 |
ttes | +0.576 |
Neg logit contributions | |
Dill | -0.625 |
rimp | -0.605 |
Rivals | -0.600 |
Switch | -0.581 |
rans | -0.580 |
Token | , |
Token ID | 11 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
bys | +0.578 |
dx | +0.480 |
Interstitial | +0.464 |
oho | +0.457 |
ttes | +0.447 |
Neg logit contributions | |
Dill | -0.491 |
rimp | -0.474 |
Rivals | -0.472 |
Switch | -0.457 |
rans | -0.455 |
Token | and |
Token ID | 290 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
bys | +0.179 |
dx | +0.151 |
Interstitial | +0.147 |
oho | +0.144 |
ttes | +0.141 |
Neg logit contributions | |
Dill | -0.128 |
rimp | -0.122 |
Rivals | -0.122 |
Switch | -0.117 |
rans | -0.117 |
Token | the |
Token ID | 262 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
Dill | +0.139 |
Rivals | +0.132 |
rimp | +0.131 |
Switch | +0.127 |
rans | +0.126 |
Neg logit contributions | |
bys | -0.195 |
dx | -0.165 |
Interstitial | -0.162 |
oho | -0.157 |
ttes | -0.154 |
Token | only |
Token ID | 691 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
bys | +0.025 |
dx | +0.021 |
Interstitial | +0.021 |
oho | +0.020 |
ttes | +0.020 |
Neg logit contributions | |
Dill | -0.016 |
rimp | -0.015 |
Rivals | -0.015 |
Switch | -0.014 |
Ames | -0.014 |
Token | w |
Token ID | 266 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
Dill | +0.087 |
Rivals | +0.084 |
rimp | +0.083 |
Switch | +0.080 |
rans | +0.079 |
Neg logit contributions | |
bys | -0.146 |
dx | -0.125 |
Interstitial | -0.121 |
oho | -0.119 |
ttes | -0.117 |
Token | isp |
Token ID | 8802 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Dill | +0.777 |
rimp | +0.756 |
Rivals | +0.748 |
rans | +0.728 |
Switch | +0.722 |
Neg logit contributions | |
bys | -0.977 |
dx | -0.812 |
Interstitial | -0.791 |
oho | -0.773 |
ttes | -0.767 |
Token | of |
Token ID | 286 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
bys | +3.040 |
dx | +2.425 |
oho | +2.275 |
Interstitial | +2.265 |
ttes | +2.213 |
Neg logit contributions | |
Dill | -3.388 |
rimp | -3.325 |
Rivals | -3.296 |
Switch | -3.190 |
Marsh | -3.162 |
Token | political |
Token ID | 1964 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Dill | +0.042 |
rimp | +0.040 |
Rivals | +0.040 |
Switch | +0.038 |
rans | +0.038 |
Neg logit contributions | |
bys | -0.063 |
dx | -0.054 |
Interstitial | -0.052 |
oho | -0.051 |
ttes | -0.050 |
Token | activity |
Token ID | 3842 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
Dill | +0.249 |
Rivals | +0.240 |
rimp | +0.239 |
Switch | +0.231 |
replace | +0.228 |
Neg logit contributions | |
bys | -0.359 |
dx | -0.302 |
Interstitial | -0.297 |
oho | -0.287 |
ttes | -0.286 |
Token | in |
Token ID | 287 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
bys | +0.499 |
dx | +0.417 |
Interstitial | +0.404 |
oho | +0.393 |
ttes | +0.385 |
Neg logit contributions | |
Dill | -0.427 |
Rivals | -0.412 |
rimp | -0.408 |
Switch | -0.398 |
Anonymous | -0.394 |
Token | her |
Token ID | 607 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
Dill | +0.054 |
Rivals | +0.052 |
rimp | +0.052 |
Switch | +0.050 |
Ames | +0.049 |
Neg logit contributions | |
bys | -0.089 |
dx | -0.076 |
Interstitial | -0.074 |
oho | -0.073 |
ttes | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
bys | +0.921 |
dx | +0.761 |
Interstitial | +0.730 |
oho | +0.724 |
ttes | +0.708 |
Neg logit contributions | |
Dill | -0.821 |
rimp | -0.804 |
Rivals | -0.797 |
rans | -0.767 |
Switch | -0.764 |
Token |
|
Token ID | 198 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
bys | +0.355 |
dx | +0.287 |
Interstitial | +0.274 |
oho | +0.270 |
ttes | +0.263 |
Neg logit contributions | |
Dill | -0.386 |
rimp | -0.377 |
Rivals | -0.371 |
rans | -0.360 |
Switch | -0.359 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
bys | +0.429 |
dx | +0.349 |
Interstitial | +0.344 |
oho | +0.338 |
ttes | +0.328 |
Neg logit contributions | |
Dill | -0.411 |
Rivals | -0.398 |
rimp | -0.397 |
Switch | -0.387 |
rans | -0.382 |
Token | With |
Token ID | 3152 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
bys | +0.284 |
dx | +0.243 |
Interstitial | +0.235 |
oho | +0.234 |
ttes | +0.229 |
Neg logit contributions | |
Dill | -0.160 |
rimp | -0.154 |
Rivals | -0.153 |
Switch | -0.146 |
rans | -0.146 |
Token | Josh |
Token ID | 8518 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
Dill | +0.073 |
Rivals | +0.070 |
rimp | +0.070 |
Switch | +0.067 |
rans | +0.066 |
Neg logit contributions | |
bys | -0.127 |
dx | -0.109 |
Interstitial | -0.106 |
oho | -0.105 |
ttes | -0.102 |
Token | Doct |
Token ID | 32155 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Dill | +0.085 |
rimp | +0.082 |
Rivals | +0.082 |
Switch | +0.079 |
rans | +0.078 |
Neg logit contributions | |
bys | -0.112 |
dx | -0.093 |
Interstitial | -0.090 |
oho | -0.089 |
ttes | -0.087 |
Token | son |
Token ID | 1559 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
bys | +3.369 |
dx | +2.734 |
oho | +2.649 |
Interstitial | +2.620 |
ttes | +2.560 |
Neg logit contributions | |
Dill | -3.016 |
rimp | -2.923 |
Rivals | -2.919 |
Switch | -2.814 |
Ames | -2.787 |
Token | finally |
Token ID | 3443 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
bys | +0.630 |
dx | +0.533 |
Interstitial | +0.517 |
oho | +0.511 |
ttes | +0.500 |
Neg logit contributions | |
Dill | -0.410 |
rimp | -0.396 |
Rivals | -0.391 |
Switch | -0.377 |
rans | -0.374 |
Token | becoming |
Token ID | 5033 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
Dill | +0.133 |
rimp | +0.128 |
Rivals | +0.127 |
Switch | +0.122 |
rans | +0.121 |
Neg logit contributions | |
bys | -0.221 |
dx | -0.188 |
Interstitial | -0.183 |
oho | -0.181 |
ttes | -0.176 |
Token | a |
Token ID | 257 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Dill | +0.856 |
Rivals | +0.822 |
rimp | +0.816 |
Switch | +0.789 |
replace | +0.777 |
Neg logit contributions | |
bys | -1.467 |
dx | -1.245 |
Interstitial | -1.211 |
oho | -1.202 |
ttes | -1.168 |
Token | force |
Token ID | 2700 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
bys | +0.230 |
dx | +0.196 |
Interstitial | +0.189 |
oho | +0.188 |
ttes | +0.184 |
Neg logit contributions | |
Dill | -0.140 |
rimp | -0.135 |
Rivals | -0.134 |
Switch | -0.129 |
rans | -0.128 |
Token | Obama |
Token ID | 2486 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
Dill | +0.006 |
rimp | +0.005 |
Rivals | +0.005 |
Switch | +0.005 |
rans | +0.005 |
Neg logit contributions | |
bys | -0.011 |
dx | -0.009 |
Interstitial | -0.009 |
oho | -0.009 |
ttes | -0.009 |
Token | 's |
Token ID | 338 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Dill | +0.010 |
Rivals | +0.010 |
rimp | +0.010 |
Switch | +0.009 |
rans | +0.009 |
Neg logit contributions | |
bys | -0.016 |
dx | -0.013 |
Interstitial | -0.013 |
oho | -0.013 |
ttes | -0.012 |
Token | radical |
Token ID | 7702 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Dill | +0.283 |
Rivals | +0.272 |
rimp | +0.271 |
Switch | +0.260 |
rans | +0.256 |
Neg logit contributions | |
bys | -0.475 |
dx | -0.406 |
Interstitial | -0.394 |
oho | -0.385 |
ttes | -0.380 |
Token | friend |
Token ID | 1545 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
Dill | +0.655 |
rimp | +0.629 |
Rivals | +0.628 |
Switch | +0.603 |
rans | +0.595 |
Neg logit contributions | |
bys | -1.078 |
dx | -0.919 |
Interstitial | -0.890 |
oho | -0.870 |
ttes | -0.863 |
Token | Bill |
Token ID | 3941 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
Dill | +1.074 |
rimp | +1.022 |
Rivals | +1.018 |
Switch | +0.980 |
Ames | +0.972 |
Neg logit contributions | |
bys | -1.655 |
dx | -1.418 |
Interstitial | -1.379 |
oho | -1.342 |
ttes | -1.322 |
Token | Ay |
Token ID | 13709 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
bys | +0.214 |
dx | +0.185 |
Interstitial | +0.180 |
oho | +0.179 |
ttes | +0.176 |
Neg logit contributions | |
Dill | -0.096 |
rimp | -0.092 |
Rivals | -0.091 |
Switch | -0.086 |
rans | -0.086 |
Token | ers |
Token ID | 364 |
Feature activation | -2.34e-03 |
Pos logit contributions | |
bys | +3.422 |
dx | +2.811 |
oho | +2.700 |
Interstitial | +2.685 |
ttes | +2.619 |
Neg logit contributions | |
Dill | -2.958 |
rimp | -2.872 |
Rivals | -2.852 |
Switch | -2.755 |
rans | -2.715 |
Token | . |
Token ID | 13 |
Feature activation | -6.87e-03 |
Pos logit contributions | |
Dill | +0.003 |
rimp | +0.003 |
Rivals | +0.003 |
Switch | +0.003 |
rans | +0.003 |
Neg logit contributions | |
bys | -0.004 |
dx | -0.004 |
Interstitial | -0.004 |
oho | -0.004 |
ttes | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Dill | +0.010 |
rimp | +0.009 |
Rivals | +0.009 |
Switch | +0.009 |
rans | +0.009 |
Neg logit contributions | |
bys | -0.014 |
dx | -0.012 |
Interstitial | -0.011 |
oho | -0.011 |
ttes | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
bys | +0.206 |
dx | +0.168 |
Interstitial | +0.165 |
oho | +0.162 |
ttes | +0.158 |
Neg logit contributions | |
Dill | -0.197 |
Rivals | -0.191 |
rimp | -0.191 |
Switch | -0.186 |
Marsh | -0.184 |
Token | Member |
Token ID | 27608 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
bys | +0.033 |
dx | +0.028 |
Interstitial | +0.028 |
oho | +0.027 |
ttes | +0.027 |
Neg logit contributions | |
Dill | -0.020 |
rimp | -0.019 |
Rivals | -0.019 |
Switch | -0.018 |
rans | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
bys | +0.546 |
dx | +0.465 |
Interstitial | +0.450 |
oho | +0.443 |
ttes | +0.435 |
Neg logit contributions | |
Dill | -0.346 |
rimp | -0.330 |
Rivals | -0.330 |
Switch | -0.317 |
rans | -0.314 |
Token | unto |
Token ID | 12722 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
bys | +0.509 |
dx | +0.428 |
Interstitial | +0.413 |
oho | +0.405 |
ttes | +0.399 |
Neg logit contributions | |
Dill | -0.377 |
rimp | -0.361 |
Rivals | -0.360 |
Switch | -0.349 |
rans | -0.346 |
Token | thy |
Token ID | 11906 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
bys | +2.249 |
dx | +1.894 |
Interstitial | +1.829 |
oho | +1.818 |
ttes | +1.781 |
Neg logit contributions | |
Dill | -1.489 |
rimp | -1.449 |
Rivals | -1.422 |
Switch | -1.372 |
rans | -1.366 |
Token | hands |
Token ID | 2832 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
bys | +1.881 |
dx | +1.585 |
Interstitial | +1.531 |
oho | +1.519 |
ttes | +1.485 |
Neg logit contributions | |
Dill | -1.290 |
rimp | -1.249 |
Rivals | -1.233 |
Switch | -1.188 |
rans | -1.183 |
Token | , |
Token ID | 11 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
bys | +0.308 |
dx | +0.259 |
Interstitial | +0.251 |
oho | +0.247 |
ttes | +0.241 |
Neg logit contributions | |
Dill | -0.236 |
rimp | -0.227 |
Rivals | -0.227 |
Switch | -0.219 |
rans | -0.219 |
Token | thou |
Token ID | 14210 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
bys | +0.841 |
dx | +0.707 |
Interstitial | +0.687 |
oho | +0.677 |
ttes | +0.664 |
Neg logit contributions | |
Dill | -0.604 |
Rivals | -0.578 |
rimp | -0.578 |
Switch | -0.561 |
replace | -0.555 |
Token | shalt |
Token ID | 36258 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
bys | +2.997 |
dx | +2.406 |
Interstitial | +2.276 |
oho | +2.270 |
ttes | +2.206 |
Neg logit contributions | |
Dill | -3.317 |
rimp | -3.249 |
Rivals | -3.207 |
rans | -3.118 |
Switch | -3.114 |
Token | sm |
Token ID | 895 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
bys | +2.741 |
dx | +2.334 |
Interstitial | +2.257 |
oho | +2.238 |
ttes | +2.195 |
Neg logit contributions | |
Dill | -1.642 |
rimp | -1.587 |
Rivals | -1.567 |
Switch | -1.502 |
rans | -1.493 |
Token | ite |
Token ID | 578 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
bys | +1.189 |
dx | +0.973 |
Interstitial | +0.939 |
oho | +0.918 |
ttes | +0.899 |
Neg logit contributions | |
Dill | -1.129 |
rimp | -1.106 |
Rivals | -1.088 |
rans | -1.057 |
Switch | -1.057 |
Token | every |
Token ID | 790 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
bys | +3.024 |
dx | +2.567 |
Interstitial | +2.481 |
oho | +2.462 |
ttes | +2.415 |
Neg logit contributions | |
Dill | -1.876 |
rimp | -1.818 |
Rivals | -1.792 |
Switch | -1.719 |
rans | -1.713 |
Token | male |
Token ID | 4257 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
bys | +1.456 |
dx | +1.229 |
Interstitial | +1.191 |
oho | +1.172 |
ttes | +1.154 |
Neg logit contributions | |
Dill | -0.974 |
rimp | -0.944 |
Rivals | -0.935 |
Switch | -0.897 |
rans | -0.893 |
Token | past |
Token ID | 1613 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Dill | +0.285 |
rimp | +0.275 |
Rivals | +0.273 |
Switch | +0.263 |
rans | +0.260 |
Neg logit contributions | |
bys | -0.493 |
dx | -0.423 |
Interstitial | -0.409 |
oho | -0.403 |
ttes | -0.396 |
Token | , |
Token ID | 11 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
Dill | +0.271 |
rimp | +0.261 |
Rivals | +0.260 |
rans | +0.250 |
Switch | +0.250 |
Neg logit contributions | |
bys | -0.436 |
dx | -0.373 |
Interstitial | -0.361 |
oho | -0.357 |
ttes | -0.349 |
Token | but |
Token ID | 475 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Dill | +0.062 |
Rivals | +0.059 |
rimp | +0.059 |
Switch | +0.057 |
rans | +0.057 |
Neg logit contributions | |
bys | -0.097 |
dx | -0.083 |
Interstitial | -0.080 |
oho | -0.079 |
ttes | -0.078 |
Token | a |
Token ID | 257 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
Dill | +0.157 |
Rivals | +0.150 |
rimp | +0.149 |
Switch | +0.146 |
replace | +0.144 |
Neg logit contributions | |
bys | -0.227 |
dx | -0.192 |
Interstitial | -0.187 |
oho | -0.183 |
ttes | -0.179 |
Token | fe |
Token ID | 730 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Dill | +0.040 |
rimp | +0.039 |
Rivals | +0.038 |
Switch | +0.037 |
rans | +0.036 |
Neg logit contributions | |
bys | -0.070 |
dx | -0.059 |
Interstitial | -0.058 |
oho | -0.057 |
ttes | -0.056 |
Token | ist |
Token ID | 396 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
bys | +0.287 |
dx | +0.243 |
Interstitial | +0.237 |
oho | +0.233 |
ttes | +0.229 |
Neg logit contributions | |
Dill | -0.178 |
rimp | -0.173 |
Rivals | -0.170 |
rans | -0.164 |
Switch | -0.164 |
Token | y |
Token ID | 88 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
bys | +2.941 |
dx | +2.364 |
oho | +2.227 |
Interstitial | +2.222 |
ttes | +2.146 |
Neg logit contributions | |
Dill | -3.298 |
rimp | -3.220 |
Rivals | -3.212 |
Switch | -3.087 |
Marsh | -3.064 |
Token | Kaine |
Token ID | 37193 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
bys | +1.212 |
dx | +1.037 |
Interstitial | +1.006 |
oho | +0.996 |
ttes | +0.978 |
Neg logit contributions | |
Dill | -0.668 |
rimp | -0.643 |
Rivals | -0.636 |
Switch | -0.609 |
rans | -0.604 |
Token | — |
Token ID | 960 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Dill | +0.099 |
rimp | +0.095 |
Rivals | +0.094 |
Switch | +0.091 |
replace | +0.090 |
Neg logit contributions | |
bys | -0.150 |
dx | -0.128 |
Interstitial | -0.125 |
oho | -0.122 |
ttes | -0.120 |
Token | jud |
Token ID | 10456 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
bys | +0.973 |
dx | +0.802 |
Interstitial | +0.771 |
oho | +0.761 |
ttes | +0.744 |
Neg logit contributions | |
Dill | -0.879 |
rimp | -0.855 |
Rivals | -0.847 |
Switch | -0.821 |
rans | -0.818 |
Token | ged |
Token ID | 2004 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
Dill | +0.426 |
rimp | +0.418 |
Rivals | +0.401 |
rans | +0.394 |
Switch | +0.391 |
Neg logit contributions | |
bys | -0.755 |
dx | -0.644 |
Interstitial | -0.635 |
oho | -0.618 |
ttes | -0.612 |
Token | 2000 |
Token ID | 4751 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
bys | +0.250 |
dx | +0.214 |
Interstitial | +0.209 |
oho | +0.208 |
ttes | +0.202 |
Neg logit contributions | |
Dill | -0.120 |
Rivals | -0.115 |
rimp | -0.113 |
Switch | -0.112 |
rans | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
bys | +1.069 |
dx | +0.872 |
Interstitial | +0.839 |
oho | +0.829 |
ttes | +0.808 |
Neg logit contributions | |
Dill | -1.021 |
rimp | -0.989 |
Rivals | -0.986 |
Switch | -0.963 |
rans | -0.951 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Dill | +0.173 |
Rivals | +0.168 |
rimp | +0.167 |
Switch | +0.164 |
Marsh | +0.161 |
Neg logit contributions | |
bys | -0.189 |
dx | -0.154 |
Interstitial | -0.152 |
oho | -0.151 |
staking | -0.147 |
Token | Developer |
Token ID | 45351 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
Dill | +0.141 |
rimp | +0.137 |
Rivals | +0.136 |
Marsh | +0.132 |
Switch | +0.132 |
Neg logit contributions | |
bys | -0.235 |
dx | -0.198 |
oho | -0.194 |
Interstitial | -0.192 |
ttes | -0.189 |
Token | : |
Token ID | 25 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
bys | +0.902 |
dx | +0.736 |
Interstitial | +0.705 |
oho | +0.696 |
ttes | +0.678 |
Neg logit contributions | |
Dill | -0.893 |
rimp | -0.870 |
Rivals | -0.862 |
Switch | -0.835 |
rans | -0.833 |
Token | Relic |
Token ID | 43437 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
bys | +0.875 |
dx | +0.728 |
Interstitial | +0.701 |
oho | +0.693 |
ttes | +0.678 |
Neg logit contributions | |
Dill | -0.703 |
rimp | -0.683 |
Rivals | -0.676 |
Switch | -0.653 |
rans | -0.650 |
Token | Entertainment |
Token ID | 11058 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
bys | +3.336 |
dx | +2.772 |
Interstitial | +2.638 |
oho | +2.627 |
ttes | +2.566 |
Neg logit contributions | |
Dill | -2.895 |
rimp | -2.823 |
Rivals | -2.785 |
rans | -2.680 |
Switch | -2.674 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
bys | +1.166 |
dx | +0.955 |
Interstitial | +0.918 |
oho | +0.906 |
ttes | +0.883 |
Neg logit contributions | |
Dill | -1.102 |
rimp | -1.073 |
Rivals | -1.064 |
Switch | -1.032 |
rans | -1.026 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Dill | +0.174 |
Rivals | +0.169 |
rimp | +0.169 |
Switch | +0.165 |
rans | +0.162 |
Neg logit contributions | |
bys | -0.187 |
dx | -0.152 |
Interstitial | -0.150 |
oho | -0.148 |
staking | -0.144 |
Token | Gen |
Token ID | 13746 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
Dill | +0.151 |
rimp | +0.146 |
Rivals | +0.146 |
Marsh | +0.142 |
Switch | +0.141 |
Neg logit contributions | |
bys | -0.277 |
dx | -0.234 |
oho | -0.230 |
Interstitial | -0.228 |
ttes | -0.224 |
Token | re |
Token ID | 260 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
bys | +1.381 |
dx | +1.215 |
Interstitial | +1.182 |
oho | +1.175 |
ttes | +1.157 |
Neg logit contributions | |
Dill | -0.396 |
rimp | -0.372 |
Rivals | -0.366 |
Switch | -0.337 |
rans | -0.334 |
Token | � |
Token ID | 447 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
Dill | +0.030 |
Rivals | +0.029 |
rimp | +0.029 |
Switch | +0.028 |
rans | +0.028 |
Neg logit contributions | |
bys | -0.028 |
dx | -0.022 |
Interstitial | -0.021 |
oho | -0.021 |
ttes | -0.021 |
Token | � |
Token ID | 251 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
bys | +0.130 |
dx | +0.110 |
Interstitial | +0.106 |
oho | +0.105 |
ttes | +0.103 |
Neg logit contributions | |
Dill | -0.084 |
rimp | -0.081 |
Rivals | -0.080 |
Switch | -0.077 |
rans | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Dill | +0.392 |
Rivals | +0.381 |
rimp | +0.378 |
Switch | +0.369 |
Anonymous | +0.365 |
Neg logit contributions | |
bys | -0.425 |
dx | -0.347 |
Interstitial | -0.333 |
oho | -0.329 |
ttes | -0.322 |
Token |
|
Token ID | 198 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
bys | +0.315 |
dx | +0.256 |
Interstitial | +0.252 |
oho | +0.248 |
ttes | +0.240 |
Neg logit contributions | |
Dill | -0.300 |
rimp | -0.291 |
Rivals | -0.291 |
Switch | -0.284 |
Marsh | -0.279 |
Token | Ev |
Token ID | 15200 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
bys | +0.165 |
dx | +0.139 |
Interstitial | +0.134 |
oho | +0.134 |
ttes | +0.131 |
Neg logit contributions | |
Dill | -0.107 |
rimp | -0.104 |
Rivals | -0.103 |
Marsh | -0.099 |
Switch | -0.099 |
Token | angel |
Token ID | 8368 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
bys | +1.192 |
dx | +0.982 |
Interstitial | +0.937 |
oho | +0.934 |
ttes | +0.913 |
Neg logit contributions | |
Dill | -1.039 |
rimp | -1.009 |
Rivals | -1.005 |
Switch | -0.968 |
rans | -0.955 |
Token | ical |
Token ID | 605 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
bys | +3.600 |
dx | +3.016 |
oho | +2.901 |
Interstitial | +2.901 |
ttes | +2.815 |
Neg logit contributions | |
Dill | -2.587 |
rimp | -2.499 |
Rivals | -2.477 |
rans | -2.384 |
Switch | -2.379 |
Token | adults |
Token ID | 6490 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
bys | +0.674 |
dx | +0.574 |
Interstitial | +0.556 |
oho | +0.550 |
ttes | +0.537 |
Neg logit contributions | |
Dill | -0.411 |
rimp | -0.395 |
Rivals | -0.393 |
Switch | -0.377 |
rans | -0.373 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
Dill | +1.367 |
rimp | +1.318 |
Rivals | +1.310 |
replace | +1.271 |
Switch | +1.269 |
Neg logit contributions | |
bys | -2.036 |
dx | -1.718 |
Interstitial | -1.678 |
oho | -1.637 |
ttes | -1.599 |
Token | like |
Token ID | 588 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Dill | +0.004 |
rimp | +0.003 |
Rivals | +0.003 |
Switch | +0.003 |
rans | +0.003 |
Neg logit contributions | |
bys | -0.006 |
dx | -0.005 |
Interstitial | -0.005 |
oho | -0.005 |
ttes | -0.005 |
Token | believers |
Token ID | 23142 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Dill | +0.186 |
Rivals | +0.176 |
rimp | +0.175 |
Switch | +0.167 |
rans | +0.165 |
Neg logit contributions | |
bys | -0.385 |
dx | -0.333 |
Interstitial | -0.324 |
oho | -0.319 |
ttes | -0.313 |
Token | which |
Token ID | 543 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
bys | +0.271 |
dx | +0.228 |
Interstitial | +0.221 |
oho | +0.218 |
ttes | +0.214 |
Neg logit contributions | |
Dill | -0.191 |
rimp | -0.184 |
Rivals | -0.184 |
Switch | -0.177 |
rans | -0.175 |
Token | went |
Token ID | 1816 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
bys | +0.301 |
dx | +0.257 |
Interstitial | +0.250 |
oho | +0.245 |
ttes | +0.241 |
Neg logit contributions | |
Dill | -0.191 |
rimp | -0.184 |
Rivals | -0.183 |
Switch | -0.175 |
rans | -0.174 |
Token | into |
Token ID | 656 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
Dill | +0.498 |
rimp | +0.484 |
Rivals | +0.477 |
Switch | +0.463 |
rans | +0.459 |
Neg logit contributions | |
bys | -0.761 |
dx | -0.644 |
Interstitial | -0.625 |
oho | -0.622 |
ttes | -0.610 |
Token | a |
Token ID | 257 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
bys | +1.138 |
dx | +0.968 |
Interstitial | +0.937 |
oho | +0.928 |
ttes | +0.910 |
Neg logit contributions | |
Dill | -0.693 |
rimp | -0.669 |
Rivals | -0.662 |
Switch | -0.635 |
rans | -0.631 |
Token | h |
Token ID | 289 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
bys | +0.272 |
dx | +0.229 |
Interstitial | +0.222 |
oho | +0.218 |
ttes | +0.215 |
Neg logit contributions | |
Dill | -0.188 |
rimp | -0.182 |
Rivals | -0.181 |
Switch | -0.174 |
rans | -0.172 |
Token | uddle |
Token ID | 24500 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Dill | +0.454 |
rimp | +0.443 |
Rivals | +0.435 |
rans | +0.421 |
Switch | +0.421 |
Neg logit contributions | |
bys | -0.603 |
dx | -0.504 |
Interstitial | -0.492 |
oho | -0.476 |
ttes | -0.474 |
Token | in |
Token ID | 287 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
bys | +3.582 |
dx | +3.017 |
Interstitial | +2.888 |
oho | +2.884 |
ttes | +2.813 |
Neg logit contributions | |
Dill | -2.522 |
rimp | -2.466 |
Rivals | -2.422 |
Switch | -2.325 |
rans | -2.315 |
Token | an |
Token ID | 281 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
bys | +0.462 |
dx | +0.395 |
Interstitial | +0.386 |
oho | +0.377 |
ttes | +0.372 |
Neg logit contributions | |
Dill | -0.265 |
rimp | -0.253 |
Rivals | -0.252 |
Switch | -0.243 |
rans | -0.239 |
Token | emergency |
Token ID | 6334 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Dill | +0.374 |
rimp | +0.355 |
Rivals | +0.351 |
Switch | +0.339 |
Anonymous | +0.336 |
Neg logit contributions | |
bys | -0.726 |
dx | -0.621 |
Interstitial | -0.605 |
oho | -0.593 |
ttes | -0.589 |
Token | meeting |
Token ID | 3249 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
Dill | +0.386 |
rimp | +0.363 |
Rivals | +0.362 |
Switch | +0.354 |
replace | +0.348 |
Neg logit contributions | |
bys | -0.645 |
dx | -0.550 |
Interstitial | -0.535 |
oho | -0.524 |
ttes | -0.521 |
Token | called |
Token ID | 1444 |
Feature activation | -9.93e-02 |
Pos logit contributions | |
bys | +0.879 |
dx | +0.738 |
Interstitial | +0.717 |
oho | +0.703 |
ttes | +0.691 |
Neg logit contributions | |
Dill | -0.636 |
rimp | -0.612 |
Rivals | -0.608 |
Switch | -0.590 |
rans | -0.584 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Dill | +0.809 |
rimp | +0.784 |
Rivals | +0.776 |
Switch | +0.752 |
rans | +0.751 |
Neg logit contributions | |
bys | -1.042 |
dx | -0.869 |
Interstitial | -0.838 |
oho | -0.827 |
ttes | -0.807 |
Token | pursue |
Token ID | 10660 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
bys | +0.295 |
dx | +0.251 |
Interstitial | +0.244 |
oho | +0.239 |
ttes | +0.235 |
Neg logit contributions | |
Dill | -0.184 |
rimp | -0.178 |
Rivals | -0.177 |
replace | -0.172 |
Switch | -0.171 |
Token | their |
Token ID | 511 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
Dill | +0.571 |
Rivals | +0.542 |
rimp | +0.539 |
Switch | +0.522 |
replace | +0.516 |
Neg logit contributions | |
bys | -0.929 |
dx | -0.788 |
Interstitial | -0.772 |
oho | -0.758 |
ttes | -0.742 |
Token | dream |
Token ID | 4320 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
bys | +0.020 |
dx | +0.017 |
Interstitial | +0.016 |
oho | +0.016 |
ttes | +0.016 |
Neg logit contributions | |
Dill | -0.015 |
Rivals | -0.014 |
rimp | -0.014 |
Switch | -0.013 |
Ames | -0.013 |
Token | un |
Token ID | 555 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Dill | +0.570 |
Rivals | +0.547 |
rimp | +0.545 |
rans | +0.531 |
Switch | +0.527 |
Neg logit contributions | |
bys | -0.757 |
dx | -0.631 |
Interstitial | -0.622 |
oho | -0.605 |
ttes | -0.588 |
Token | apolog |
Token ID | 46407 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
bys | +0.735 |
dx | +0.615 |
Interstitial | +0.593 |
oho | +0.586 |
ttes | +0.573 |
Neg logit contributions | |
Dill | -0.560 |
rimp | -0.543 |
Rivals | -0.538 |
Switch | -0.519 |
rans | -0.517 |
Token | etically |
Token ID | 16877 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
bys | +3.023 |
dx | +2.457 |
Interstitial | +2.343 |
oho | +2.321 |
ttes | +2.255 |
Neg logit contributions | |
Dill | -3.113 |
rimp | -3.035 |
Rivals | -3.014 |
Switch | -2.919 |
rans | -2.907 |
Token | , |
Token ID | 11 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
bys | +0.728 |
dx | +0.606 |
Interstitial | +0.589 |
oho | +0.578 |
ttes | +0.568 |
Neg logit contributions | |
Dill | -0.568 |
rimp | -0.546 |
Rivals | -0.542 |
Switch | -0.525 |
rans | -0.525 |
Token | � |
Token ID | 447 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Dill | +0.087 |
rimp | +0.083 |
Rivals | +0.083 |
Switch | +0.080 |
rans | +0.079 |
Neg logit contributions | |
bys | -0.124 |
dx | -0.104 |
Interstitial | -0.101 |
oho | -0.100 |
ttes | -0.098 |
Token | � |
Token ID | 251 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
Dill | +0.227 |
rimp | +0.218 |
Rivals | +0.218 |
Switch | +0.209 |
rans | +0.206 |
Neg logit contributions | |
bys | -0.394 |
dx | -0.335 |
Interstitial | -0.326 |
oho | -0.321 |
ttes | -0.317 |
Token | said |
Token ID | 531 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
Dill | +0.466 |
rimp | +0.447 |
Rivals | +0.446 |
Switch | +0.429 |
rans | +0.424 |
Neg logit contributions | |
bys | -0.715 |
dx | -0.606 |
Interstitial | -0.589 |
oho | -0.579 |
ttes | -0.569 |
Token | is |
Token ID | 318 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Dill | +0.189 |
rimp | +0.182 |
Rivals | +0.181 |
Switch | +0.174 |
rans | +0.173 |
Neg logit contributions | |
bys | -0.300 |
dx | -0.255 |
Interstitial | -0.248 |
oho | -0.243 |
ttes | -0.239 |
Token | likely |
Token ID | 1884 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
Dill | +0.194 |
Rivals | +0.185 |
rimp | +0.185 |
Switch | +0.178 |
rans | +0.177 |
Neg logit contributions | |
bys | -0.319 |
dx | -0.272 |
Interstitial | -0.262 |
oho | -0.259 |
ttes | -0.254 |
Token | to |
Token ID | 284 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
Dill | +0.970 |
rimp | +0.935 |
Rivals | +0.933 |
rans | +0.899 |
replace | +0.897 |
Neg logit contributions | |
bys | -1.316 |
dx | -1.105 |
Interstitial | -1.059 |
oho | -1.047 |
ttes | -1.029 |
Token | include |
Token ID | 2291 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
Dill | +0.106 |
rimp | +0.103 |
Rivals | +0.101 |
replace | +0.098 |
Switch | +0.097 |
Neg logit contributions | |
bys | -0.169 |
dx | -0.143 |
Interstitial | -0.140 |
oho | -0.137 |
ttes | -0.134 |
Token | a |
Token ID | 257 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
bys | +0.970 |
dx | +0.827 |
Interstitial | +0.801 |
oho | +0.794 |
ttes | +0.778 |
Neg logit contributions | |
Dill | -0.566 |
rimp | -0.546 |
Rivals | -0.539 |
Switch | -0.517 |
rans | -0.514 |
Token | prisoner |
Token ID | 17234 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Dill | +0.052 |
rimp | +0.050 |
Rivals | +0.050 |
Switch | +0.048 |
rans | +0.047 |
Neg logit contributions | |
bys | -0.087 |
dx | -0.074 |
Interstitial | -0.072 |
oho | -0.071 |
ttes | -0.070 |
Token | swap |
Token ID | 16075 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
bys | +3.382 |
dx | +2.813 |
Interstitial | +2.704 |
oho | +2.674 |
ttes | +2.616 |
Neg logit contributions | |
Dill | -2.722 |
rimp | -2.650 |
Rivals | -2.615 |
Switch | -2.512 |
rans | -2.497 |
Token | – |
Token ID | 784 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
bys | +0.140 |
dx | +0.118 |
Interstitial | +0.114 |
oho | +0.112 |
ttes | +0.109 |
Neg logit contributions | |
Dill | -0.108 |
rimp | -0.104 |
Rivals | -0.104 |
rans | -0.101 |
Switch | -0.101 |
Token | or |
Token ID | 393 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
Dill | +0.269 |
rimp | +0.259 |
Rivals | +0.257 |
Switch | +0.248 |
rans | +0.247 |
Neg logit contributions | |
bys | -0.424 |
dx | -0.361 |
Interstitial | -0.349 |
oho | -0.345 |
ttes | -0.338 |
Token | a |
Token ID | 257 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Dill | +0.084 |
rimp | +0.081 |
Rivals | +0.080 |
Switch | +0.078 |
replace | +0.077 |
Neg logit contributions | |
bys | -0.131 |
dx | -0.111 |
Interstitial | -0.108 |
oho | -0.107 |
ttes | -0.104 |
Token | � |
Token ID | 564 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
Dill | +0.134 |
rimp | +0.129 |
Rivals | +0.127 |
Switch | +0.123 |
rans | +0.121 |
Neg logit contributions | |
bys | -0.230 |
dx | -0.196 |
Interstitial | -0.191 |
oho | -0.188 |
ttes | -0.185 |
Token | will |
Token ID | 481 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
Dill | +0.089 |
rimp | +0.086 |
Rivals | +0.085 |
Switch | +0.082 |
rans | +0.081 |
Neg logit contributions | |
bys | -0.158 |
dx | -0.135 |
Interstitial | -0.132 |
oho | -0.130 |
ttes | -0.128 |
Token | o |
Token ID | 267 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Dill | +0.800 |
rimp | +0.778 |
Rivals | +0.769 |
rans | +0.753 |
Switch | +0.747 |
Neg logit contributions | |
bys | -1.007 |
dx | -0.839 |
Interstitial | -0.814 |
oho | -0.798 |
ttes | -0.780 |
Token | ' |
Token ID | 6 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
bys | +0.833 |
dx | +0.705 |
Interstitial | +0.682 |
oho | +0.674 |
ttes | +0.661 |
Neg logit contributions | |
Dill | -0.542 |
rimp | -0.524 |
Rivals | -0.519 |
Switch | -0.499 |
rans | -0.496 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
bys | +0.751 |
dx | +0.638 |
Interstitial | +0.617 |
oho | +0.611 |
ttes | +0.599 |
Neg logit contributions | |
Dill | -0.469 |
rimp | -0.453 |
Rivals | -0.448 |
Switch | -0.430 |
rans | -0.427 |
Token | w |
Token ID | 266 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
Dill | +0.213 |
rimp | +0.205 |
Rivals | +0.204 |
Switch | +0.196 |
rans | +0.194 |
Neg logit contributions | |
bys | -0.359 |
dx | -0.304 |
Interstitial | -0.297 |
oho | -0.291 |
ttes | -0.288 |
Token | isp |
Token ID | 8802 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Dill | +0.866 |
rimp | +0.840 |
Rivals | +0.829 |
rans | +0.802 |
Switch | +0.799 |
Neg logit contributions | |
bys | -1.274 |
dx | -1.076 |
Interstitial | -1.045 |
oho | -1.023 |
ttes | -1.014 |
Token | of |
Token ID | 286 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
bys | +3.263 |
dx | +2.711 |
Interstitial | +2.565 |
oho | +2.549 |
ttes | +2.497 |
Neg logit contributions | |
Dill | -2.795 |
rimp | -2.722 |
Rivals | -2.697 |
Switch | -2.597 |
Marsh | -2.577 |
Token | a |
Token ID | 257 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Dill | +0.148 |
rimp | +0.142 |
Rivals | +0.141 |
Switch | +0.135 |
rans | +0.134 |
Neg logit contributions | |
bys | -0.247 |
dx | -0.211 |
Interstitial | -0.205 |
oho | -0.201 |
ttes | -0.199 |
Token | grand |
Token ID | 4490 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Dill | +0.199 |
rimp | +0.191 |
Rivals | +0.190 |
Switch | +0.183 |
rans | +0.181 |
Neg logit contributions | |
bys | -0.323 |
dx | -0.274 |
Interstitial | -0.266 |
oho | -0.262 |
ttes | -0.259 |
Token | constitution |
Token ID | 11784 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
Dill | +0.352 |
rimp | +0.341 |
Rivals | +0.338 |
Switch | +0.326 |
rans | +0.324 |
Neg logit contributions | |
bys | -0.516 |
dx | -0.434 |
Interstitial | -0.420 |
oho | -0.415 |
ttes | -0.408 |
Token | , |
Token ID | 11 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
Dill | +1.248 |
Rivals | +1.197 |
rimp | +1.193 |
replace | +1.164 |
Switch | +1.161 |
Neg logit contributions | |
bys | -1.768 |
dx | -1.487 |
Interstitial | -1.446 |
oho | -1.423 |
ttes | -1.382 |
Token | But |
Token ID | 1537 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
bys | +0.598 |
dx | +0.506 |
Interstitial | +0.488 |
oho | +0.486 |
ttes | +0.477 |
Neg logit contributions | |
Dill | -0.385 |
rimp | -0.373 |
Rivals | -0.369 |
Switch | -0.355 |
rans | -0.354 |
Token | …. |
Token ID | 11580 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
bys | +0.003 |
dx | +0.002 |
Interstitial | +0.002 |
oho | +0.002 |
ttes | +0.002 |
Neg logit contributions | |
Dill | -0.002 |
Rivals | -0.002 |
rimp | -0.002 |
Switch | -0.002 |
Ames | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Dill | +0.209 |
Rivals | +0.201 |
rimp | +0.200 |
Switch | +0.196 |
rans | +0.194 |
Neg logit contributions | |
bys | -0.261 |
dx | -0.216 |
Interstitial | -0.211 |
ttes | -0.205 |
oho | -0.204 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
bys | +0.452 |
dx | +0.369 |
Interstitial | +0.363 |
oho | +0.356 |
ttes | +0.347 |
Neg logit contributions | |
Dill | -0.428 |
Rivals | -0.415 |
rimp | -0.415 |
Switch | -0.405 |
Marsh | -0.399 |
Token | " |
Token ID | 1 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
bys | +0.260 |
dx | +0.220 |
Interstitial | +0.212 |
oho | +0.212 |
ttes | +0.208 |
Neg logit contributions | |
Dill | -0.164 |
rimp | -0.159 |
Rivals | -0.158 |
Switch | -0.152 |
rans | -0.151 |
Token | Ah |
Token ID | 10910 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
bys | +0.030 |
dx | +0.025 |
Interstitial | +0.025 |
oho | +0.024 |
ttes | +0.024 |
Neg logit contributions | |
Dill | -0.020 |
rimp | -0.019 |
Rivals | -0.019 |
Switch | -0.018 |
Marsh | -0.018 |
Token | ." |
Token ID | 526 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
bys | +3.173 |
dx | +2.608 |
oho | +2.516 |
Interstitial | +2.504 |
ttes | +2.401 |
Neg logit contributions | |
Dill | -2.900 |
rimp | -2.819 |
Rivals | -2.803 |
Switch | -2.697 |
rans | -2.672 |
Token |
|
Token ID | 198 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
bys | +1.224 |
dx | +0.984 |
Interstitial | +0.936 |
oho | +0.927 |
ttes | +0.892 |
Neg logit contributions | |
Dill | -1.392 |
rimp | -1.367 |
Rivals | -1.343 |
rans | -1.303 |
Switch | -1.302 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
bys | +0.511 |
dx | +0.416 |
Interstitial | +0.406 |
oho | +0.400 |
ttes | +0.390 |
Neg logit contributions | |
Dill | -0.493 |
Rivals | -0.477 |
rimp | -0.475 |
Switch | -0.465 |
Marsh | -0.458 |
Token | " |
Token ID | 1 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
bys | +0.416 |
dx | +0.352 |
Interstitial | +0.340 |
oho | +0.338 |
ttes | +0.332 |
Neg logit contributions | |
Dill | -0.263 |
rimp | -0.254 |
Rivals | -0.252 |
Switch | -0.242 |
rans | -0.242 |
Token | Ste |
Token ID | 7447 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
bys | +0.812 |
dx | +0.683 |
Interstitial | +0.659 |
oho | +0.654 |
ttes | +0.642 |
Neg logit contributions | |
Dill | -0.558 |
rimp | -0.539 |
Rivals | -0.534 |
Switch | -0.515 |
rans | -0.512 |
Token | skin |
Token ID | 4168 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
Dill | +0.407 |
rimp | +0.393 |
Rivals | +0.389 |
Switch | +0.375 |
rans | +0.372 |
Neg logit contributions | |
bys | -0.612 |
dx | -0.518 |
Interstitial | -0.500 |
oho | -0.495 |
ttes | -0.485 |
Token | condition |
Token ID | 4006 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
bys | +1.446 |
dx | +1.215 |
Interstitial | +1.173 |
oho | +1.160 |
ttes | +1.136 |
Neg logit contributions | |
Dill | -1.038 |
rimp | -1.006 |
Rivals | -0.995 |
Switch | -0.959 |
rans | -0.954 |
Token | , |
Token ID | 11 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Dill | +1.398 |
rimp | +1.337 |
Rivals | +1.328 |
Switch | +1.294 |
rans | +1.279 |
Neg logit contributions | |
bys | -1.952 |
dx | -1.634 |
Interstitial | -1.588 |
oho | -1.572 |
ttes | -1.526 |
Token | an |
Token ID | 281 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
bys | +0.769 |
dx | +0.649 |
Interstitial | +0.627 |
oho | +0.623 |
ttes | +0.609 |
Neg logit contributions | |
Dill | -0.516 |
rimp | -0.495 |
Rivals | -0.493 |
Switch | -0.475 |
rans | -0.470 |
Token | autos |
Token ID | 44619 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
Dill | +0.536 |
rimp | +0.518 |
Rivals | +0.511 |
Switch | +0.494 |
rans | +0.491 |
Neg logit contributions | |
bys | -0.820 |
dx | -0.692 |
Interstitial | -0.666 |
oho | -0.663 |
ttes | -0.650 |
Token | omal |
Token ID | 18048 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
bys | +0.493 |
dx | +0.389 |
Interstitial | +0.373 |
oho | +0.367 |
ttes | +0.357 |
Neg logit contributions | |
Dill | -0.608 |
rimp | -0.594 |
Rivals | -0.589 |
Switch | -0.573 |
rans | -0.573 |
Token | dominant |
Token ID | 11410 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
bys | +4.100 |
dx | +3.546 |
Interstitial | +3.437 |
oho | +3.395 |
ttes | +3.323 |
Neg logit contributions | |
Dill | -1.949 |
rimp | -1.886 |
Rivals | -1.838 |
rans | -1.745 |
Switch | -1.726 |
Token | palm |
Token ID | 18057 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
bys | +0.385 |
dx | +0.321 |
Interstitial | +0.311 |
oho | +0.307 |
ttes | +0.300 |
Neg logit contributions | |
Dill | -0.300 |
rimp | -0.291 |
Rivals | -0.289 |
Switch | -0.280 |
rans | -0.277 |
Token | opl |
Token ID | 20106 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Dill | +0.426 |
rimp | +0.410 |
Rivals | +0.407 |
Switch | +0.398 |
rans | +0.394 |
Neg logit contributions | |
bys | -0.556 |
dx | -0.462 |
Interstitial | -0.451 |
oho | -0.441 |
ttes | -0.434 |
Token | ant |
Token ID | 415 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
Dill | +0.551 |
rimp | +0.542 |
Rivals | +0.535 |
rans | +0.521 |
Switch | +0.520 |
Neg logit contributions | |
bys | -0.454 |
dx | -0.359 |
Interstitial | -0.347 |
oho | -0.336 |
ttes | -0.328 |
Token | ar |
Token ID | 283 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
Dill | +1.046 |
rimp | +1.011 |
Rivals | +1.003 |
Switch | +0.981 |
rans | +0.976 |
Neg logit contributions | |
bys | -1.385 |
dx | -1.156 |
Interstitial | -1.114 |
oho | -1.106 |
ttes | -1.080 |
Token | of |
Token ID | 286 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
bys | +0.117 |
dx | +0.097 |
Interstitial | +0.094 |
oho | +0.093 |
ttes | +0.091 |
Neg logit contributions | |
Dill | -0.094 |
rimp | -0.091 |
Rivals | -0.091 |
Switch | -0.088 |
rans | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
bys | +0.415 |
dx | +0.351 |
Interstitial | +0.339 |
oho | +0.335 |
ttes | +0.330 |
Neg logit contributions | |
Dill | -0.278 |
rimp | -0.268 |
Rivals | -0.265 |
Switch | -0.257 |
rans | -0.255 |
Token | fact |
Token ID | 1109 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
Dill | +0.013 |
rimp | +0.013 |
Rivals | +0.012 |
Switch | +0.012 |
rans | +0.012 |
Neg logit contributions | |
bys | -0.021 |
dx | -0.018 |
Interstitial | -0.018 |
oho | -0.017 |
ttes | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Dill | +0.134 |
rimp | +0.130 |
Rivals | +0.128 |
Switch | +0.124 |
rans | +0.124 |
Neg logit contributions | |
bys | -0.167 |
dx | -0.139 |
Interstitial | -0.134 |
oho | -0.133 |
ttes | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
Dill | +0.256 |
rimp | +0.244 |
Rivals | +0.242 |
Switch | +0.235 |
rans | +0.233 |
Neg logit contributions | |
bys | -0.394 |
dx | -0.333 |
Interstitial | -0.324 |
oho | -0.321 |
ttes | -0.315 |
Token | ice |
Token ID | 4771 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
bys | +0.127 |
dx | +0.107 |
Interstitial | +0.104 |
oho | +0.103 |
ttes | +0.101 |
Neg logit contributions | |
Dill | -0.087 |
rimp | -0.083 |
Rivals | -0.083 |
Switch | -0.081 |
rans | -0.079 |
Token | sheet |
Token ID | 9629 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
bys | +3.035 |
dx | +2.472 |
Interstitial | +2.348 |
oho | +2.331 |
ttes | +2.282 |
Neg logit contributions | |
Dill | -3.011 |
rimp | -2.944 |
Rivals | -2.915 |
Switch | -2.814 |
rans | -2.803 |
Token | is |
Token ID | 318 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
bys | +0.916 |
dx | +0.778 |
Interstitial | +0.755 |
oho | +0.745 |
ttes | +0.730 |
Neg logit contributions | |
Dill | -0.578 |
rimp | -0.557 |
Rivals | -0.551 |
Switch | -0.531 |
rans | -0.528 |
Token | getting |
Token ID | 1972 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
bys | +0.177 |
dx | +0.151 |
Interstitial | +0.146 |
oho | +0.144 |
ttes | +0.142 |
Neg logit contributions | |
Dill | -0.107 |
rimp | -0.103 |
Rivals | -0.102 |
Switch | -0.098 |
rans | -0.097 |
Token | smaller |
Token ID | 4833 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
bys | +0.825 |
dx | +0.703 |
Interstitial | +0.682 |
oho | +0.675 |
ttes | +0.662 |
Neg logit contributions | |
Dill | -0.493 |
rimp | -0.475 |
Rivals | -0.470 |
Switch | -0.452 |
rans | -0.448 |
Token | and |
Token ID | 290 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
bys | +0.029 |
dx | +0.024 |
Interstitial | +0.024 |
oho | +0.023 |
ttes | +0.023 |
Neg logit contributions | |
Dill | -0.021 |
rimp | -0.021 |
Rivals | -0.020 |
Switch | -0.020 |
rans | -0.019 |
Token | entire |
Token ID | 2104 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Dill | +0.191 |
Rivals | +0.183 |
rimp | +0.182 |
Switch | +0.177 |
Ames | +0.172 |
Neg logit contributions | |
bys | -0.315 |
dx | -0.270 |
Interstitial | -0.261 |
oho | -0.258 |
ttes | -0.253 |
Token | defense |
Token ID | 3761 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
bys | +0.541 |
dx | +0.461 |
Interstitial | +0.446 |
oho | +0.442 |
ttes | +0.431 |
Neg logit contributions | |
Dill | -0.340 |
Rivals | -0.326 |
rimp | -0.325 |
Switch | -0.316 |
rans | -0.309 |
Token | into |
Token ID | 656 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
bys | +0.039 |
dx | +0.033 |
Interstitial | +0.032 |
oho | +0.032 |
ttes | +0.031 |
Neg logit contributions | |
Dill | -0.024 |
Rivals | -0.023 |
rimp | -0.023 |
Switch | -0.022 |
rans | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -9.59e-03 |
Pos logit contributions | |
bys | +0.343 |
dx | +0.294 |
Interstitial | +0.285 |
oho | +0.282 |
ttes | +0.277 |
Neg logit contributions | |
Dill | -0.189 |
rimp | -0.182 |
Rivals | -0.180 |
Switch | -0.172 |
rans | -0.171 |
Token | h |
Token ID | 289 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Dill | +0.013 |
rimp | +0.013 |
Rivals | +0.013 |
Switch | +0.012 |
rans | +0.012 |
Neg logit contributions | |
bys | -0.019 |
dx | -0.016 |
Interstitial | -0.016 |
oho | -0.015 |
ttes | -0.015 |
Token | uddle |
Token ID | 24500 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Dill | +0.335 |
rimp | +0.327 |
Rivals | +0.315 |
rans | +0.305 |
Switch | +0.303 |
Neg logit contributions | |
bys | -0.654 |
dx | -0.563 |
Interstitial | -0.550 |
ttes | -0.534 |
oho | -0.534 |
Token | and |
Token ID | 290 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
bys | +3.357 |
dx | +2.791 |
Interstitial | +2.675 |
oho | +2.664 |
ttes | +2.611 |
Neg logit contributions | |
Dill | -2.652 |
rimp | -2.598 |
Rivals | -2.556 |
Switch | -2.462 |
rans | -2.452 |
Token | delivered |
Token ID | 6793 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
bys | +0.482 |
dx | +0.407 |
Interstitial | +0.394 |
oho | +0.388 |
ttes | +0.379 |
Neg logit contributions | |
Dill | -0.331 |
Rivals | -0.316 |
rimp | -0.315 |
Switch | -0.305 |
rans | -0.300 |
Token | a |
Token ID | 257 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
bys | +0.462 |
dx | +0.395 |
Interstitial | +0.383 |
oho | +0.378 |
ttes | +0.369 |
Neg logit contributions | |
Dill | -0.270 |
Rivals | -0.256 |
rimp | -0.253 |
Switch | -0.247 |
replace | -0.242 |
Token | colorful |
Token ID | 20239 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
bys | +0.047 |
dx | +0.040 |
Interstitial | +0.038 |
oho | +0.038 |
ttes | +0.037 |
Neg logit contributions | |
Dill | -0.030 |
rimp | -0.029 |
Rivals | -0.029 |
Switch | -0.028 |
replace | -0.028 |
Token | speech |
Token ID | 4046 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Dill | +0.188 |
Rivals | +0.180 |
rimp | +0.179 |
Switch | +0.174 |
underdog | +0.172 |
Neg logit contributions | |
bys | -0.312 |
dx | -0.265 |
Interstitial | -0.255 |
oho | -0.252 |
ttes | -0.249 |
Token | to |
Token ID | 284 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
Dill | +0.848 |
Rivals | +0.821 |
rimp | +0.805 |
Switch | +0.794 |
Anonymous | +0.780 |
Neg logit contributions | |
bys | -1.165 |
dx | -0.967 |
Interstitial | -0.940 |
oho | -0.934 |
ttes | -0.904 |
Token | The |
Token ID | 383 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
Dill | +0.068 |
Rivals | +0.066 |
rimp | +0.065 |
Switch | +0.063 |
rans | +0.062 |
Neg logit contributions | |
bys | -0.116 |
dx | -0.099 |
Interstitial | -0.096 |
oho | -0.094 |
ttes | -0.093 |
Token | Verge |
Token ID | 44499 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
Dill | +0.455 |
Rivals | +0.435 |
rimp | +0.432 |
Switch | +0.419 |
rans | +0.410 |
Neg logit contributions | |
bys | -0.729 |
dx | -0.618 |
Interstitial | -0.603 |
oho | -0.593 |
ttes | -0.584 |
Token | . |
Token ID | 13 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
bys | +1.079 |
dx | +0.894 |
Interstitial | +0.861 |
oho | +0.851 |
ttes | +0.831 |
Neg logit contributions | |
Dill | -0.905 |
rimp | -0.876 |
Rivals | -0.872 |
Switch | -0.845 |
rans | -0.839 |
Token | Ellis |
Token ID | 21299 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
bys | +0.084 |
dx | +0.069 |
Interstitial | +0.067 |
oho | +0.066 |
ttes | +0.064 |
Neg logit contributions | |
Dill | -0.077 |
Rivals | -0.075 |
rimp | -0.074 |
Switch | -0.073 |
rans | -0.071 |
Token | Hamb |
Token ID | 26175 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Dill | +0.053 |
rimp | +0.051 |
Rivals | +0.051 |
Switch | +0.049 |
rans | +0.048 |
Neg logit contributions | |
bys | -0.087 |
dx | -0.074 |
Interstitial | -0.071 |
oho | -0.071 |
ttes | -0.069 |
Token | urger |
Token ID | 32650 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Dill | +2.320 |
rimp | +2.265 |
Rivals | +2.192 |
rans | +2.173 |
Switch | +2.087 |
Neg logit contributions | |
bys | -4.808 |
dx | -4.175 |
Interstitial | -4.148 |
oho | -4.014 |
ttes | -3.938 |
Token | got |
Token ID | 1392 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Dill | +2.000 |
Rivals | +1.910 |
rimp | +1.888 |
Switch | +1.865 |
Marsh | +1.826 |
Neg logit contributions | |
bys | -2.763 |
dx | -2.333 |
Interstitial | -2.268 |
oho | -2.240 |
ttes | -2.176 |
Token | to |
Token ID | 284 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
bys | +0.278 |
dx | +0.236 |
Interstitial | +0.229 |
oho | +0.226 |
ttes | +0.221 |
Neg logit contributions | |
Dill | -0.169 |
rimp | -0.162 |
Rivals | -0.162 |
Switch | -0.156 |
rans | -0.153 |
Token | test |
Token ID | 1332 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Dill | +0.165 |
Rivals | +0.159 |
rimp | +0.158 |
Switch | +0.153 |
rans | +0.151 |
Neg logit contributions | |
bys | -0.270 |
dx | -0.230 |
Interstitial | -0.222 |
oho | -0.219 |
ttes | -0.214 |
Token | it |
Token ID | 340 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Dill | +0.329 |
Rivals | +0.316 |
rimp | +0.314 |
Switch | +0.304 |
rans | +0.299 |
Neg logit contributions | |
bys | -0.533 |
dx | -0.450 |
Interstitial | -0.437 |
oho | -0.433 |
ttes | -0.423 |
Token | staying |
Token ID | 10589 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Dill | +0.070 |
rimp | +0.066 |
Rivals | +0.066 |
Switch | +0.064 |
rans | +0.063 |
Neg logit contributions | |
bys | -0.119 |
dx | -0.102 |
Interstitial | -0.099 |
oho | -0.098 |
ttes | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
bys | +0.248 |
dx | +0.208 |
Interstitial | +0.203 |
oho | +0.200 |
ttes | +0.195 |
Neg logit contributions | |
Dill | -0.184 |
rimp | -0.174 |
Rivals | -0.173 |
Switch | -0.168 |
Anonymous | -0.167 |
Token | fighting |
Token ID | 4330 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
bys | +0.537 |
dx | +0.456 |
Interstitial | +0.443 |
oho | +0.438 |
ttes | +0.430 |
Neg logit contributions | |
Dill | -0.337 |
rimp | -0.321 |
Rivals | -0.320 |
Switch | -0.308 |
rans | -0.305 |
Token | ." |
Token ID | 526 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
bys | +0.786 |
dx | +0.661 |
Interstitial | +0.644 |
oho | +0.634 |
ttes | +0.619 |
Neg logit contributions | |
Dill | -0.580 |
rimp | -0.554 |
Rivals | -0.550 |
Switch | -0.533 |
rans | -0.526 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
Dill | +0.195 |
rimp | +0.188 |
Rivals | +0.188 |
Switch | +0.182 |
rans | +0.180 |
Neg logit contributions | |
bys | -0.207 |
dx | -0.170 |
Interstitial | -0.163 |
oho | -0.161 |
ttes | -0.157 |
Token | Anonymous |
Token ID | 20660 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Dill | +0.110 |
rimp | +0.107 |
Rivals | +0.106 |
Marsh | +0.102 |
rans | +0.102 |
Neg logit contributions | |
bys | -0.171 |
dx | -0.145 |
Interstitial | -0.140 |
oho | -0.140 |
ttes | -0.137 |
Token | asked |
Token ID | 1965 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
Dill | +2.766 |
Anonymous | +2.663 |
Rivals | +2.655 |
rimp | +2.637 |
Switch | +2.609 |
Neg logit contributions | |
bys | -4.260 |
dx | -3.605 |
Interstitial | -3.532 |
oho | -3.482 |
ttes | -3.411 |
Token | : |
Token ID | 25 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
Dill | +0.616 |
Rivals | +0.591 |
rimp | +0.591 |
Switch | +0.576 |
Anonymous | +0.571 |
Neg logit contributions | |
bys | -0.707 |
dx | -0.588 |
Interstitial | -0.572 |
oho | -0.555 |
ttes | -0.544 |
Token | AU |
Token ID | 27548 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
bys | +0.173 |
dx | +0.146 |
Interstitial | +0.142 |
oho | +0.140 |
ttes | +0.137 |
Neg logit contributions | |
Dill | -0.120 |
rimp | -0.115 |
Rivals | -0.115 |
Switch | -0.111 |
Anonymous | -0.110 |
Token | idea |
Token ID | 2126 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
Dill | +0.474 |
rimp | +0.458 |
Rivals | +0.456 |
Switch | +0.441 |
rans | +0.437 |
Neg logit contributions | |
bys | -0.681 |
dx | -0.573 |
Interstitial | -0.555 |
oho | -0.550 |
ttes | -0.538 |
Token | : |
Token ID | 25 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Dill | +0.106 |
rimp | +0.102 |
Rivals | +0.102 |
Switch | +0.099 |
rans | +0.098 |
Neg logit contributions | |
bys | -0.142 |
dx | -0.119 |
Interstitial | -0.116 |
oho | -0.114 |
ttes | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
Dill | +0.455 |
rimp | +0.436 |
Rivals | +0.434 |
Switch | +0.421 |
rans | +0.418 |
Neg logit contributions | |
bys | -0.634 |
dx | -0.531 |
Interstitial | -0.518 |
oho | -0.506 |
ttes | -0.498 |
Token | including |
Token ID | 1390 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
Dill | +0.388 |
rimp | +0.371 |
Rivals | +0.370 |
Switch | +0.356 |
rans | +0.352 |
Neg logit contributions | |
bys | -0.628 |
dx | -0.531 |
Interstitial | -0.520 |
oho | -0.511 |
ttes | -0.501 |
Token | headset |
Token ID | 23492 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
bys | +1.446 |
dx | +1.235 |
Interstitial | +1.192 |
oho | +1.183 |
ttes | +1.161 |
Neg logit contributions | |
Dill | -0.846 |
rimp | -0.820 |
Rivals | -0.806 |
Switch | -0.773 |
rans | -0.771 |
Token | , |
Token ID | 11 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Dill | +1.745 |
Rivals | +1.684 |
rimp | +1.671 |
Switch | +1.617 |
replace | +1.616 |
Neg logit contributions | |
bys | -2.495 |
dx | -2.081 |
Interstitial | -2.055 |
oho | -2.006 |
ttes | -1.948 |
Token | cr |
Token ID | 1067 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
Dill | +0.345 |
rimp | +0.329 |
Rivals | +0.327 |
Switch | +0.314 |
rans | +0.310 |
Neg logit contributions | |
bys | -0.635 |
dx | -0.541 |
Interstitial | -0.529 |
oho | -0.522 |
ttes | -0.513 |
Token | anks |
Token ID | 2283 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
bys | +1.478 |
dx | +1.294 |
Interstitial | +1.250 |
oho | +1.250 |
ttes | +1.226 |
Neg logit contributions | |
Dill | -0.516 |
rimp | -0.488 |
Rivals | -0.480 |
Switch | -0.449 |
rans | -0.445 |
Token | and |
Token ID | 290 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Dill | +3.451 |
rimp | +3.394 |
Rivals | +3.381 |
Switch | +3.310 |
replace | +3.306 |
Neg logit contributions | |
bys | -3.259 |
Interstitial | -2.641 |
dx | -2.580 |
oho | -2.519 |
ttes | -2.447 |
Token | brakes |
Token ID | 23746 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Dill | +0.405 |
rimp | +0.385 |
Rivals | +0.384 |
Switch | +0.369 |
replace | +0.363 |
Neg logit contributions | |
bys | -0.769 |
dx | -0.658 |
Interstitial | -0.644 |
oho | -0.636 |
ttes | -0.623 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
Dill | +0.687 |
Rivals | +0.662 |
rimp | +0.661 |
Switch | +0.640 |
replace | +0.638 |
Neg logit contributions | |
bys | -0.907 |
dx | -0.753 |
Interstitial | -0.739 |
oho | -0.725 |
ttes | -0.701 |
Token | The |
Token ID | 383 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
Dill | +0.020 |
rimp | +0.019 |
Rivals | +0.019 |
Switch | +0.018 |
rans | +0.018 |
Neg logit contributions | |
bys | -0.031 |
dx | -0.026 |
Interstitial | -0.025 |
oho | -0.025 |
ttes | -0.025 |
Token | wheels |
Token ID | 13666 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
bys | +0.171 |
dx | +0.145 |
Interstitial | +0.142 |
oho | +0.140 |
ttes | +0.137 |
Neg logit contributions | |
Dill | -0.102 |
Rivals | -0.097 |
rimp | -0.097 |
Switch | -0.094 |
replace | -0.092 |
Token | , |
Token ID | 11 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
Dill | +0.643 |
rimp | +0.618 |
Rivals | +0.613 |
Switch | +0.590 |
rans | +0.588 |
Neg logit contributions | |
bys | -1.137 |
dx | -0.973 |
Interstitial | -0.953 |
oho | -0.933 |
ttes | -0.914 |
Token | destabil |
Token ID | 27397 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
Dill | +0.127 |
rimp | +0.123 |
Rivals | +0.122 |
Switch | +0.117 |
replace | +0.116 |
Neg logit contributions | |
bys | -0.208 |
dx | -0.177 |
Interstitial | -0.172 |
oho | -0.170 |
ttes | -0.167 |
Token | ize |
Token ID | 1096 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Dill | +0.596 |
rimp | +0.578 |
Rivals | +0.570 |
Switch | +0.549 |
rans | +0.547 |
Neg logit contributions | |
bys | -0.983 |
dx | -0.836 |
Interstitial | -0.809 |
oho | -0.798 |
ttes | -0.783 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Dill | +0.770 |
rimp | +0.747 |
Rivals | +0.742 |
Switch | +0.717 |
rans | +0.714 |
Neg logit contributions | |
bys | -0.964 |
dx | -0.804 |
Interstitial | -0.775 |
oho | -0.764 |
ttes | -0.747 |
Token | and |
Token ID | 290 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Dill | +0.385 |
rimp | +0.374 |
Rivals | +0.370 |
Switch | +0.356 |
rans | +0.355 |
Neg logit contributions | |
bys | -0.547 |
dx | -0.460 |
Interstitial | -0.445 |
oho | -0.440 |
ttes | -0.431 |
Token | demoral |
Token ID | 49077 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
Dill | +0.535 |
rimp | +0.516 |
Rivals | +0.510 |
replace | +0.504 |
Switch | +0.493 |
Neg logit contributions | |
bys | -1.002 |
dx | -0.859 |
Interstitial | -0.838 |
oho | -0.823 |
ttes | -0.810 |
Token | ize |
Token ID | 1096 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
Dill | +2.188 |
rimp | +2.140 |
replace | +2.036 |
rans | +2.026 |
Rivals | +2.012 |
Neg logit contributions | |
bys | -4.523 |
dx | -3.853 |
Interstitial | -3.800 |
oho | -3.698 |
ttes | -3.619 |
Token | its |
Token ID | 663 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
Dill | +0.726 |
Rivals | +0.692 |
rimp | +0.688 |
Switch | +0.665 |
rans | +0.662 |
Neg logit contributions | |
bys | -1.346 |
dx | -1.154 |
Interstitial | -1.127 |
oho | -1.107 |
ttes | -1.082 |
Token | geopolitical |
Token ID | 35493 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Dill | +0.444 |
Rivals | +0.426 |
rimp | +0.424 |
Switch | +0.402 |
rans | +0.402 |
Neg logit contributions | |
bys | -0.937 |
dx | -0.808 |
Interstitial | -0.787 |
oho | -0.777 |
ttes | -0.765 |
Token | opponents |
Token ID | 7691 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
Dill | +0.319 |
Rivals | +0.307 |
rimp | +0.305 |
Switch | +0.289 |
rans | +0.287 |
Neg logit contributions | |
bys | -0.687 |
dx | -0.593 |
Interstitial | -0.578 |
oho | -0.570 |
ttes | -0.561 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Dill | +0.937 |
rimp | +0.910 |
Rivals | +0.901 |
rans | +0.881 |
Switch | +0.878 |
Neg logit contributions | |
bys | -1.261 |
dx | -1.062 |
Interstitial | -1.032 |
oho | -1.013 |
ttes | -0.985 |
Token | was |
Token ID | 373 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Dill | +0.862 |
rimp | +0.839 |
Rivals | +0.821 |
Switch | +0.801 |
replace | +0.799 |
Neg logit contributions | |
bys | -1.327 |
dx | -1.135 |
Interstitial | -1.093 |
oho | -1.087 |
ttes | -1.056 |
Token | characterized |
Token ID | 16264 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
bys | +0.421 |
dx | +0.354 |
Interstitial | +0.341 |
oho | +0.338 |
ttes | +0.330 |
Neg logit contributions | |
Dill | -0.308 |
rimp | -0.296 |
Rivals | -0.294 |
Switch | -0.285 |
rans | -0.283 |
Token | as |
Token ID | 355 |
Feature activation | -7.32e-03 |
Pos logit contributions | |
Dill | +0.619 |
rimp | +0.597 |
Rivals | +0.590 |
Switch | +0.581 |
replace | +0.580 |
Neg logit contributions | |
bys | -0.736 |
dx | -0.619 |
Interstitial | -0.602 |
oho | -0.595 |
ttes | -0.584 |
Token | having |
Token ID | 1719 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
Dill | +0.009 |
rimp | +0.009 |
Rivals | +0.009 |
Switch | +0.008 |
rans | +0.008 |
Neg logit contributions | |
bys | -0.016 |
dx | -0.013 |
Interstitial | -0.013 |
oho | -0.013 |
ttes | -0.013 |
Token | bacterial |
Token ID | 23462 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
bys | +0.154 |
dx | +0.131 |
Interstitial | +0.127 |
oho | +0.127 |
ttes | +0.124 |
Neg logit contributions | |
Dill | -0.093 |
rimp | -0.088 |
Rivals | -0.088 |
Switch | -0.085 |
rans | -0.084 |
Token | vag |
Token ID | 14334 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Dill | +0.261 |
rimp | +0.253 |
Rivals | +0.251 |
Switch | +0.244 |
rans | +0.242 |
Neg logit contributions | |
bys | -0.315 |
dx | -0.263 |
Interstitial | -0.252 |
oho | -0.251 |
ttes | -0.246 |
Token | in |
Token ID | 259 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
Dill | +2.789 |
rimp | +2.735 |
Rivals | +2.679 |
rans | +2.677 |
Switch | +2.595 |
Neg logit contributions | |
bys | -3.798 |
dx | -3.201 |
Interstitial | -3.085 |
oho | -3.020 |
ttes | -2.985 |
Token | osis |
Token ID | 5958 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
Dill | +0.432 |
rimp | +0.415 |
Rivals | +0.410 |
Switch | +0.393 |
rans | +0.393 |
Neg logit contributions | |
bys | -0.795 |
dx | -0.685 |
Interstitial | -0.661 |
oho | -0.654 |
ttes | -0.645 |
Token | ( |
Token ID | 357 |
Feature activation | -9.75e-02 |
Pos logit contributions | |
Dill | +1.063 |
rimp | +1.021 |
Rivals | +1.010 |
Switch | +0.982 |
rans | +0.980 |
Neg logit contributions | |
bys | -1.475 |
dx | -1.235 |
oho | -1.200 |
Interstitial | -1.194 |
ttes | -1.169 |
Token | B |
Token ID | 33 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
Dill | +0.147 |
rimp | +0.142 |
Rivals | +0.140 |
rans | +0.136 |
Switch | +0.136 |
Neg logit contributions | |
bys | -0.183 |
dx | -0.152 |
Interstitial | -0.146 |
oho | -0.146 |
ttes | -0.143 |
Token | V |
Token ID | 53 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
Dill | +0.267 |
rimp | +0.260 |
Rivals | +0.252 |
Switch | +0.245 |
rans | +0.243 |
Neg logit contributions | |
bys | -0.497 |
dx | -0.421 |
Interstitial | -0.414 |
oho | -0.407 |
ttes | -0.406 |
Token | by |
Token ID | 416 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
bys | +0.480 |
dx | +0.401 |
Interstitial | +0.387 |
oho | +0.382 |
ttes | +0.373 |
Neg logit contributions | |
Dill | -0.409 |
Rivals | -0.394 |
rimp | -0.394 |
Switch | -0.379 |
rans | -0.378 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Dill | +0.214 |
Rivals | +0.203 |
rimp | +0.201 |
Switch | +0.195 |
Ames | +0.193 |
Neg logit contributions | |
bys | -0.334 |
dx | -0.284 |
Interstitial | -0.276 |
oho | -0.272 |
ttes | -0.267 |
Token | vulnerability |
Token ID | 15131 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
Dill | +0.211 |
rimp | +0.202 |
Rivals | +0.201 |
Switch | +0.194 |
Ames | +0.191 |
Neg logit contributions | |
bys | -0.309 |
dx | -0.262 |
Interstitial | -0.255 |
oho | -0.249 |
ttes | -0.245 |
Token | of |
Token ID | 286 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Dill | +0.096 |
Rivals | +0.092 |
rimp | +0.092 |
Switch | +0.089 |
rans | +0.089 |
Neg logit contributions | |
bys | -0.121 |
dx | -0.101 |
Interstitial | -0.098 |
oho | -0.096 |
ttes | -0.094 |
Token | his |
Token ID | 465 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Dill | +0.294 |
Rivals | +0.279 |
rimp | +0.278 |
Switch | +0.268 |
Anonymous | +0.265 |
Neg logit contributions | |
bys | -0.483 |
dx | -0.411 |
Interstitial | -0.402 |
oho | -0.391 |
ttes | -0.386 |
Token | prog |
Token ID | 1172 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Dill | +0.593 |
Rivals | +0.568 |
rimp | +0.566 |
Switch | +0.547 |
rans | +0.540 |
Neg logit contributions | |
bys | -0.857 |
dx | -0.724 |
Interstitial | -0.704 |
oho | -0.686 |
ttes | -0.680 |
Token | eny |
Token ID | 28558 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
Dill | +2.580 |
rimp | +2.512 |
Rivals | +2.445 |
rans | +2.417 |
Switch | +2.365 |
Neg logit contributions | |
bys | -3.980 |
dx | -3.367 |
Interstitial | -3.322 |
oho | -3.231 |
ttes | -3.205 |
Token | , |
Token ID | 11 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
bys | +0.499 |
dx | +0.417 |
Interstitial | +0.403 |
oho | +0.399 |
ttes | +0.389 |
Neg logit contributions | |
Dill | -0.382 |
rimp | -0.366 |
Rivals | -0.366 |
Switch | -0.353 |
rans | -0.350 |
Token | that |
Token ID | 326 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Dill | +0.178 |
Rivals | +0.170 |
rimp | +0.170 |
Switch | +0.164 |
rans | +0.163 |
Neg logit contributions | |
bys | -0.232 |
dx | -0.194 |
Interstitial | -0.188 |
oho | -0.185 |
ttes | -0.182 |
Token | he |
Token ID | 339 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Dill | +0.245 |
Rivals | +0.233 |
rimp | +0.232 |
Switch | +0.225 |
Anonymous | +0.222 |
Neg logit contributions | |
bys | -0.355 |
dx | -0.299 |
Interstitial | -0.292 |
oho | -0.285 |
ttes | -0.280 |
Token | began |
Token ID | 2540 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
Dill | +0.222 |
rimp | +0.211 |
Rivals | +0.209 |
Switch | +0.203 |
rans | +0.201 |
Neg logit contributions | |
bys | -0.339 |
dx | -0.288 |
Interstitial | -0.283 |
oho | -0.274 |
ttes | -0.270 |
Token | success |
Token ID | 1943 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
bys | +0.158 |
dx | +0.134 |
Interstitial | +0.131 |
oho | +0.127 |
ttes | +0.125 |
Neg logit contributions | |
Dill | -0.116 |
Rivals | -0.111 |
rimp | -0.110 |
Switch | -0.107 |
replace | -0.105 |
Token | ". |
Token ID | 1911 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
Dill | +0.100 |
rimp | +0.096 |
Rivals | +0.094 |
Switch | +0.090 |
rans | +0.090 |
Neg logit contributions | |
bys | -0.185 |
dx | -0.159 |
Interstitial | -0.155 |
oho | -0.153 |
ttes | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Dill | +1.350 |
Rivals | +1.319 |
rimp | +1.288 |
Switch | +1.281 |
Marsh | +1.253 |
Neg logit contributions | |
bys | -1.407 |
dx | -1.142 |
Interstitial | -1.105 |
oho | -1.103 |
ttes | -1.067 |
Token |
|
Token ID | 198 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
bys | +0.272 |
dx | +0.222 |
Interstitial | +0.218 |
oho | +0.216 |
ttes | +0.209 |
Neg logit contributions | |
Dill | -0.258 |
Rivals | -0.250 |
rimp | -0.249 |
Switch | -0.244 |
Marsh | -0.241 |
Token | L |
Token ID | 43 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
bys | +0.141 |
dx | +0.121 |
Interstitial | +0.117 |
oho | +0.117 |
ttes | +0.114 |
Neg logit contributions | |
Dill | -0.079 |
rimp | -0.077 |
Rivals | -0.076 |
Marsh | -0.073 |
Switch | -0.073 |
Token | ever |
Token ID | 964 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Dill | +0.458 |
rimp | +0.449 |
Rivals | +0.433 |
rans | +0.416 |
Switch | +0.414 |
Neg logit contributions | |
bys | -1.061 |
dx | -0.918 |
Interstitial | -0.895 |
oho | -0.884 |
ttes | -0.874 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Dill | +2.518 |
Rivals | +2.401 |
rimp | +2.384 |
replace | +2.343 |
Switch | +2.309 |
Neg logit contributions | |
bys | -3.997 |
dx | -3.411 |
Interstitial | -3.394 |
oho | -3.266 |
ttes | -3.208 |
Token | like |
Token ID | 588 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
Dill | +0.262 |
Rivals | +0.250 |
rimp | +0.246 |
Switch | +0.240 |
replace | +0.236 |
Neg logit contributions | |
bys | -0.420 |
dx | -0.357 |
Interstitial | -0.349 |
oho | -0.344 |
ttes | -0.337 |
Token | Gibbs |
Token ID | 41071 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Dill | +0.331 |
Rivals | +0.314 |
rimp | +0.311 |
Switch | +0.299 |
rans | +0.292 |
Neg logit contributions | |
bys | -0.723 |
dx | -0.626 |
Interstitial | -0.612 |
oho | -0.603 |
ttes | -0.592 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
bys | +0.196 |
dx | +0.164 |
Interstitial | +0.158 |
oho | +0.156 |
ttes | +0.153 |
Neg logit contributions | |
Dill | -0.153 |
rimp | -0.148 |
Rivals | -0.147 |
Switch | -0.142 |
rans | -0.142 |
Token | was |
Token ID | 373 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Dill | +0.199 |
Rivals | +0.190 |
rimp | +0.190 |
Switch | +0.183 |
rans | +0.180 |
Neg logit contributions | |
bys | -0.318 |
dx | -0.270 |
Interstitial | -0.264 |
oho | -0.259 |
ttes | -0.255 |
Token | bury |
Token ID | 30033 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Dill | +0.636 |
rimp | +0.605 |
replace | +0.603 |
Rivals | +0.601 |
Switch | +0.592 |
Neg logit contributions | |
bys | -1.094 |
dx | -0.938 |
Interstitial | -0.921 |
oho | -0.899 |
ttes | -0.876 |
Token | them |
Token ID | 606 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
Dill | +0.295 |
rimp | +0.282 |
Rivals | +0.279 |
Switch | +0.270 |
rans | +0.266 |
Neg logit contributions | |
bys | -0.464 |
dx | -0.395 |
Interstitial | -0.383 |
oho | -0.379 |
ttes | -0.369 |
Token | in |
Token ID | 287 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
bys | +0.832 |
dx | +0.696 |
Interstitial | +0.675 |
oho | +0.668 |
ttes | +0.643 |
Neg logit contributions | |
Dill | -0.689 |
rimp | -0.662 |
Rivals | -0.650 |
Switch | -0.637 |
rans | -0.630 |
Token | a |
Token ID | 257 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
bys | +0.131 |
dx | +0.111 |
Interstitial | +0.108 |
oho | +0.107 |
ttes | +0.104 |
Neg logit contributions | |
Dill | -0.079 |
rimp | -0.076 |
Rivals | -0.075 |
Switch | -0.072 |
rans | -0.071 |
Token | bur |
Token ID | 4356 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
bys | +0.331 |
dx | +0.284 |
Interstitial | +0.277 |
oho | +0.273 |
ttes | +0.268 |
Neg logit contributions | |
Dill | -0.170 |
rimp | -0.162 |
Rivals | -0.160 |
Switch | -0.154 |
rans | -0.152 |
Token | rito |
Token ID | 39834 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
bys | +0.362 |
dx | +0.302 |
Interstitial | +0.294 |
oho | +0.288 |
ttes | +0.283 |
Neg logit contributions | |
Dill | -0.277 |
rimp | -0.269 |
Rivals | -0.263 |
rans | -0.257 |
Switch | -0.256 |
Token | or |
Token ID | 393 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
Dill | +2.538 |
rimp | +2.348 |
replace | +2.328 |
Switch | +2.315 |
Rivals | +2.313 |
Neg logit contributions | |
bys | -3.934 |
dx | -3.326 |
Interstitial | -3.299 |
oho | -3.229 |
staking | -3.110 |
Token | peanut |
Token ID | 26636 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
bys | +0.192 |
dx | +0.164 |
Interstitial | +0.159 |
oho | +0.157 |
ttes | +0.153 |
Neg logit contributions | |
Dill | -0.115 |
rimp | -0.111 |
Rivals | -0.109 |
Switch | -0.106 |
replace | -0.105 |
Token | butter |
Token ID | 9215 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Dill | +1.292 |
rimp | +1.209 |
Rivals | +1.186 |
Switch | +1.158 |
replace | +1.156 |
Neg logit contributions | |
bys | -2.597 |
dx | -2.242 |
Interstitial | -2.192 |
oho | -2.145 |
ttes | -2.106 |
Token | sandwich |
Token ID | 20433 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
Dill | +1.299 |
rimp | +1.222 |
Rivals | +1.219 |
Switch | +1.182 |
replace | +1.176 |
Neg logit contributions | |
bys | -2.224 |
dx | -1.896 |
Interstitial | -1.850 |
oho | -1.822 |
ttes | -1.773 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
Dill | +0.982 |
rimp | +0.930 |
Rivals | +0.925 |
Switch | +0.903 |
replace | +0.901 |
Neg logit contributions | |
bys | -1.328 |
dx | -1.118 |
Interstitial | -1.093 |
oho | -1.074 |
ttes | -1.033 |
Token | of |
Token ID | 286 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
Dill | +0.230 |
rimp | +0.223 |
Rivals | +0.221 |
Switch | +0.214 |
rans | +0.213 |
Neg logit contributions | |
bys | -0.275 |
dx | -0.228 |
Interstitial | -0.220 |
oho | -0.217 |
ttes | -0.212 |
Token | homeless |
Token ID | 10463 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
Dill | +0.103 |
rimp | +0.098 |
Rivals | +0.098 |
Switch | +0.095 |
rans | +0.094 |
Neg logit contributions | |
bys | -0.172 |
dx | -0.147 |
Interstitial | -0.143 |
oho | -0.140 |
ttes | -0.138 |
Token | families |
Token ID | 4172 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
Dill | +1.055 |
Rivals | +1.013 |
rimp | +1.012 |
Switch | +0.983 |
rans | +0.979 |
Neg logit contributions | |
bys | -1.262 |
dx | -1.060 |
Interstitial | -1.039 |
oho | -1.013 |
ttes | -0.980 |
Token | was |
Token ID | 373 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Dill | +0.629 |
rimp | +0.607 |
Rivals | +0.602 |
Switch | +0.586 |
rans | +0.582 |
Neg logit contributions | |
bys | -0.848 |
dx | -0.711 |
Interstitial | -0.693 |
oho | -0.680 |
ttes | -0.667 |
Token | creeping |
Token ID | 38598 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
Dill | +0.021 |
rimp | +0.021 |
Rivals | +0.021 |
Switch | +0.020 |
rans | +0.020 |
Neg logit contributions | |
bys | -0.036 |
dx | -0.030 |
Interstitial | -0.030 |
oho | -0.029 |
ttes | -0.029 |
Token | upward |
Token ID | 18644 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Dill | +0.822 |
rimp | +0.780 |
Rivals | +0.779 |
Switch | +0.751 |
replace | +0.742 |
Neg logit contributions | |
bys | -1.590 |
dx | -1.366 |
Interstitial | -1.340 |
oho | -1.324 |
ttes | -1.299 |
Token | again |
Token ID | 757 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Dill | +2.619 |
Rivals | +2.542 |
rimp | +2.528 |
Switch | +2.476 |
replace | +2.466 |
Neg logit contributions | |
bys | -3.740 |
dx | -3.154 |
Interstitial | -3.097 |
oho | -3.064 |
ttes | -2.982 |
Token | . |
Token ID | 13 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
Dill | +0.658 |
rimp | +0.640 |
Rivals | +0.633 |
Switch | +0.616 |
rans | +0.614 |
Neg logit contributions | |
bys | -0.855 |
dx | -0.713 |
Interstitial | -0.693 |
oho | -0.683 |
ttes | -0.668 |
Token |
|
Token ID | 198 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Dill | +0.541 |
Rivals | +0.524 |
rimp | +0.514 |
Switch | +0.507 |
Marijuana | +0.492 |
Neg logit contributions | |
bys | -0.799 |
dx | -0.675 |
Interstitial | -0.657 |
oho | -0.647 |
ttes | -0.635 |
Token |
|
Token ID | 198 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Dill | +0.357 |
Rivals | +0.346 |
rimp | +0.346 |
Switch | +0.338 |
Marsh | +0.334 |
Neg logit contributions | |
bys | -0.387 |
dx | -0.315 |
Interstitial | -0.309 |
oho | -0.307 |
staking | -0.300 |
Token | Last |
Token ID | 5956 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
Dill | +0.365 |
rimp | +0.358 |
Rivals | +0.354 |
Marsh | +0.345 |
Switch | +0.340 |
Neg logit contributions | |
bys | -0.557 |
dx | -0.471 |
oho | -0.455 |
Interstitial | -0.454 |
ttes | -0.447 |
Token | Doctor |
Token ID | 9356 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Dill | +0.683 |
rimp | +0.656 |
Rivals | +0.653 |
Switch | +0.629 |
rans | +0.624 |
Neg logit contributions | |
bys | -0.974 |
dx | -0.820 |
Interstitial | -0.796 |
oho | -0.783 |
ttes | -0.767 |
Token | ), |
Token ID | 828 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
bys | +0.542 |
dx | +0.460 |
Interstitial | +0.445 |
oho | +0.440 |
ttes | +0.432 |
Neg logit contributions | |
Dill | -0.343 |
rimp | -0.331 |
Rivals | -0.328 |
Switch | -0.315 |
rans | -0.313 |
Token | around |
Token ID | 1088 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
Dill | +0.237 |
Rivals | +0.224 |
rimp | +0.224 |
Switch | +0.217 |
rans | +0.214 |
Neg logit contributions | |
bys | -0.362 |
dx | -0.308 |
Interstitial | -0.299 |
oho | -0.294 |
ttes | -0.289 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
bys | +0.183 |
dx | +0.157 |
Interstitial | +0.152 |
oho | +0.149 |
ttes | +0.146 |
Neg logit contributions | |
Dill | -0.113 |
Rivals | -0.107 |
rimp | -0.106 |
Switch | -0.103 |
rans | -0.102 |
Token | fifth |
Token ID | 8150 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Dill | +0.155 |
Rivals | +0.148 |
rimp | +0.147 |
Switch | +0.143 |
rans | +0.140 |
Neg logit contributions | |
bys | -0.271 |
dx | -0.231 |
Interstitial | -0.225 |
oho | -0.221 |
ttes | -0.216 |
Token | episode |
Token ID | 4471 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Dill | +0.308 |
Rivals | +0.295 |
rimp | +0.295 |
Switch | +0.286 |
rans | +0.283 |
Neg logit contributions | |
bys | -0.430 |
dx | -0.364 |
Interstitial | -0.352 |
oho | -0.345 |
ttes | -0.339 |
Token | in |
Token ID | 287 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Dill | +2.637 |
Rivals | +2.494 |
Switch | +2.445 |
rimp | +2.444 |
rans | +2.400 |
Neg logit contributions | |
bys | -3.779 |
dx | -3.212 |
Interstitial | -3.095 |
oho | -3.030 |
ttes | -2.912 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Dill | +0.344 |
Rivals | +0.328 |
rimp | +0.324 |
Switch | +0.315 |
rans | +0.310 |
Neg logit contributions | |
bys | -0.601 |
dx | -0.516 |
Interstitial | -0.499 |
oho | -0.491 |
ttes | -0.481 |
Token | when |
Token ID | 618 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
Dill | +0.195 |
rimp | +0.186 |
Rivals | +0.186 |
Switch | +0.179 |
rans | +0.178 |
Neg logit contributions | |
bys | -0.298 |
dx | -0.254 |
Interstitial | -0.245 |
oho | -0.242 |
ttes | -0.237 |
Token | we |
Token ID | 356 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Dill | +1.015 |
Rivals | +0.966 |
rimp | +0.959 |
Switch | +0.933 |
rans | +0.923 |
Neg logit contributions | |
bys | -1.481 |
dx | -1.252 |
Interstitial | -1.216 |
oho | -1.194 |
ttes | -1.167 |
Token | were |
Token ID | 547 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Dill | +0.277 |
rimp | +0.267 |
Rivals | +0.264 |
Switch | +0.257 |
replace | +0.257 |
Neg logit contributions | |
bys | -0.400 |
dx | -0.338 |
Interstitial | -0.330 |
oho | -0.322 |
ttes | -0.313 |
Token | iff |
Token ID | 733 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
bys | +0.300 |
dx | +0.252 |
Interstitial | +0.245 |
oho | +0.241 |
ttes | +0.237 |
Neg logit contributions | |
Dill | -0.209 |
rimp | -0.206 |
Rivals | -0.201 |
rans | -0.193 |
Switch | -0.193 |
Token | Tra |
Token ID | 15721 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
bys | +1.569 |
dx | +1.334 |
Interstitial | +1.294 |
oho | +1.282 |
ttes | +1.255 |
Neg logit contributions | |
Dill | -0.931 |
rimp | -0.901 |
Rivals | -0.890 |
Switch | -0.854 |
rans | -0.850 |
Token | x |
Token ID | 87 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
bys | +0.622 |
dx | +0.507 |
Interstitial | +0.504 |
oho | +0.493 |
ttes | +0.475 |
Neg logit contributions | |
Dill | -0.533 |
rimp | -0.521 |
Rivals | -0.512 |
rans | -0.501 |
Switch | -0.498 |
Token |
|
Token ID | 198 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
bys | +0.648 |
dx | +0.525 |
Interstitial | +0.504 |
oho | +0.497 |
ttes | +0.483 |
Neg logit contributions | |
Dill | -0.674 |
rimp | -0.659 |
Rivals | -0.651 |
Switch | -0.632 |
rans | -0.631 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Dill | +0.425 |
rimp | +0.411 |
Rivals | +0.411 |
Switch | +0.402 |
Marsh | +0.396 |
Neg logit contributions | |
bys | -0.466 |
dx | -0.380 |
Interstitial | -0.376 |
oho | -0.371 |
staking | -0.364 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Dill | +0.214 |
rimp | +0.204 |
Rivals | +0.197 |
rans | +0.184 |
Switch | +0.182 |
Neg logit contributions | |
bys | -0.800 |
dx | -0.704 |
Interstitial | -0.687 |
oho | -0.684 |
ttes | -0.674 |
Token | : |
Token ID | 25 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
Dill | +2.660 |
Rivals | +2.568 |
rimp | +2.554 |
Switch | +2.543 |
vs | +2.479 |
Neg logit contributions | |
bys | -3.576 |
Interstitial | -3.074 |
staking | -3.024 |
dx | -2.982 |
oho | -2.943 |
Token | V |
Token ID | 569 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
bys | +0.071 |
dx | +0.061 |
Interstitial | +0.059 |
oho | +0.058 |
ttes | +0.057 |
Neg logit contributions | |
Dill | -0.043 |
rimp | -0.041 |
Rivals | -0.041 |
Switch | -0.039 |
rans | -0.039 |
Token | the |
Token ID | 1169 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
bys | +0.184 |
dx | +0.154 |
Interstitial | +0.149 |
oho | +0.147 |
ttes | +0.144 |
Neg logit contributions | |
Dill | -0.137 |
rimp | -0.133 |
Rivals | -0.131 |
rans | -0.126 |
Switch | -0.126 |
Token | Happy |
Token ID | 25082 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
Dill | +0.095 |
rimp | +0.092 |
Rivals | +0.091 |
Switch | +0.088 |
rans | +0.087 |
Neg logit contributions | |
bys | -0.130 |
dx | -0.109 |
Interstitial | -0.105 |
oho | -0.104 |
ttes | -0.102 |
Token | L |
Token ID | 43 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
Dill | +1.019 |
rimp | +0.989 |
Rivals | +0.975 |
Switch | +0.941 |
rans | +0.935 |
Neg logit contributions | |
bys | -1.491 |
dx | -1.260 |
Interstitial | -1.217 |
oho | -1.207 |
ttes | -1.180 |
Token | for |
Token ID | 329 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Dill | +1.485 |
rimp | +1.414 |
Rivals | +1.407 |
Switch | +1.385 |
rans | +1.364 |
Neg logit contributions | |
bys | -2.079 |
dx | -1.770 |
Interstitial | -1.732 |
oho | -1.670 |
ttes | -1.652 |
Token | talks |
Token ID | 6130 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
Dill | +0.134 |
rimp | +0.126 |
Rivals | +0.126 |
Switch | +0.122 |
rans | +0.120 |
Neg logit contributions | |
bys | -0.238 |
dx | -0.205 |
Interstitial | -0.200 |
oho | -0.196 |
ttes | -0.192 |
Token | with |
Token ID | 351 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
bys | +0.577 |
dx | +0.484 |
Interstitial | +0.471 |
oho | +0.461 |
ttes | +0.452 |
Neg logit contributions | |
Dill | -0.431 |
rimp | -0.416 |
Rivals | -0.414 |
Switch | -0.400 |
rans | -0.398 |
Token | President |
Token ID | 1992 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
bys | +0.225 |
dx | +0.194 |
Interstitial | +0.189 |
oho | +0.186 |
ttes | +0.184 |
Neg logit contributions | |
Dill | -0.107 |
rimp | -0.101 |
Rivals | -0.101 |
Switch | -0.096 |
rans | -0.095 |
Token | Recep |
Token ID | 44970 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
bys | +1.641 |
dx | +1.395 |
Interstitial | +1.348 |
oho | +1.344 |
ttes | +1.311 |
Neg logit contributions | |
Dill | -0.999 |
rimp | -0.971 |
Rivals | -0.960 |
Switch | -0.915 |
rans | -0.914 |
Token | Tayyip |
Token ID | 41346 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Dill | +1.454 |
rimp | +1.351 |
Rivals | +1.346 |
Switch | +1.306 |
rans | +1.277 |
Neg logit contributions | |
bys | -3.069 |
dx | -2.631 |
Interstitial | -2.602 |
oho | -2.524 |
ttes | -2.518 |
Token | Erdogan |
Token ID | 20065 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Dill | +2.376 |
Rivals | +2.228 |
rimp | +2.222 |
Switch | +2.172 |
rans | +2.131 |
Neg logit contributions | |
bys | -4.067 |
dx | -3.481 |
Interstitial | -3.411 |
oho | -3.292 |
ttes | -3.287 |
Token | on |
Token ID | 319 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
Dill | +1.540 |
rimp | +1.479 |
Rivals | +1.474 |
Switch | +1.441 |
replace | +1.427 |
Neg logit contributions | |
bys | -2.181 |
dx | -1.850 |
Interstitial | -1.803 |
oho | -1.739 |
ttes | -1.729 |
Token | Saturday |
Token ID | 3909 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
bys | +0.033 |
dx | +0.028 |
Interstitial | +0.027 |
oho | +0.026 |
ttes | +0.026 |
Neg logit contributions | |
Dill | -0.024 |
rimp | -0.023 |
Rivals | -0.023 |
Switch | -0.022 |
rans | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
bys | +0.602 |
dx | +0.505 |
Interstitial | +0.487 |
oho | +0.478 |
ttes | +0.470 |
Neg logit contributions | |
Dill | -0.469 |
rimp | -0.453 |
Rivals | -0.450 |
Switch | -0.436 |
rans | -0.433 |
Token | where |
Token ID | 810 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
bys | +0.100 |
dx | +0.084 |
Interstitial | +0.081 |
oho | +0.080 |
ttes | +0.079 |
Neg logit contributions | |
Dill | -0.069 |
rimp | -0.067 |
Rivals | -0.066 |
Switch | -0.064 |
rans | -0.063 |
Token | Rob |
Token ID | 3851 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
Dill | +0.496 |
Rivals | +0.462 |
rimp | +0.456 |
Switch | +0.452 |
replace | +0.437 |
Neg logit contributions | |
bys | -0.865 |
dx | -0.737 |
Interstitial | -0.711 |
oho | -0.702 |
ttes | -0.690 |
Token | H |
Token ID | 367 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
bys | +0.147 |
dx | +0.125 |
Interstitial | +0.121 |
oho | +0.119 |
ttes | +0.117 |
Neg logit contributions | |
Dill | -0.101 |
rimp | -0.097 |
Rivals | -0.096 |
Switch | -0.093 |
rans | -0.092 |
Token | oe |
Token ID | 2577 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
Dill | +0.423 |
rimp | +0.407 |
Rivals | +0.400 |
rans | +0.391 |
Switch | +0.388 |
Neg logit contributions | |
bys | -0.631 |
dx | -0.532 |
Interstitial | -0.524 |
oho | -0.505 |
ttes | -0.500 |
Token | gee |
Token ID | 29622 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
bys | +1.061 |
dx | +0.887 |
Interstitial | +0.854 |
oho | +0.845 |
ttes | +0.827 |
Neg logit contributions | |
Dill | -0.818 |
rimp | -0.794 |
Rivals | -0.786 |
Switch | -0.759 |
rans | -0.755 |
Token | 's |
Token ID | 338 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
bys | +0.122 |
dx | +0.103 |
Interstitial | +0.100 |
oho | +0.099 |
ttes | +0.097 |
Neg logit contributions | |
Dill | -0.080 |
rimp | -0.077 |
Rivals | -0.076 |
Switch | -0.074 |
rans | -0.073 |
Token | episode |
Token ID | 4471 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Dill | +0.390 |
Rivals | +0.370 |
rimp | +0.367 |
Switch | +0.356 |
replace | +0.346 |
Neg logit contributions | |
bys | -0.776 |
dx | -0.670 |
Interstitial | -0.650 |
oho | -0.640 |
ttes | -0.631 |
Token | and |
Token ID | 290 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
Dill | +2.601 |
Rivals | +2.467 |
Switch | +2.420 |
rimp | +2.381 |
rans | +2.357 |
Neg logit contributions | |
bys | -3.738 |
dx | -3.143 |
Interstitial | -3.047 |
oho | -2.990 |
ttes | -2.864 |
Token | I |
Token ID | 314 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
bys | +0.159 |
dx | +0.135 |
Interstitial | +0.130 |
oho | +0.129 |
ttes | +0.126 |
Neg logit contributions | |
Dill | -0.101 |
Rivals | -0.096 |
rimp | -0.095 |
Switch | -0.093 |
rans | -0.091 |
Token | think |
Token ID | 892 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Dill | +0.046 |
rimp | +0.045 |
Rivals | +0.044 |
Switch | +0.043 |
rans | +0.043 |
Neg logit contributions | |
bys | -0.056 |
dx | -0.046 |
Interstitial | -0.045 |
oho | -0.044 |
ttes | -0.043 |
Token | it |
Token ID | 340 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Dill | +0.550 |
Rivals | +0.522 |
rimp | +0.511 |
Switch | +0.504 |
rans | +0.494 |
Neg logit contributions | |
bys | -0.859 |
dx | -0.730 |
Interstitial | -0.707 |
oho | -0.694 |
ttes | -0.682 |
Token | 's |
Token ID | 338 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
Dill | +0.316 |
Rivals | +0.300 |
rimp | +0.299 |
Switch | +0.289 |
rans | +0.287 |
Neg logit contributions | |
bys | -0.486 |
dx | -0.414 |
Interstitial | -0.405 |
oho | -0.395 |
ttes | -0.387 |
Token | 's |
Token ID | 338 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
bys | +1.166 |
dx | +0.988 |
Interstitial | +0.956 |
oho | +0.942 |
ttes | +0.924 |
Neg logit contributions | |
Dill | -0.772 |
rimp | -0.742 |
Rivals | -0.737 |
Switch | -0.710 |
rans | -0.706 |
Token | death |
Token ID | 1918 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Dill | +0.443 |
Rivals | +0.425 |
rimp | +0.424 |
Switch | +0.414 |
replace | +0.407 |
Neg logit contributions | |
bys | -0.540 |
dx | -0.452 |
Interstitial | -0.436 |
oho | -0.426 |
ttes | -0.418 |
Token | in |
Token ID | 287 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Dill | +0.478 |
Rivals | +0.454 |
rimp | +0.451 |
Switch | +0.439 |
rans | +0.438 |
Neg logit contributions | |
bys | -0.637 |
dx | -0.535 |
Interstitial | -0.521 |
oho | -0.508 |
ttes | -0.495 |
Token | the |
Token ID | 262 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
Dill | +0.270 |
Rivals | +0.259 |
rimp | +0.257 |
Switch | +0.249 |
rans | +0.244 |
Neg logit contributions | |
bys | -0.424 |
dx | -0.360 |
Interstitial | -0.350 |
oho | -0.343 |
ttes | -0.336 |
Token | second |
Token ID | 1218 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Dill | +0.057 |
rimp | +0.055 |
Rivals | +0.054 |
Switch | +0.052 |
rans | +0.052 |
Neg logit contributions | |
bys | -0.095 |
dx | -0.081 |
Interstitial | -0.078 |
oho | -0.077 |
ttes | -0.076 |
Token | episode |
Token ID | 4471 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
bys | +0.227 |
dx | +0.195 |
Interstitial | +0.189 |
oho | +0.186 |
ttes | +0.183 |
Neg logit contributions | |
Dill | -0.121 |
rimp | -0.115 |
Rivals | -0.115 |
Switch | -0.110 |
rans | -0.109 |
Token | of |
Token ID | 286 |
Feature activation | -4.05e-04 |
Pos logit contributions | |
Dill | +2.591 |
Rivals | +2.475 |
Switch | +2.417 |
rimp | +2.413 |
Anonymous | +2.363 |
Neg logit contributions | |
bys | -3.677 |
dx | -3.115 |
Interstitial | -3.010 |
oho | -2.938 |
ttes | -2.830 |
Token | M |
Token ID | 337 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Dill | +0.000 |
rimp | +0.000 |
Rivals | +0.000 |
Switch | +0.000 |
rans | +0.000 |
Neg logit contributions | |
bys | -0.001 |
dx | -0.001 |
Interstitial | -0.001 |
oho | -0.001 |
ttes | -0.001 |
Token | upp |
Token ID | 7211 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
Dill | +0.062 |
rimp | +0.056 |
Rivals | +0.055 |
Switch | +0.049 |
rans | +0.048 |
Neg logit contributions | |
bys | -0.349 |
dx | -0.311 |
Interstitial | -0.304 |
oho | -0.302 |
ttes | -0.298 |
Token | ets |
Token ID | 1039 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Dill | +1.663 |
Rivals | +1.637 |
rimp | +1.635 |
rans | +1.587 |
Switch | +1.570 |
Neg logit contributions | |
bys | -1.598 |
Interstitial | -1.331 |
dx | -1.294 |
oho | -1.208 |
staking | -1.200 |
Token | Tonight |
Token ID | 27117 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
Dill | +0.263 |
Rivals | +0.254 |
rimp | +0.253 |
Switch | +0.244 |
rans | +0.241 |
Neg logit contributions | |
bys | -0.406 |
dx | -0.345 |
Interstitial | -0.334 |
oho | -0.329 |
ttes | -0.322 |
Token | — |
Token ID | 851 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Dill | +1.305 |
rimp | +1.261 |
Rivals | +1.230 |
replace | +1.204 |
Switch | +1.203 |
Neg logit contributions | |
bys | -1.787 |
dx | -1.515 |
Interstitial | -1.477 |
oho | -1.447 |
ttes | -1.398 |
Token | � |
Token ID | 564 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
Dill | +0.149 |
rimp | +0.144 |
Rivals | +0.142 |
Switch | +0.137 |
rans | +0.135 |
Neg logit contributions | |
bys | -0.230 |
dx | -0.196 |
Interstitial | -0.190 |
oho | -0.187 |
ttes | -0.183 |
Token | � |
Token ID | 250 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Dill | +0.032 |
rimp | +0.031 |
Rivals | +0.031 |
Switch | +0.030 |
rans | +0.029 |
Neg logit contributions | |
bys | -0.055 |
dx | -0.047 |
Interstitial | -0.045 |
oho | -0.045 |
ttes | -0.044 |
Token | t |
Token ID | 83 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Dill | +0.343 |
rimp | +0.334 |
Rivals | +0.330 |
rans | +0.320 |
Switch | +0.319 |
Neg logit contributions | |
bys | -0.420 |
dx | -0.348 |
Interstitial | -0.336 |
oho | -0.330 |
ttes | -0.323 |
Token | iger |
Token ID | 8254 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Dill | +0.381 |
rimp | +0.370 |
Rivals | +0.363 |
rans | +0.352 |
Switch | +0.352 |
Neg logit contributions | |
bys | -0.532 |
dx | -0.447 |
Interstitial | -0.434 |
oho | -0.424 |
ttes | -0.418 |
Token | salad |
Token ID | 20698 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
bys | +0.428 |
dx | +0.361 |
Interstitial | +0.350 |
oho | +0.346 |
ttes | +0.338 |
Neg logit contributions | |
Dill | -0.291 |
rimp | -0.282 |
Rivals | -0.278 |
Switch | -0.269 |
rans | -0.266 |
Token | � |
Token ID | 447 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Dill | +2.606 |
rimp | +2.568 |
Rivals | +2.480 |
replace | +2.460 |
Switch | +2.423 |
Neg logit contributions | |
bys | -3.550 |
dx | -2.990 |
Interstitial | -2.948 |
oho | -2.877 |
staking | -2.752 |
Token | � |
Token ID | 251 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
bys | +0.357 |
dx | +0.303 |
Interstitial | +0.296 |
oho | +0.290 |
ttes | +0.285 |
Neg logit contributions | |
Dill | -0.212 |
rimp | -0.206 |
Rivals | -0.204 |
Switch | -0.196 |
rans | -0.193 |
Token | — |
Token ID | 851 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Dill | +0.321 |
rimp | +0.313 |
Rivals | +0.308 |
Switch | +0.298 |
rans | +0.297 |
Neg logit contributions | |
bys | -0.406 |
dx | -0.339 |
Interstitial | -0.329 |
oho | -0.323 |
ttes | -0.314 |
Token | that |
Token ID | 326 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
bys | +0.439 |
dx | +0.368 |
Interstitial | +0.356 |
oho | +0.351 |
ttes | +0.343 |
Neg logit contributions | |
Dill | -0.335 |
rimp | -0.326 |
Rivals | -0.321 |
Switch | -0.310 |
rans | -0.309 |
Token | is |
Token ID | 318 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
bys | +0.084 |
dx | +0.072 |
Interstitial | +0.070 |
oho | +0.068 |
ttes | +0.067 |
Neg logit contributions | |
Dill | -0.055 |
rimp | -0.053 |
Rivals | -0.052 |
Switch | -0.050 |
rans | -0.050 |
Token | ank |
Token ID | 962 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Dill | +0.397 |
rimp | +0.389 |
Rivals | +0.374 |
rans | +0.364 |
Switch | +0.362 |
Neg logit contributions | |
bys | -0.712 |
dx | -0.608 |
Interstitial | -0.594 |
oho | -0.579 |
ttes | -0.577 |
Token | ering |
Token ID | 1586 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
bys | +0.323 |
dx | +0.276 |
Interstitial | +0.266 |
oho | +0.264 |
ttes | +0.259 |
Neg logit contributions | |
Dill | -0.191 |
rimp | -0.184 |
Rivals | -0.182 |
Switch | -0.174 |
rans | -0.173 |
Token | for |
Token ID | 329 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
bys | +2.109 |
dx | +1.747 |
Interstitial | +1.681 |
oho | +1.662 |
ttes | +1.626 |
Neg logit contributions | |
Dill | -1.760 |
rimp | -1.714 |
Rivals | -1.698 |
Switch | -1.639 |
rans | -1.634 |
Token | a |
Token ID | 257 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Dill | +0.257 |
rimp | +0.243 |
Rivals | +0.242 |
Switch | +0.233 |
replace | +0.229 |
Neg logit contributions | |
bys | -0.448 |
dx | -0.384 |
Interstitial | -0.374 |
oho | -0.368 |
ttes | -0.361 |
Token | c |
Token ID | 269 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
bys | +0.243 |
dx | +0.206 |
Interstitial | +0.200 |
oho | +0.197 |
ttes | +0.194 |
Neg logit contributions | |
Dill | -0.159 |
rimp | -0.152 |
Rivals | -0.151 |
Switch | -0.146 |
rans | -0.144 |
Token | upp |
Token ID | 7211 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
bys | +0.782 |
dx | +0.664 |
Interstitial | +0.644 |
oho | +0.634 |
ttes | +0.624 |
Neg logit contributions | |
Dill | -0.490 |
rimp | -0.476 |
Rivals | -0.467 |
Switch | -0.449 |
rans | -0.448 |
Token | a |
Token ID | 64 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
Dill | +3.197 |
rimp | +3.178 |
rans | +3.085 |
Rivals | +3.062 |
Switch | +3.018 |
Neg logit contributions | |
bys | -2.851 |
Interstitial | -2.345 |
dx | -2.296 |
ttes | -2.147 |
oho | -2.087 |
Token | . |
Token ID | 13 |
Feature activation | -7.76e-03 |
Pos logit contributions | |
Dill | +0.015 |
rimp | +0.014 |
Rivals | +0.014 |
Switch | +0.014 |
rans | +0.013 |
Neg logit contributions | |
bys | -0.021 |
dx | -0.017 |
Interstitial | -0.017 |
oho | -0.017 |
ttes | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
Dill | +0.010 |
Rivals | +0.010 |
rimp | +0.010 |
Switch | +0.010 |
Anonymous | +0.009 |
Neg logit contributions | |
bys | -0.016 |
dx | -0.014 |
Interstitial | -0.013 |
oho | -0.013 |
ttes | -0.013 |
Token | cookies |
Token ID | 14746 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
Dill | +0.037 |
rimp | +0.035 |
Rivals | +0.035 |
Switch | +0.034 |
rans | +0.033 |
Neg logit contributions | |
bys | -0.058 |
dx | -0.049 |
Interstitial | -0.048 |
oho | -0.047 |
ttes | -0.046 |
Token | were |
Token ID | 547 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Dill | +0.604 |
rimp | +0.581 |
Rivals | +0.573 |
replace | +0.561 |
Switch | +0.556 |
Neg logit contributions | |
bys | -0.769 |
dx | -0.645 |
Interstitial | -0.632 |
oho | -0.611 |
ttes | -0.596 |
Token | , |
Token ID | 11 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
Dill | +0.001 |
Rivals | +0.001 |
rimp | +0.001 |
Switch | +0.001 |
replace | +0.001 |
Neg logit contributions | |
bys | -0.001 |
dx | -0.001 |
Interstitial | -0.001 |
oho | -0.001 |
ttes | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
bys | +0.181 |
dx | +0.154 |
Interstitial | +0.150 |
oho | +0.147 |
ttes | +0.144 |
Neg logit contributions | |
Dill | -0.117 |
Rivals | -0.110 |
rimp | -0.109 |
Switch | -0.107 |
rans | -0.104 |
Token | end |
Token ID | 886 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
Dill | +0.131 |
Rivals | +0.124 |
rimp | +0.124 |
Switch | +0.120 |
rans | +0.117 |
Neg logit contributions | |
bys | -0.227 |
dx | -0.194 |
Interstitial | -0.189 |
oho | -0.185 |
ttes | -0.182 |
Token | of |
Token ID | 286 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Dill | +0.038 |
rimp | +0.036 |
Rivals | +0.036 |
Switch | +0.035 |
rans | +0.035 |
Neg logit contributions | |
bys | -0.050 |
dx | -0.043 |
Interstitial | -0.041 |
oho | -0.040 |
ttes | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
Dill | +0.300 |
Rivals | +0.284 |
rimp | +0.283 |
Switch | +0.272 |
rans | +0.267 |
Neg logit contributions | |
bys | -0.548 |
dx | -0.471 |
Interstitial | -0.457 |
oho | -0.451 |
ttes | -0.442 |
Token | episode |
Token ID | 4471 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Dill | +0.450 |
Rivals | +0.428 |
rimp | +0.426 |
Switch | +0.411 |
rans | +0.404 |
Neg logit contributions | |
bys | -0.803 |
dx | -0.688 |
Interstitial | -0.668 |
oho | -0.657 |
ttes | -0.647 |
Token | is |
Token ID | 318 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Dill | +2.410 |
Rivals | +2.252 |
Switch | +2.212 |
rimp | +2.202 |
replace | +2.180 |
Neg logit contributions | |
bys | -3.754 |
dx | -3.223 |
Interstitial | -3.162 |
oho | -3.072 |
ttes | -2.956 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Dill | +0.248 |
Rivals | +0.235 |
rimp | +0.232 |
Switch | +0.229 |
replace | +0.223 |
Neg logit contributions | |
bys | -0.412 |
dx | -0.352 |
Interstitial | -0.341 |
oho | -0.335 |
ttes | -0.327 |
Token | c |
Token ID | 269 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
Dill | +0.187 |
Rivals | +0.177 |
rimp | +0.176 |
Switch | +0.170 |
rans | +0.165 |
Neg logit contributions | |
bys | -0.399 |
dx | -0.345 |
Interstitial | -0.336 |
oho | -0.331 |
ttes | -0.326 |
Token | oda |
Token ID | 11329 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
bys | +0.052 |
dx | +0.044 |
Interstitial | +0.043 |
oho | +0.042 |
ttes | +0.042 |
Neg logit contributions | |
Dill | -0.032 |
rimp | -0.031 |
Rivals | -0.030 |
Switch | -0.029 |
rans | -0.029 |
Token | for |
Token ID | 329 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Dill | +1.941 |
Rivals | +1.823 |
Switch | +1.798 |
rimp | +1.783 |
replace | +1.768 |
Neg logit contributions | |
bys | -2.668 |
dx | -2.245 |
Interstitial | -2.173 |
oho | -2.155 |
ttes | -2.073 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Dill | +0.932 |
rimp | +0.906 |
Rivals | +0.899 |
Switch | +0.877 |
rans | +0.867 |
Neg logit contributions | |
bys | -1.079 |
dx | -0.897 |
Interstitial | -0.862 |
oho | -0.858 |
ttes | -0.835 |
Token |
|
Token ID | 198 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
bys | +0.172 |
dx | +0.140 |
Interstitial | +0.135 |
oho | +0.135 |
ttes | +0.131 |
Neg logit contributions | |
Dill | -0.170 |
Rivals | -0.165 |
rimp | -0.164 |
Switch | -0.160 |
Marsh | -0.159 |
Token | Subscribe |
Token ID | 27125 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
bys | +0.020 |
dx | +0.017 |
Interstitial | +0.016 |
oho | +0.016 |
ttes | +0.016 |
Neg logit contributions | |
Dill | -0.012 |
rimp | -0.012 |
Rivals | -0.012 |
Switch | -0.011 |
rans | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
Dill | +1.026 |
rimp | +0.992 |
Rivals | +0.986 |
Switch | +0.961 |
Ames | +0.940 |
Neg logit contributions | |
bys | -1.367 |
dx | -1.161 |
Interstitial | -1.119 |
oho | -1.103 |
ttes | -1.089 |
Token | C |
Token ID | 327 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
Dill | +0.326 |
Rivals | +0.313 |
rimp | +0.311 |
Switch | +0.301 |
replace | +0.295 |
Neg logit contributions | |
bys | -0.567 |
dx | -0.486 |
Interstitial | -0.472 |
oho | -0.468 |
ttes | -0.456 |
Token | rave |
Token ID | 5758 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Dill | +0.069 |
rimp | +0.069 |
Rivals | +0.066 |
Switch | +0.064 |
rans | +0.063 |
Neg logit contributions | |
bys | -0.118 |
dx | -0.100 |
Interstitial | -0.097 |
oho | -0.094 |
ttes | -0.094 |
Token | : |
Token ID | 25 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
Dill | +2.363 |
Rivals | +2.280 |
Switch | +2.221 |
rimp | +2.191 |
Marsh | +2.177 |
Neg logit contributions | |
bys | -3.667 |
dx | -3.131 |
Interstitial | -3.096 |
oho | -3.046 |
staking | -2.932 |
Token |
|
Token ID | 198 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
bys | +0.159 |
dx | +0.134 |
Interstitial | +0.129 |
oho | +0.128 |
ttes | +0.126 |
Neg logit contributions | |
Dill | -0.112 |
rimp | -0.108 |
Rivals | -0.107 |
Switch | -0.103 |
rans | -0.102 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Dill | +0.031 |
Rivals | +0.030 |
rimp | +0.030 |
Switch | +0.029 |
Marsh | +0.029 |
Neg logit contributions | |
bys | -0.033 |
dx | -0.027 |
Interstitial | -0.026 |
oho | -0.026 |
ttes | -0.025 |
Token | i |
Token ID | 72 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
Dill | +0.167 |
rimp | +0.163 |
Rivals | +0.161 |
Marsh | +0.155 |
rans | +0.155 |
Neg logit contributions | |
bys | -0.261 |
dx | -0.221 |
oho | -0.213 |
Interstitial | -0.212 |
ttes | -0.208 |
Token | T |
Token ID | 51 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Dill | +0.385 |
rimp | +0.372 |
Rivals | +0.367 |
Switch | +0.352 |
rans | +0.350 |
Neg logit contributions | |
bys | -0.634 |
dx | -0.539 |
Interstitial | -0.522 |
oho | -0.516 |
ttes | -0.506 |
Token | mon |
Token ID | 937 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
bys | +1.988 |
dx | +1.699 |
Interstitial | +1.646 |
oho | +1.629 |
ttes | +1.598 |
Neg logit contributions | |
Dill | -1.114 |
rimp | -1.070 |
Rivals | -1.060 |
Switch | -1.015 |
rans | -1.009 |
Token | ologue |
Token ID | 39795 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
bys | +0.694 |
dx | +0.586 |
Interstitial | +0.569 |
oho | +0.557 |
ttes | +0.549 |
Neg logit contributions | |
Dill | -0.454 |
rimp | -0.441 |
Rivals | -0.434 |
Switch | -0.419 |
rans | -0.418 |
Token | in |
Token ID | 287 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Dill | +0.400 |
Rivals | +0.382 |
replace | +0.377 |
rimp | +0.377 |
Switch | +0.374 |
Neg logit contributions | |
bys | -0.579 |
dx | -0.484 |
Interstitial | -0.471 |
oho | -0.465 |
ttes | -0.446 |
Token | the |
Token ID | 262 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
Dill | +0.124 |
rimp | +0.119 |
Rivals | +0.119 |
Switch | +0.114 |
rans | +0.112 |
Neg logit contributions | |
bys | -0.220 |
dx | -0.188 |
Interstitial | -0.183 |
oho | -0.180 |
ttes | -0.176 |
Token | second |
Token ID | 1218 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
bys | +0.058 |
dx | +0.050 |
Interstitial | +0.048 |
oho | +0.048 |
ttes | +0.047 |
Neg logit contributions | |
Dill | -0.033 |
rimp | -0.032 |
Rivals | -0.032 |
Switch | -0.030 |
rans | -0.030 |
Token | episode |
Token ID | 4471 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
bys | +0.435 |
dx | +0.373 |
Interstitial | +0.362 |
oho | +0.358 |
ttes | +0.351 |
Neg logit contributions | |
Dill | -0.232 |
rimp | -0.222 |
Rivals | -0.221 |
Switch | -0.211 |
rans | -0.209 |
Token | of |
Token ID | 286 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
Dill | +2.600 |
Rivals | +2.504 |
rimp | +2.441 |
Switch | +2.440 |
replace | +2.402 |
Neg logit contributions | |
bys | -3.544 |
dx | -2.984 |
Interstitial | -2.868 |
oho | -2.831 |
ttes | -2.697 |
Token | Stat |
Token ID | 5133 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
bys | +0.061 |
dx | +0.052 |
Interstitial | +0.051 |
oho | +0.050 |
ttes | +0.049 |
Neg logit contributions | |
Dill | -0.033 |
rimp | -0.032 |
Rivals | -0.032 |
Switch | -0.030 |
rans | -0.030 |
Token | ler |
Token ID | 1754 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
bys | +0.770 |
dx | +0.646 |
Interstitial | +0.619 |
oho | +0.618 |
ttes | +0.606 |
Neg logit contributions | |
Dill | -0.563 |
rimp | -0.546 |
Rivals | -0.538 |
rans | -0.519 |
Switch | -0.518 |
Token | and |
Token ID | 290 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
Dill | +0.483 |
rimp | +0.464 |
Rivals | +0.463 |
Switch | +0.445 |
rans | +0.443 |
Neg logit contributions | |
bys | -0.732 |
dx | -0.620 |
Interstitial | -0.599 |
oho | -0.593 |
ttes | -0.578 |
Token | Wald |
Token ID | 24261 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Dill | +0.030 |
rimp | +0.029 |
Rivals | +0.028 |
Switch | +0.027 |
rans | +0.027 |
Neg logit contributions | |
bys | -0.055 |
dx | -0.047 |
Interstitial | -0.046 |
oho | -0.045 |
ttes | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
Dill | +1.505 |
rimp | +1.430 |
Rivals | +1.414 |
replace | +1.399 |
Switch | +1.396 |
Neg logit contributions | |
bys | -2.169 |
dx | -1.833 |
Interstitial | -1.795 |
oho | -1.765 |
ttes | -1.724 |
Token | but |
Token ID | 475 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Dill | +0.051 |
rimp | +0.048 |
Rivals | +0.048 |
Switch | +0.047 |
replace | +0.047 |
Neg logit contributions | |
bys | -0.077 |
dx | -0.065 |
Interstitial | -0.064 |
oho | -0.063 |
ttes | -0.062 |
Token | yields |
Token ID | 19299 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
Dill | +0.481 |
rimp | +0.450 |
Rivals | +0.446 |
Switch | +0.437 |
replace | +0.437 |
Neg logit contributions | |
bys | -0.813 |
dx | -0.695 |
Interstitial | -0.682 |
oho | -0.667 |
ttes | -0.651 |
Token | a |
Token ID | 257 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
Dill | +1.022 |
rimp | +0.943 |
Rivals | +0.934 |
Switch | +0.926 |
replace | +0.915 |
Neg logit contributions | |
bys | -1.878 |
dx | -1.612 |
Interstitial | -1.587 |
oho | -1.551 |
ttes | -1.507 |
Token | different |
Token ID | 1180 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
bys | +0.089 |
dx | +0.076 |
Interstitial | +0.074 |
oho | +0.073 |
ttes | +0.072 |
Neg logit contributions | |
Dill | -0.050 |
rimp | -0.048 |
Rivals | -0.047 |
Switch | -0.046 |
rans | -0.045 |
Token | flavor |
Token ID | 9565 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
bys | +0.163 |
dx | +0.138 |
Interstitial | +0.134 |
oho | +0.132 |
ttes | +0.130 |
Neg logit contributions | |
Dill | -0.104 |
rimp | -0.099 |
Rivals | -0.098 |
Switch | -0.096 |
rans | -0.095 |
Token | to |
Token ID | 284 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Dill | +2.423 |
rimp | +2.297 |
rans | +2.266 |
replace | +2.264 |
Switch | +2.261 |
Neg logit contributions | |
bys | -3.691 |
dx | -3.112 |
Interstitial | -3.014 |
oho | -2.981 |
ttes | -2.921 |
Token | the |
Token ID | 262 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
Dill | +0.209 |
rimp | +0.199 |
Rivals | +0.196 |
Switch | +0.191 |
replace | +0.190 |
Neg logit contributions | |
bys | -0.349 |
dx | -0.297 |
Interstitial | -0.290 |
oho | -0.285 |
ttes | -0.280 |
Token | baking |
Token ID | 16871 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
bys | +0.144 |
dx | +0.122 |
Interstitial | +0.119 |
oho | +0.117 |
ttes | +0.115 |
Neg logit contributions | |
Dill | -0.088 |
rimp | -0.083 |
Rivals | -0.083 |
Switch | -0.080 |
replace | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
Dill | +0.232 |
rimp | +0.221 |
Rivals | +0.220 |
Switch | +0.212 |
rans | +0.210 |
Neg logit contributions | |
bys | -0.376 |
dx | -0.321 |
Interstitial | -0.313 |
oho | -0.309 |
ttes | -0.302 |
Token |
|
Token ID | 198 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Dill | +0.125 |
Rivals | +0.118 |
rimp | +0.118 |
Switch | +0.115 |
Ames | +0.112 |
Neg logit contributions | |
bys | -0.206 |
dx | -0.176 |
Interstitial | -0.171 |
oho | -0.168 |
ttes | -0.165 |
Token | research |
Token ID | 2267 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
bys | +0.754 |
dx | +0.643 |
Interstitial | +0.624 |
oho | +0.617 |
ttes | +0.605 |
Neg logit contributions | |
Dill | -0.441 |
rimp | -0.426 |
Rivals | -0.422 |
Switch | -0.404 |
rans | -0.401 |
Token | labs |
Token ID | 27887 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Dill | +0.027 |
rimp | +0.026 |
Rivals | +0.026 |
Switch | +0.025 |
rans | +0.025 |
Neg logit contributions | |
bys | -0.040 |
dx | -0.034 |
Interstitial | -0.033 |
oho | -0.032 |
ttes | -0.031 |
Token | across |
Token ID | 1973 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
bys | +0.487 |
dx | +0.410 |
Interstitial | +0.401 |
oho | +0.394 |
ttes | +0.383 |
Neg logit contributions | |
Dill | -0.340 |
rimp | -0.330 |
Rivals | -0.326 |
Switch | -0.315 |
replace | -0.315 |
Token | the |
Token ID | 262 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
bys | +1.387 |
dx | +1.188 |
Interstitial | +1.152 |
oho | +1.141 |
ttes | +1.120 |
Neg logit contributions | |
Dill | -0.761 |
rimp | -0.733 |
Rivals | -0.724 |
Switch | -0.693 |
rans | -0.688 |
Token | country |
Token ID | 1499 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
bys | +0.315 |
dx | +0.266 |
Interstitial | +0.261 |
oho | +0.257 |
ttes | +0.250 |
Neg logit contributions | |
Dill | -0.197 |
rimp | -0.188 |
Rivals | -0.188 |
Switch | -0.183 |
Ames | -0.179 |
Token | sponsor |
Token ID | 17487 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
bys | +0.875 |
dx | +0.739 |
Interstitial | +0.723 |
oho | +0.707 |
ttes | +0.691 |
Neg logit contributions | |
Dill | -0.574 |
rimp | -0.555 |
Rivals | -0.550 |
Switch | -0.530 |
replace | -0.527 |
Token | similar |
Token ID | 2092 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
bys | +2.111 |
dx | +1.773 |
Interstitial | +1.702 |
oho | +1.688 |
ttes | +1.657 |
Neg logit contributions | |
Dill | -1.554 |
rimp | -1.512 |
Rivals | -1.488 |
rans | -1.435 |
Switch | -1.435 |
Token | contests |
Token ID | 22830 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
bys | +0.066 |
dx | +0.056 |
Interstitial | +0.054 |
oho | +0.053 |
ttes | +0.052 |
Neg logit contributions | |
Dill | -0.047 |
Rivals | -0.045 |
rimp | -0.045 |
Switch | -0.044 |
rans | -0.043 |
Token | on |
Token ID | 319 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
bys | +0.739 |
dx | +0.616 |
Interstitial | +0.599 |
oho | +0.589 |
ttes | +0.575 |
Neg logit contributions | |
Dill | -0.564 |
rimp | -0.547 |
Rivals | -0.540 |
rans | -0.524 |
Switch | -0.523 |
Token | a |
Token ID | 257 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
bys | +0.494 |
dx | +0.420 |
Interstitial | +0.408 |
oho | +0.404 |
ttes | +0.395 |
Neg logit contributions | |
Dill | -0.295 |
rimp | -0.284 |
Rivals | -0.282 |
Switch | -0.271 |
rans | -0.269 |
Token | regular |
Token ID | 3218 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
bys | +0.548 |
dx | +0.464 |
Interstitial | +0.449 |
oho | +0.445 |
ttes | +0.435 |
Neg logit contributions | |
Dill | -0.355 |
rimp | -0.342 |
Rivals | -0.339 |
Switch | -0.326 |
rans | -0.324 |
Token | Yahoo |
Token ID | 16551 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
bys | +0.323 |
dx | +0.277 |
Interstitial | +0.269 |
oho | +0.266 |
ttes | +0.260 |
Neg logit contributions | |
Dill | -0.182 |
rimp | -0.176 |
Rivals | -0.174 |
Switch | -0.167 |
rans | -0.165 |
Token | search |
Token ID | 2989 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
bys | +0.025 |
dx | +0.021 |
Interstitial | +0.020 |
oho | +0.020 |
ttes | +0.020 |
Neg logit contributions | |
Dill | -0.018 |
rimp | -0.017 |
Rivals | -0.017 |
Switch | -0.017 |
rans | -0.017 |
Token | results |
Token ID | 2482 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
bys | +0.710 |
dx | +0.594 |
Interstitial | +0.573 |
oho | +0.566 |
ttes | +0.554 |
Neg logit contributions | |
Dill | -0.539 |
rimp | -0.523 |
Rivals | -0.517 |
Switch | -0.499 |
rans | -0.497 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
bys | +1.760 |
dx | +1.474 |
Interstitial | +1.424 |
oho | +1.409 |
ttes | +1.373 |
Neg logit contributions | |
Dill | -1.322 |
rimp | -1.281 |
Rivals | -1.268 |
Switch | -1.227 |
rans | -1.218 |
Token | targeted |
Token ID | 7977 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
bys | +0.273 |
dx | +0.232 |
Interstitial | +0.224 |
oho | +0.223 |
ttes | +0.217 |
Neg logit contributions | |
Dill | -0.164 |
rimp | -0.158 |
Rivals | -0.157 |
Switch | -0.152 |
replace | -0.151 |
Token | ads |
Token ID | 9011 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
bys | +0.778 |
dx | +0.656 |
Interstitial | +0.632 |
oho | +0.626 |
ttes | +0.611 |
Neg logit contributions | |
Dill | -0.575 |
rimp | -0.558 |
Rivals | -0.552 |
Switch | -0.534 |
rans | -0.528 |
Token | . |
Token ID | 13 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
bys | +1.967 |
dx | +1.643 |
Interstitial | +1.583 |
oho | +1.567 |
ttes | +1.531 |
Neg logit contributions | |
Dill | -1.529 |
rimp | -1.484 |
Rivals | -1.469 |
Switch | -1.420 |
rans | -1.413 |
Token | Thankfully |
Token ID | 31251 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
bys | +0.193 |
dx | +0.164 |
Interstitial | +0.159 |
oho | +0.158 |
ttes | +0.155 |
Neg logit contributions | |
Dill | -0.121 |
Rivals | -0.116 |
rimp | -0.116 |
Switch | -0.113 |
rans | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
bys | +0.586 |
dx | +0.490 |
Interstitial | +0.472 |
oho | +0.467 |
ttes | +0.457 |
Neg logit contributions | |
Dill | -0.450 |
rimp | -0.438 |
Rivals | -0.433 |
Switch | -0.416 |
rans | -0.416 |
Token | I |
Token ID | 314 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
bys | +0.602 |
dx | +0.517 |
Interstitial | +0.502 |
oho | +0.498 |
ttes | +0.489 |
Neg logit contributions | |
Dill | -0.315 |
rimp | -0.302 |
Rivals | -0.299 |
Switch | -0.287 |
rans | -0.284 |
Token | can |
Token ID | 460 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
Dill | +0.149 |
rimp | +0.145 |
Rivals | +0.143 |
Switch | +0.139 |
replace | +0.138 |
Neg logit contributions | |
bys | -0.231 |
dx | -0.197 |
Interstitial | -0.191 |
oho | -0.188 |
ttes | -0.184 |
Token | opot |
Token ID | 43372 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
bys | +0.219 |
dx | +0.186 |
Interstitial | +0.181 |
oho | +0.178 |
ttes | +0.175 |
Neg logit contributions | |
Dill | -0.137 |
rimp | -0.133 |
Rivals | -0.132 |
rans | -0.126 |
Switch | -0.126 |
Token | am |
Token ID | 321 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
bys | +0.740 |
dx | +0.600 |
Interstitial | +0.578 |
oho | +0.567 |
ttes | +0.555 |
Neg logit contributions | |
Dill | -0.766 |
rimp | -0.750 |
Rivals | -0.743 |
rans | -0.720 |
Switch | -0.718 |
Token | ian |
Token ID | 666 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
bys | +0.823 |
dx | +0.682 |
Interstitial | +0.657 |
oho | +0.647 |
ttes | +0.634 |
Neg logit contributions | |
Dill | -0.696 |
rimp | -0.678 |
Rivals | -0.670 |
Switch | -0.648 |
rans | -0.647 |
Token | , |
Token ID | 11 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
bys | +0.723 |
dx | +0.608 |
Interstitial | +0.588 |
oho | +0.581 |
ttes | +0.567 |
Neg logit contributions | |
Dill | -0.536 |
rimp | -0.519 |
Rivals | -0.518 |
Switch | -0.497 |
rans | -0.496 |
Token | Israel |
Token ID | 2692 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Dill | +0.051 |
Rivals | +0.049 |
rimp | +0.049 |
Switch | +0.047 |
rans | +0.047 |
Neg logit contributions | |
bys | -0.080 |
dx | -0.068 |
Interstitial | -0.066 |
oho | -0.065 |
ttes | -0.064 |
Token | ite |
Token ID | 578 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Dill | +0.232 |
rimp | +0.226 |
Rivals | +0.225 |
rans | +0.219 |
Switch | +0.217 |
Neg logit contributions | |
bys | -0.258 |
dx | -0.212 |
Interstitial | -0.204 |
oho | -0.200 |
ttes | -0.198 |
Token | , |
Token ID | 11 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
bys | +2.723 |
dx | +2.256 |
Interstitial | +2.173 |
oho | +2.148 |
ttes | +2.103 |
Neg logit contributions | |
Dill | -2.253 |
rimp | -2.192 |
Rivals | -2.163 |
Switch | -2.094 |
rans | -2.081 |
Token | Egyptian |
Token ID | 14075 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
Dill | +0.211 |
Rivals | +0.202 |
rimp | +0.201 |
Switch | +0.194 |
rans | +0.193 |
Neg logit contributions | |
bys | -0.318 |
dx | -0.270 |
Interstitial | -0.261 |
oho | -0.258 |
ttes | -0.254 |
Token | and |
Token ID | 290 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
bys | +0.182 |
dx | +0.152 |
Interstitial | +0.147 |
oho | +0.145 |
ttes | +0.142 |
Neg logit contributions | |
Dill | -0.138 |
rimp | -0.134 |
Rivals | -0.133 |
Switch | -0.128 |
rans | -0.128 |
Token | Greek |
Token ID | 8312 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
Dill | +0.469 |
Rivals | +0.447 |
rimp | +0.443 |
Switch | +0.431 |
rans | +0.427 |
Neg logit contributions | |
bys | -0.730 |
dx | -0.619 |
Interstitial | -0.599 |
oho | -0.595 |
ttes | -0.586 |
Token | – |
Token ID | 784 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
Dill | +0.117 |
Rivals | +0.113 |
rimp | +0.113 |
rans | +0.109 |
Switch | +0.109 |
Neg logit contributions | |
bys | -0.154 |
dx | -0.129 |
Interstitial | -0.125 |
oho | -0.124 |
ttes | -0.120 |
Token | for |
Token ID | 329 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
bys | +0.081 |
dx | +0.068 |
Interstitial | +0.066 |
oho | +0.066 |
ttes | +0.064 |
Neg logit contributions | |
Dill | -0.053 |
rimp | -0.050 |
Rivals | -0.050 |
Switch | -0.049 |
rans | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
Dill | +0.288 |
Rivals | +0.275 |
rimp | +0.273 |
Switch | +0.266 |
rans | +0.262 |
Neg logit contributions | |
bys | -0.456 |
dx | -0.385 |
Interstitial | -0.376 |
oho | -0.372 |
ttes | -0.363 |
Token | hour |
Token ID | 1711 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
bys | +0.151 |
dx | +0.125 |
Interstitial | +0.121 |
oho | +0.120 |
ttes | +0.117 |
Neg logit contributions | |
Dill | -0.119 |
rimp | -0.115 |
Rivals | -0.115 |
Switch | -0.111 |
rans | -0.110 |
Token | record |
Token ID | 1700 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
Dill | +0.052 |
rimp | +0.050 |
Rivals | +0.050 |
Switch | +0.048 |
rans | +0.048 |
Neg logit contributions | |
bys | -0.068 |
dx | -0.057 |
Interstitial | -0.055 |
oho | -0.055 |
ttes | -0.053 |
Token | in |
Token ID | 287 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
bys | +1.106 |
dx | +0.919 |
Interstitial | +0.886 |
oho | +0.876 |
ttes | +0.855 |
Neg logit contributions | |
Dill | -0.898 |
rimp | -0.871 |
Rivals | -0.863 |
Switch | -0.835 |
rans | -0.831 |
Token | particular |
Token ID | 1948 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
bys | +0.207 |
dx | +0.174 |
Interstitial | +0.169 |
oho | +0.168 |
ttes | +0.164 |
Neg logit contributions | |
Dill | -0.136 |
Rivals | -0.130 |
rimp | -0.129 |
Switch | -0.125 |
rans | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
bys | +2.337 |
dx | +1.938 |
Interstitial | +1.856 |
oho | +1.834 |
ttes | +1.791 |
Neg logit contributions | |
Dill | -2.023 |
rimp | -1.975 |
Rivals | -1.950 |
Switch | -1.878 |
rans | -1.867 |
Token | This |
Token ID | 770 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Dill | +0.195 |
Rivals | +0.188 |
rimp | +0.186 |
Switch | +0.182 |
rans | +0.178 |
Neg logit contributions | |
bys | -0.262 |
dx | -0.218 |
Interstitial | -0.212 |
oho | -0.210 |
ttes | -0.205 |
Token | record |
Token ID | 1700 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
bys | +0.551 |
dx | +0.467 |
Interstitial | +0.455 |
oho | +0.449 |
ttes | +0.441 |
Neg logit contributions | |
Dill | -0.339 |
rimp | -0.323 |
Rivals | -0.323 |
Switch | -0.312 |
rans | -0.307 |
Token | will |
Token ID | 481 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
bys | +0.515 |
dx | +0.437 |
Interstitial | +0.424 |
oho | +0.419 |
ttes | +0.410 |
Neg logit contributions | |
Dill | -0.329 |
rimp | -0.317 |
Rivals | -0.314 |
Switch | -0.303 |
rans | -0.301 |
Token | regain |
Token ID | 21509 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Dill | +0.688 |
rimp | +0.663 |
replace | +0.660 |
Rivals | +0.653 |
rans | +0.635 |
Neg logit contributions | |
bys | -1.245 |
dx | -1.063 |
Interstitial | -1.048 |
oho | -1.018 |
ttes | -1.002 |
Token | will |
Token ID | 481 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
bys | +0.214 |
dx | +0.183 |
Interstitial | +0.177 |
oho | +0.175 |
ttes | +0.172 |
Neg logit contributions | |
Dill | -0.125 |
rimp | -0.120 |
Rivals | -0.119 |
Switch | -0.114 |
rans | -0.113 |
Token | be |
Token ID | 307 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Dill | +0.437 |
rimp | +0.418 |
Rivals | +0.412 |
replace | +0.411 |
Switch | +0.400 |
Neg logit contributions | |
bys | -0.822 |
dx | -0.704 |
Interstitial | -0.693 |
oho | -0.677 |
ttes | -0.661 |
Token | transferred |
Token ID | 11172 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
bys | +0.809 |
dx | +0.684 |
Interstitial | +0.664 |
oho | +0.655 |
ttes | +0.642 |
Neg logit contributions | |
Dill | -0.525 |
rimp | -0.502 |
Rivals | -0.501 |
Switch | -0.483 |
rans | -0.483 |
Token | to |
Token ID | 284 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
bys | +0.162 |
dx | +0.136 |
Interstitial | +0.133 |
oho | +0.130 |
ttes | +0.127 |
Neg logit contributions | |
Dill | -0.122 |
rimp | -0.118 |
Rivals | -0.116 |
rans | -0.113 |
Switch | -0.113 |
Token | a |
Token ID | 257 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
Dill | +0.334 |
rimp | +0.321 |
Rivals | +0.317 |
Switch | +0.304 |
rans | +0.302 |
Neg logit contributions | |
bys | -0.616 |
dx | -0.528 |
Interstitial | -0.512 |
oho | -0.507 |
ttes | -0.498 |
Token | special |
Token ID | 2041 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Dill | +0.039 |
rimp | +0.038 |
Rivals | +0.037 |
Switch | +0.036 |
rans | +0.036 |
Neg logit contributions | |
bys | -0.069 |
dx | -0.059 |
Interstitial | -0.057 |
oho | -0.057 |
ttes | -0.056 |
Token | fund |
Token ID | 1814 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
bys | +2.074 |
dx | +1.752 |
Interstitial | +1.689 |
oho | +1.674 |
ttes | +1.633 |
Neg logit contributions | |
Dill | -1.406 |
rimp | -1.371 |
Rivals | -1.358 |
Switch | -1.291 |
rans | -1.286 |
Token | that |
Token ID | 326 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
bys | +0.808 |
dx | +0.677 |
Interstitial | +0.655 |
oho | +0.646 |
ttes | +0.632 |
Neg logit contributions | |
Dill | -0.600 |
rimp | -0.581 |
Rivals | -0.577 |
Switch | -0.557 |
rans | -0.555 |
Token | will |
Token ID | 481 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
bys | +0.284 |
dx | +0.243 |
Interstitial | +0.236 |
oho | +0.232 |
ttes | +0.228 |
Neg logit contributions | |
Dill | -0.168 |
rimp | -0.161 |
Rivals | -0.160 |
Switch | -0.154 |
rans | -0.153 |
Token | in |
Token ID | 287 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
Dill | +0.459 |
rimp | +0.442 |
replace | +0.437 |
Rivals | +0.436 |
Switch | +0.424 |
Neg logit contributions | |
bys | -0.860 |
dx | -0.740 |
Interstitial | -0.728 |
oho | -0.709 |
ttes | -0.691 |
Token | turn |
Token ID | 1210 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
bys | +0.056 |
dx | +0.048 |
Interstitial | +0.047 |
oho | +0.046 |
ttes | +0.045 |
Neg logit contributions | |
Dill | -0.032 |
rimp | -0.030 |
Rivals | -0.030 |
Switch | -0.029 |
rans | -0.029 |
Token | provides |
Token ID | 3769 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Dill | +0.245 |
rimp | +0.235 |
Rivals | +0.234 |
rans | +0.227 |
Switch | +0.226 |
Neg logit contributions | |
bys | -0.344 |
dx | -0.290 |
Interstitial | -0.282 |
oho | -0.277 |
ttes | -0.269 |
Token | information |
Token ID | 1321 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Dill | +0.711 |
Rivals | +0.686 |
rimp | +0.677 |
Switch | +0.661 |
transgender | +0.655 |
Neg logit contributions | |
bys | -1.078 |
dx | -0.919 |
Interstitial | -0.894 |
oho | -0.875 |
ttes | -0.846 |
Token | to |
Token ID | 284 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Dill | +0.539 |
Rivals | +0.512 |
rimp | +0.508 |
Switch | +0.494 |
replace | +0.490 |
Neg logit contributions | |
bys | -0.851 |
dx | -0.720 |
Interstitial | -0.706 |
oho | -0.692 |
ttes | -0.668 |
Token | entities |
Token ID | 12066 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
bys | +0.253 |
dx | +0.213 |
Interstitial | +0.206 |
oho | +0.203 |
ttes | +0.197 |
Neg logit contributions | |
Dill | -0.186 |
rimp | -0.180 |
Rivals | -0.179 |
Switch | -0.173 |
rans | -0.171 |
Token | that |
Token ID | 326 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
Dill | +0.734 |
rimp | +0.705 |
Rivals | +0.704 |
Switch | +0.682 |
rans | +0.679 |
Neg logit contributions | |
bys | -1.026 |
dx | -0.863 |
Interstitial | -0.839 |
oho | -0.825 |
ttes | -0.803 |
Token | request |
Token ID | 2581 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
bys | +0.189 |
dx | +0.161 |
Interstitial | +0.156 |
oho | +0.153 |
ttes | +0.150 |
Neg logit contributions | |
Dill | -0.120 |
Rivals | -0.115 |
rimp | -0.115 |
Switch | -0.111 |
replace | -0.110 |
Token | it |
Token ID | 340 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
bys | +0.274 |
dx | +0.234 |
Interstitial | +0.226 |
oho | +0.224 |
ttes | +0.219 |
Neg logit contributions | |
Dill | -0.165 |
rimp | -0.159 |
Rivals | -0.158 |
Switch | -0.151 |
rans | -0.150 |
Token | to |
Token ID | 284 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
bys | +0.499 |
dx | +0.418 |
Interstitial | +0.407 |
oho | +0.398 |
ttes | +0.387 |
Neg logit contributions | |
Dill | -0.370 |
rimp | -0.357 |
Rivals | -0.353 |
Switch | -0.344 |
replace | -0.343 |
Token | help |
Token ID | 1037 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
bys | +0.429 |
dx | +0.366 |
Interstitial | +0.355 |
oho | +0.348 |
ttes | +0.340 |
Neg logit contributions | |
Dill | -0.270 |
Rivals | -0.260 |
rimp | -0.259 |
Switch | -0.251 |
replace | -0.250 |
Token | them |
Token ID | 606 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
bys | +0.480 |
dx | +0.407 |
Interstitial | +0.394 |
oho | +0.388 |
ttes | +0.378 |
Neg logit contributions | |
Dill | -0.329 |
rimp | -0.316 |
Rivals | -0.316 |
Switch | -0.305 |
rans | -0.302 |
Token | assist |
Token ID | 3342 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
bys | +1.318 |
dx | +1.117 |
Interstitial | +1.084 |
oho | +1.069 |
ttes | +1.042 |
Neg logit contributions | |
Dill | -0.864 |
rimp | -0.835 |
Rivals | -0.831 |
Switch | -0.803 |
replace | -0.800 |
Token | is |
Token ID | 318 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Dill | +0.003 |
rimp | +0.003 |
Rivals | +0.002 |
Switch | +0.002 |
rans | +0.002 |
Neg logit contributions | |
bys | -0.004 |
dx | -0.004 |
Interstitial | -0.004 |
oho | -0.003 |
ttes | -0.003 |
Token | important |
Token ID | 1593 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Dill | +0.187 |
rimp | +0.176 |
Rivals | +0.175 |
Switch | +0.171 |
replace | +0.168 |
Neg logit contributions | |
bys | -0.338 |
dx | -0.290 |
Interstitial | -0.282 |
oho | -0.280 |
ttes | -0.273 |
Token | to |
Token ID | 284 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
Dill | +0.740 |
rimp | +0.715 |
Rivals | +0.708 |
Switch | +0.687 |
rans | +0.682 |
Neg logit contributions | |
bys | -0.948 |
dx | -0.791 |
Interstitial | -0.762 |
oho | -0.755 |
ttes | -0.738 |
Token | keep |
Token ID | 1394 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
Dill | +0.073 |
rimp | +0.069 |
Rivals | +0.068 |
Switch | +0.065 |
replace | +0.064 |
Neg logit contributions | |
bys | -0.196 |
dx | -0.172 |
Interstitial | -0.168 |
oho | -0.166 |
ttes | -0.163 |
Token | in |
Token ID | 287 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
Dill | +0.005 |
rimp | +0.005 |
Rivals | +0.005 |
Switch | +0.005 |
rans | +0.005 |
Neg logit contributions | |
bys | -0.006 |
dx | -0.005 |
Interstitial | -0.005 |
oho | -0.005 |
ttes | -0.005 |
Token | mind |
Token ID | 2000 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
bys | +0.144 |
dx | +0.123 |
Interstitial | +0.120 |
oho | +0.119 |
ttes | +0.117 |
Neg logit contributions | |
Dill | -0.076 |
rimp | -0.072 |
Rivals | -0.072 |
Switch | -0.069 |
rans | -0.068 |
Token | that |
Token ID | 326 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
bys | +1.056 |
dx | +0.880 |
Interstitial | +0.847 |
oho | +0.838 |
ttes | +0.819 |
Neg logit contributions | |
Dill | -0.844 |
rimp | -0.819 |
Rivals | -0.811 |
Switch | -0.784 |
rans | -0.780 |
Token | teachers |
Token ID | 7799 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Dill | +0.297 |
Rivals | +0.280 |
rimp | +0.279 |
Switch | +0.272 |
replace | +0.269 |
Neg logit contributions | |
bys | -0.468 |
dx | -0.399 |
Interstitial | -0.388 |
oho | -0.384 |
ttes | -0.375 |
Token | who |
Token ID | 508 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
bys | +0.828 |
dx | +0.701 |
Interstitial | +0.679 |
oho | +0.670 |
ttes | +0.657 |
Neg logit contributions | |
Dill | -0.552 |
rimp | -0.534 |
Rivals | -0.526 |
Switch | -0.509 |
rans | -0.507 |
Token | choose |
Token ID | 3853 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
bys | +0.885 |
dx | +0.753 |
Interstitial | +0.732 |
oho | +0.719 |
ttes | +0.706 |
Neg logit contributions | |
Dill | -0.555 |
rimp | -0.536 |
Rivals | -0.527 |
Switch | -0.510 |
replace | -0.507 |
Token | to |
Token ID | 284 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
bys | +0.689 |
dx | +0.576 |
Interstitial | +0.555 |
oho | +0.549 |
ttes | +0.537 |
Neg logit contributions | |
Dill | -0.525 |
rimp | -0.510 |
Rivals | -0.505 |
Switch | -0.487 |
rans | -0.484 |
Token | Sports |
Token ID | 7092 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
bys | +1.340 |
dx | +1.124 |
Interstitial | +1.082 |
oho | +1.073 |
ttes | +1.054 |
Neg logit contributions | |
Dill | -0.968 |
rimp | -0.940 |
Rivals | -0.919 |
rans | -0.889 |
Switch | -0.886 |
Token | Club |
Token ID | 6289 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
bys | +1.673 |
dx | +1.386 |
Interstitial | +1.329 |
oho | +1.316 |
ttes | +1.300 |
Neg logit contributions | |
Dill | -1.379 |
rimp | -1.347 |
Rivals | -1.294 |
rans | -1.279 |
Marsh | -1.276 |
Token | – |
Token ID | 784 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
bys | +0.057 |
dx | +0.048 |
Interstitial | +0.046 |
oho | +0.046 |
ttes | +0.044 |
Neg logit contributions | |
Dill | -0.040 |
Rivals | -0.039 |
rimp | -0.038 |
Switch | -0.037 |
rans | -0.037 |
Token | Baseball |
Token ID | 17362 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
bys | +0.108 |
dx | +0.091 |
Interstitial | +0.088 |
oho | +0.088 |
ttes | +0.086 |
Neg logit contributions | |
Dill | -0.072 |
Rivals | -0.070 |
rimp | -0.070 |
Switch | -0.068 |
rans | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
bys | +2.552 |
dx | +2.142 |
Interstitial | +2.049 |
oho | +2.034 |
ttes | +2.001 |
Neg logit contributions | |
Dill | -1.926 |
rimp | -1.873 |
Rivals | -1.833 |
rans | -1.784 |
Marsh | -1.765 |
Token | the |
Token ID | 262 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
Dill | +0.116 |
rimp | +0.112 |
Rivals | +0.111 |
Switch | +0.108 |
rans | +0.106 |
Neg logit contributions | |
bys | -0.171 |
dx | -0.144 |
Interstitial | -0.139 |
oho | -0.138 |
ttes | -0.135 |
Token | pitcher |
Token ID | 18086 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
bys | +0.067 |
dx | +0.057 |
Interstitial | +0.056 |
oho | +0.055 |
ttes | +0.054 |
Neg logit contributions | |
Dill | -0.041 |
Rivals | -0.040 |
rimp | -0.040 |
Switch | -0.039 |
rans | -0.038 |
Token | aims |
Token ID | 12031 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
bys | +0.679 |
dx | +0.579 |
Interstitial | +0.561 |
oho | +0.554 |
ttes | +0.540 |
Neg logit contributions | |
Dill | -0.440 |
rimp | -0.423 |
Rivals | -0.421 |
Switch | -0.410 |
replace | -0.400 |
Token | a |
Token ID | 257 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
bys | +0.120 |
dx | +0.102 |
Interstitial | +0.098 |
oho | +0.097 |
ttes | +0.095 |
Neg logit contributions | |
Dill | -0.085 |
rimp | -0.082 |
Rivals | -0.081 |
Switch | -0.079 |
rans | -0.077 |
Token | fastball |
Token ID | 38287 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
bys | +0.189 |
dx | +0.163 |
Interstitial | +0.158 |
oho | +0.156 |
ttes | +0.153 |
Neg logit contributions | |
Dill | -0.098 |
rimp | -0.094 |
Rivals | -0.093 |
Switch | -0.090 |
rans | -0.088 |
Token | , |
Token ID | 11 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
bys | +2.328 |
dx | +1.958 |
Interstitial | +1.890 |
oho | +1.870 |
ttes | +1.830 |
Neg logit contributions | |
Dill | -1.669 |
rimp | -1.617 |
Rivals | -1.600 |
Switch | -1.543 |
rans | -1.534 |
Token | faith |
Token ID | 4562 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
bys | +0.342 |
dx | +0.289 |
Interstitial | +0.280 |
oho | +0.274 |
ttes | +0.271 |
Neg logit contributions | |
Dill | -0.231 |
Rivals | -0.224 |
rimp | -0.223 |
Switch | -0.215 |
rans | -0.212 |
Token | , |
Token ID | 11 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
Dill | +1.151 |
rimp | +1.127 |
Rivals | +1.107 |
rans | +1.082 |
replace | +1.078 |
Neg logit contributions | |
bys | -1.662 |
dx | -1.400 |
Interstitial | -1.353 |
oho | -1.350 |
ttes | -1.316 |
Token | fret |
Token ID | 33960 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
bys | +0.113 |
dx | +0.096 |
Interstitial | +0.093 |
oho | +0.092 |
ttes | +0.090 |
Neg logit contributions | |
Dill | -0.072 |
rimp | -0.069 |
Rivals | -0.069 |
Switch | -0.066 |
rans | -0.065 |
Token | about |
Token ID | 546 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Dill | +0.329 |
rimp | +0.318 |
Rivals | +0.314 |
Switch | +0.301 |
rans | +0.301 |
Neg logit contributions | |
bys | -0.523 |
dx | -0.444 |
Interstitial | -0.432 |
oho | -0.426 |
ttes | -0.416 |
Token | losing |
Token ID | 6078 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Dill | +0.240 |
rimp | +0.231 |
Rivals | +0.230 |
Switch | +0.220 |
rans | +0.219 |
Neg logit contributions | |
bys | -0.379 |
dx | -0.322 |
Interstitial | -0.312 |
oho | -0.308 |
ttes | -0.302 |
Token | the |
Token ID | 262 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
Dill | +0.540 |
Rivals | +0.517 |
rimp | +0.515 |
Switch | +0.493 |
rans | +0.489 |
Neg logit contributions | |
bys | -0.924 |
dx | -0.788 |
Interstitial | -0.766 |
oho | -0.751 |
ttes | -0.741 |
Token | next |
Token ID | 1306 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
bys | +0.058 |
dx | +0.049 |
Interstitial | +0.047 |
oho | +0.047 |
ttes | +0.046 |
Neg logit contributions | |
Dill | -0.039 |
rimp | -0.037 |
Rivals | -0.037 |
Switch | -0.036 |
rans | -0.035 |
Token | generation |
Token ID | 5270 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Dill | +0.869 |
Rivals | +0.834 |
rimp | +0.834 |
Switch | +0.802 |
rans | +0.794 |
Neg logit contributions | |
bys | -1.272 |
dx | -1.077 |
Interstitial | -1.042 |
oho | -1.024 |
ttes | -1.010 |
Token | , |
Token ID | 11 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
Dill | +0.259 |
Rivals | +0.250 |
rimp | +0.249 |
Switch | +0.242 |
rans | +0.241 |
Neg logit contributions | |
bys | -0.337 |
dx | -0.283 |
Interstitial | -0.274 |
oho | -0.270 |
ttes | -0.263 |
Token | said |
Token ID | 531 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
Dill | +0.106 |
rimp | +0.102 |
Rivals | +0.102 |
Switch | +0.098 |
rans | +0.098 |
Neg logit contributions | |
bys | -0.129 |
dx | -0.107 |
Interstitial | -0.103 |
oho | -0.102 |
ttes | -0.100 |
Token | the |
Token ID | 262 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
bys | +0.196 |
dx | +0.168 |
Interstitial | +0.163 |
oho | +0.161 |
ttes | +0.158 |
Neg logit contributions | |
Dill | -0.104 |
rimp | -0.099 |
Rivals | -0.099 |
Switch | -0.094 |
rans | -0.093 |
Token | according |
Token ID | 1864 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
Dill | +0.998 |
Rivals | +0.964 |
rimp | +0.953 |
Switch | +0.928 |
replace | +0.913 |
Neg logit contributions | |
bys | -1.480 |
dx | -1.250 |
Interstitial | -1.222 |
oho | -1.206 |
ttes | -1.189 |
Token | to |
Token ID | 284 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Dill | +1.077 |
Rivals | +1.044 |
rimp | +1.022 |
Switch | +1.004 |
Anonymous | +0.992 |
Neg logit contributions | |
bys | -1.509 |
dx | -1.268 |
Interstitial | -1.235 |
oho | -1.228 |
ttes | -1.198 |
Token | a |
Token ID | 257 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
Dill | +0.147 |
Rivals | +0.141 |
rimp | +0.141 |
Switch | +0.136 |
rans | +0.133 |
Neg logit contributions | |
bys | -0.249 |
dx | -0.213 |
Interstitial | -0.207 |
oho | -0.204 |
ttes | -0.200 |
Token | housing |
Token ID | 5627 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Dill | +0.017 |
rimp | +0.016 |
Rivals | +0.016 |
Switch | +0.016 |
rans | +0.016 |
Neg logit contributions | |
bys | -0.029 |
dx | -0.024 |
Interstitial | -0.024 |
oho | -0.023 |
ttes | -0.023 |
Token | expert |
Token ID | 5887 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
bys | +0.406 |
dx | +0.336 |
Interstitial | +0.329 |
oho | +0.320 |
ttes | +0.316 |
Neg logit contributions | |
Dill | -0.339 |
rimp | -0.328 |
Rivals | -0.327 |
Switch | -0.318 |
replace | -0.313 |
Token | . |
Token ID | 13 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
Dill | +0.193 |
rimp | +0.187 |
Rivals | +0.186 |
Switch | +0.179 |
rans | +0.178 |
Neg logit contributions | |
bys | -0.264 |
dx | -0.222 |
Interstitial | -0.216 |
oho | -0.212 |
ttes | -0.208 |
Token |
|
Token ID | 198 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
Dill | +0.040 |
rimp | +0.038 |
Rivals | +0.038 |
Switch | +0.037 |
rans | +0.037 |
Neg logit contributions | |
bys | -0.044 |
dx | -0.036 |
Interstitial | -0.035 |
oho | -0.034 |
ttes | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
bys | +0.012 |
dx | +0.010 |
Interstitial | +0.010 |
oho | +0.009 |
ttes | +0.009 |
Neg logit contributions | |
Dill | -0.011 |
Rivals | -0.011 |
rimp | -0.011 |
Switch | -0.011 |
Marsh | -0.011 |
Token | H |
Token ID | 39 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Dill | +0.116 |
rimp | +0.113 |
Rivals | +0.112 |
Marsh | +0.108 |
Switch | +0.107 |
Neg logit contributions | |
bys | -0.190 |
dx | -0.161 |
Interstitial | -0.156 |
oho | -0.156 |
ttes | -0.154 |
Token | ousing |
Token ID | 12752 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
Dill | +0.652 |
rimp | +0.641 |
Rivals | +0.620 |
Switch | +0.609 |
rans | +0.606 |
Neg logit contributions | |
bys | -0.738 |
dx | -0.605 |
Interstitial | -0.586 |
oho | -0.569 |
ttes | -0.569 |
Token | Minister |
Token ID | 4139 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
bys | +0.669 |
dx | +0.564 |
Interstitial | +0.551 |
oho | +0.540 |
ttes | +0.533 |
Neg logit contributions | |
Dill | -0.453 |
Rivals | -0.436 |
rimp | -0.435 |
Switch | -0.421 |
rans | -0.413 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
bys | +0.341 |
dx | +0.288 |
Interstitial | +0.280 |
oho | +0.275 |
ttes | +0.272 |
Neg logit contributions | |
Dill | -0.241 |
rimp | -0.233 |
Rivals | -0.232 |
Switch | -0.225 |
rans | -0.222 |
Token | out |
Token ID | 448 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
bys | +0.307 |
dx | +0.255 |
Interstitial | +0.251 |
oho | +0.243 |
ttes | +0.238 |
Neg logit contributions | |
Dill | -0.293 |
rimp | -0.288 |
Rivals | -0.283 |
Switch | -0.278 |
rans | -0.277 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Dill | +0.069 |
rimp | +0.066 |
Rivals | +0.066 |
Switch | +0.064 |
Ames | +0.064 |
Neg logit contributions | |
bys | -0.093 |
dx | -0.079 |
Interstitial | -0.077 |
oho | -0.075 |
ttes | -0.075 |
Token | Or |
Token ID | 5574 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
Dill | +0.219 |
rimp | +0.213 |
Rivals | +0.211 |
Marsh | +0.204 |
rans | +0.203 |
Neg logit contributions | |
bys | -0.341 |
dx | -0.288 |
Interstitial | -0.278 |
oho | -0.278 |
ttes | -0.273 |
Token | at |
Token ID | 379 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
bys | +0.096 |
dx | +0.081 |
Interstitial | +0.078 |
oho | +0.077 |
ttes | +0.076 |
Neg logit contributions | |
Dill | -0.068 |
rimp | -0.066 |
Rivals | -0.065 |
Switch | -0.063 |
rans | -0.062 |
Token | least |
Token ID | 1551 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
Dill | +0.514 |
rimp | +0.492 |
Rivals | +0.487 |
Switch | +0.471 |
rans | +0.468 |
Neg logit contributions | |
bys | -0.825 |
dx | -0.702 |
Interstitial | -0.681 |
oho | -0.673 |
ttes | -0.658 |
Token | 26 |
Token ID | 2608 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Dill | +0.512 |
Rivals | +0.491 |
rimp | +0.489 |
Switch | +0.475 |
replace | +0.471 |
Neg logit contributions | |
bys | -0.768 |
dx | -0.649 |
Interstitial | -0.628 |
oho | -0.619 |
ttes | -0.604 |
Token | of |
Token ID | 286 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Dill | +0.266 |
rimp | +0.256 |
Rivals | +0.255 |
Switch | +0.247 |
rans | +0.244 |
Neg logit contributions | |
bys | -0.380 |
dx | -0.321 |
Interstitial | -0.310 |
oho | -0.305 |
ttes | -0.301 |
Token | 27 |
Token ID | 2681 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Dill | +0.213 |
rimp | +0.204 |
Rivals | +0.203 |
Switch | +0.195 |
rans | +0.192 |
Neg logit contributions | |
bys | -0.351 |
dx | -0.301 |
Interstitial | -0.292 |
oho | -0.286 |
ttes | -0.281 |
Token | : |
Token ID | 25 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Dill | +0.297 |
Rivals | +0.286 |
rimp | +0.285 |
Switch | +0.275 |
rans | +0.271 |
Neg logit contributions | |
bys | -0.452 |
dx | -0.385 |
Interstitial | -0.373 |
oho | -0.366 |
ttes | -0.358 |
Token | THE |
Token ID | 10970 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Dill | +0.235 |
rimp | +0.226 |
Rivals | +0.226 |
Switch | +0.217 |
rans | +0.214 |
Neg logit contributions | |
bys | -0.327 |
dx | -0.275 |
Interstitial | -0.265 |
oho | -0.263 |
ttes | -0.257 |
Token | : |
Token ID | 25 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
Dill | +0.671 |
Rivals | +0.644 |
rimp | +0.638 |
Switch | +0.624 |
Anonymous | +0.610 |
Neg logit contributions | |
bys | -1.025 |
dx | -0.868 |
Interstitial | -0.844 |
oho | -0.831 |
ttes | -0.813 |
Token | I |
Token ID | 314 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
bys | +0.076 |
dx | +0.065 |
Interstitial | +0.063 |
oho | +0.062 |
ttes | +0.061 |
Neg logit contributions | |
Dill | -0.045 |
Rivals | -0.042 |
rimp | -0.041 |
Switch | -0.041 |
Anonymous | -0.040 |
Token | noticed |
Token ID | 6810 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
bys | +0.569 |
dx | +0.478 |
Interstitial | +0.462 |
oho | +0.455 |
ttes | +0.445 |
Neg logit contributions | |
Dill | -0.407 |
rimp | -0.394 |
Rivals | -0.391 |
Switch | -0.376 |
rans | -0.375 |
Token | that |
Token ID | 326 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
bys | +1.982 |
dx | +1.668 |
Interstitial | +1.617 |
oho | +1.596 |
ttes | +1.558 |
Neg logit contributions | |
Dill | -1.410 |
rimp | -1.346 |
Rivals | -1.344 |
Switch | -1.298 |
rans | -1.282 |
Token | everyone |
Token ID | 2506 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
Dill | +0.416 |
Rivals | +0.386 |
rimp | +0.379 |
Switch | +0.377 |
Anonymous | +0.368 |
Neg logit contributions | |
bys | -0.642 |
dx | -0.544 |
Interstitial | -0.533 |
oho | -0.524 |
ttes | -0.508 |
Token | picked |
Token ID | 6497 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Dill | +0.280 |
rimp | +0.266 |
Rivals | +0.265 |
Switch | +0.258 |
rans | +0.254 |
Neg logit contributions | |
bys | -0.422 |
dx | -0.357 |
Interstitial | -0.351 |
oho | -0.342 |
ttes | -0.333 |
Token | up |
Token ID | 510 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Dill | +0.366 |
rimp | +0.348 |
Rivals | +0.346 |
Switch | +0.333 |
rans | +0.327 |
Neg logit contributions | |
bys | -0.623 |
dx | -0.532 |
Interstitial | -0.518 |
oho | -0.511 |
ttes | -0.500 |
Token | on |
Token ID | 319 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
Dill | +0.287 |
rimp | +0.272 |
Rivals | +0.271 |
Switch | +0.262 |
rans | +0.256 |
Neg logit contributions | |
bys | -0.481 |
dx | -0.410 |
Interstitial | -0.397 |
oho | -0.394 |
ttes | -0.385 |
Token | that |
Token ID | 326 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Dill | +0.108 |
Rivals | +0.102 |
rimp | +0.101 |
Switch | +0.099 |
Anonymous | +0.096 |
Neg logit contributions | |
bys | -0.157 |
dx | -0.133 |
Interstitial | -0.129 |
oho | -0.127 |
ttes | -0.124 |
Token | very |
Token ID | 845 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Dill | +0.271 |
Rivals | +0.255 |
rimp | +0.252 |
Switch | +0.248 |
Anonymous | +0.243 |
Neg logit contributions | |
bys | -0.389 |
dx | -0.328 |
Interstitial | -0.319 |
oho | -0.314 |
ttes | -0.306 |
Token | clear |
Token ID | 1598 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Dill | +0.290 |
Rivals | +0.272 |
rimp | +0.270 |
Switch | +0.265 |
replace | +0.259 |
Neg logit contributions | |
bys | -0.462 |
dx | -0.392 |
Interstitial | -0.381 |
oho | -0.374 |
ttes | -0.369 |
Token | grid |
Token ID | 10706 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
bys | +0.177 |
dx | +0.151 |
Interstitial | +0.146 |
oho | +0.145 |
ttes | +0.142 |
Neg logit contributions | |
Dill | -0.104 |
rimp | -0.099 |
Rivals | -0.099 |
Switch | -0.096 |
rans | -0.095 |
Token | could |
Token ID | 714 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Dill | +1.429 |
rimp | +1.391 |
Rivals | +1.362 |
rans | +1.356 |
Switch | +1.345 |
Neg logit contributions | |
bys | -2.126 |
dx | -1.817 |
Interstitial | -1.772 |
oho | -1.757 |
ttes | -1.704 |
Token | help |
Token ID | 1037 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
bys | +0.314 |
dx | +0.268 |
Interstitial | +0.264 |
oho | +0.259 |
ttes | +0.254 |
Neg logit contributions | |
Dill | -0.176 |
rimp | -0.170 |
Rivals | -0.168 |
replace | -0.165 |
Switch | -0.163 |
Token | that |
Token ID | 326 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
bys | +0.517 |
dx | +0.439 |
Interstitial | +0.426 |
oho | +0.421 |
ttes | +0.412 |
Neg logit contributions | |
Dill | -0.330 |
rimp | -0.318 |
Rivals | -0.316 |
Switch | -0.305 |
rans | -0.302 |
Token | jump |
Token ID | 4391 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
bys | +0.159 |
dx | +0.136 |
Interstitial | +0.132 |
oho | +0.130 |
ttes | +0.128 |
Neg logit contributions | |
Dill | -0.089 |
rimp | -0.085 |
Rivals | -0.085 |
Switch | -0.081 |
rans | -0.081 |
Token | happen |
Token ID | 1645 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
Dill | +0.505 |
rimp | +0.488 |
Rivals | +0.481 |
rans | +0.469 |
Switch | +0.466 |
Neg logit contributions | |
bys | -0.737 |
dx | -0.625 |
Interstitial | -0.609 |
oho | -0.595 |
ttes | -0.586 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Dill | +0.626 |
rimp | +0.598 |
Rivals | +0.591 |
Switch | +0.578 |
rans | +0.575 |
Neg logit contributions | |
bys | -0.892 |
dx | -0.762 |
Interstitial | -0.742 |
oho | -0.729 |
ttes | -0.715 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
Dill | +0.177 |
Rivals | +0.170 |
rimp | +0.169 |
Switch | +0.166 |
Ames | +0.161 |
Neg logit contributions | |
bys | -0.224 |
dx | -0.187 |
Interstitial | -0.181 |
oho | -0.180 |
ttes | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
bys | +0.003 |
dx | +0.002 |
Interstitial | +0.002 |
oho | +0.002 |
ttes | +0.002 |
Neg logit contributions | |
Dill | -0.002 |
Rivals | -0.002 |
rimp | -0.002 |
Switch | -0.002 |
rans | -0.002 |
Token | Image |
Token ID | 5159 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Dill | +0.154 |
rimp | +0.150 |
Rivals | +0.148 |
Marsh | +0.143 |
Switch | +0.142 |
Neg logit contributions | |
bys | -0.241 |
dx | -0.204 |
oho | -0.197 |
Interstitial | -0.197 |
ttes | -0.193 |
Token | via |
Token ID | 2884 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Dill | +0.501 |
rimp | +0.480 |
Rivals | +0.479 |
Switch | +0.461 |
rans | +0.458 |
Neg logit contributions | |
bys | -0.719 |
dx | -0.611 |
Interstitial | -0.593 |
oho | -0.583 |
ttes | -0.574 |
Token | and |
Token ID | 290 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
bys | +0.155 |
dx | +0.131 |
oho | +0.126 |
Interstitial | +0.126 |
ttes | +0.124 |
Neg logit contributions | |
Dill | -0.102 |
rimp | -0.098 |
Rivals | -0.097 |
Switch | -0.094 |
rans | -0.093 |
Token | higher |
Token ID | 2440 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Dill | +0.229 |
rimp | +0.218 |
Rivals | +0.216 |
Switch | +0.211 |
replace | +0.207 |
Neg logit contributions | |
bys | -0.410 |
dx | -0.351 |
oho | -0.339 |
Interstitial | -0.338 |
ttes | -0.331 |
Token | par |
Token ID | 1582 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
bys | +1.134 |
dx | +0.953 |
Interstitial | +0.917 |
oho | +0.912 |
ttes | +0.895 |
Neg logit contributions | |
Dill | -0.802 |
rimp | -0.774 |
Rivals | -0.767 |
Switch | -0.744 |
rans | -0.737 |
Token | asy |
Token ID | 4107 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Dill | +0.086 |
rimp | +0.085 |
Rivals | +0.083 |
rans | +0.082 |
Switch | +0.081 |
Neg logit contributions | |
bys | -0.132 |
dx | -0.112 |
Interstitial | -0.110 |
oho | -0.107 |
ttes | -0.106 |
Token | mp |
Token ID | 3149 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
Dill | +0.221 |
rimp | +0.218 |
Rivals | +0.214 |
Switch | +0.210 |
rans | +0.209 |
Neg logit contributions | |
bys | -0.192 |
dx | -0.153 |
Interstitial | -0.149 |
oho | -0.145 |
ttes | -0.140 |
Token | athetic |
Token ID | 18874 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
bys | +0.012 |
dx | +0.010 |
Interstitial | +0.010 |
oho | +0.010 |
ttes | +0.010 |
Neg logit contributions | |
Dill | -0.003 |
rimp | -0.002 |
Rivals | -0.002 |
rans | -0.002 |
Switch | -0.002 |
Token | resting |
Token ID | 19186 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
Dill | +0.505 |
rimp | +0.487 |
Rivals | +0.483 |
Switch | +0.468 |
rans | +0.463 |
Neg logit contributions | |
bys | -0.792 |
dx | -0.671 |
Interstitial | -0.647 |
oho | -0.642 |
ttes | -0.632 |
Token | tone |
Token ID | 8216 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
bys | +1.603 |
dx | +1.352 |
Interstitial | +1.307 |
oho | +1.291 |
ttes | +1.263 |
Neg logit contributions | |
Dill | -1.097 |
rimp | -1.063 |
Rivals | -1.052 |
Switch | -1.008 |
rans | -1.004 |
Token | in |
Token ID | 287 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
Dill | +0.131 |
rimp | +0.126 |
Rivals | +0.125 |
Switch | +0.122 |
rans | +0.121 |
Neg logit contributions | |
bys | -0.171 |
dx | -0.142 |
Interstitial | -0.137 |
oho | -0.136 |
ttes | -0.133 |
Token | the |
Token ID | 262 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
Dill | +0.050 |
rimp | +0.047 |
Rivals | +0.047 |
Switch | +0.045 |
rans | +0.045 |
Neg logit contributions | |
bys | -0.094 |
dx | -0.080 |
Interstitial | -0.078 |
oho | -0.078 |
ttes | -0.076 |
Token | evening |
Token ID | 6180 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
bys | +0.120 |
dx | +0.100 |
Interstitial | +0.097 |
oho | +0.096 |
ttes | +0.094 |
Neg logit contributions | |
Dill | -0.084 |
rimp | -0.081 |
Rivals | -0.080 |
Switch | -0.077 |
rans | -0.077 |
Token | irregular |
Token ID | 21388 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Dill | +0.073 |
rimp | +0.069 |
Rivals | +0.069 |
Switch | +0.066 |
rans | +0.066 |
Neg logit contributions | |
bys | -0.123 |
dx | -0.105 |
Interstitial | -0.102 |
oho | -0.101 |
ttes | -0.099 |
Token | siph |
Token ID | 44105 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
Dill | +0.275 |
rimp | +0.264 |
Rivals | +0.262 |
Switch | +0.255 |
rans | +0.253 |
Neg logit contributions | |
bys | -0.364 |
dx | -0.305 |
Interstitial | -0.295 |
oho | -0.291 |
ttes | -0.284 |
Token | oning |
Token ID | 12484 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
Dill | +1.018 |
rimp | +0.993 |
Rivals | +0.982 |
Switch | +0.951 |
rans | +0.950 |
Neg logit contributions | |
bys | -1.184 |
dx | -0.982 |
Interstitial | -0.950 |
oho | -0.931 |
ttes | -0.910 |
Token | activities |
Token ID | 4568 |
Feature activation | +9.80e-04 |
Pos logit contributions | |
Dill | +0.029 |
rimp | +0.027 |
Rivals | +0.027 |
Switch | +0.026 |
rans | +0.026 |
Neg logit contributions | |
bys | -0.037 |
dx | -0.032 |
Interstitial | -0.030 |
oho | -0.030 |
ttes | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
bys | +0.002 |
dx | +0.002 |
Interstitial | +0.002 |
oho | +0.002 |
ttes | +0.001 |
Neg logit contributions | |
Dill | -0.001 |
rimp | -0.001 |
Rivals | -0.001 |
Switch | -0.001 |
rans | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Dill | +0.079 |
rimp | +0.075 |
Rivals | +0.075 |
Switch | +0.072 |
rans | +0.072 |
Neg logit contributions | |
bys | -0.117 |
dx | -0.098 |
Interstitial | -0.095 |
oho | -0.095 |
ttes | -0.093 |
Token | they |
Token ID | 484 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Dill | +0.238 |
Rivals | +0.226 |
rimp | +0.225 |
Switch | +0.218 |
replace | +0.217 |
Neg logit contributions | |
bys | -0.358 |
dx | -0.303 |
Interstitial | -0.295 |
oho | -0.290 |
ttes | -0.286 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
bys | +0.356 |
dx | +0.302 |
Interstitial | +0.296 |
oho | +0.289 |
ttes | +0.284 |
Neg logit contributions | |
Dill | -0.226 |
rimp | -0.217 |
Rivals | -0.215 |
Switch | -0.208 |
replace | -0.208 |
Token | him |
Token ID | 683 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
bys | +0.222 |
dx | +0.187 |
Interstitial | +0.181 |
oho | +0.178 |
ttes | +0.174 |
Neg logit contributions | |
Dill | -0.167 |
rimp | -0.161 |
Rivals | -0.160 |
Switch | -0.154 |
rans | -0.153 |
Token | to |
Token ID | 284 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
bys | +0.994 |
dx | +0.838 |
Interstitial | +0.808 |
oho | +0.800 |
ttes | +0.784 |
Neg logit contributions | |
Dill | -0.695 |
rimp | -0.674 |
Rivals | -0.667 |
Switch | -0.642 |
rans | -0.638 |
Token | go |
Token ID | 467 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
bys | +0.292 |
dx | +0.250 |
Interstitial | +0.245 |
oho | +0.239 |
ttes | +0.235 |
Neg logit contributions | |
Dill | -0.163 |
rimp | -0.157 |
Rivals | -0.154 |
replace | -0.151 |
Switch | -0.150 |
Token | system |
Token ID | 1080 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Dill | +0.327 |
rimp | +0.316 |
Rivals | +0.314 |
rans | +0.304 |
Switch | +0.304 |
Neg logit contributions | |
bys | -0.407 |
dx | -0.341 |
Interstitial | -0.329 |
oho | -0.324 |
ttes | -0.315 |
Token | used |
Token ID | 973 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
Dill | +0.275 |
rimp | +0.264 |
Rivals | +0.263 |
Switch | +0.255 |
rans | +0.254 |
Neg logit contributions | |
bys | -0.358 |
dx | -0.301 |
Interstitial | -0.292 |
oho | -0.286 |
ttes | -0.280 |
Token | by |
Token ID | 416 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Dill | +0.048 |
rimp | +0.047 |
Rivals | +0.046 |
Switch | +0.045 |
rans | +0.045 |
Neg logit contributions | |
bys | -0.058 |
dx | -0.049 |
Interstitial | -0.047 |
oho | -0.046 |
ttes | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
Dill | +0.269 |
rimp | +0.257 |
Rivals | +0.256 |
Switch | +0.244 |
rans | +0.242 |
Neg logit contributions | |
bys | -0.473 |
dx | -0.406 |
Interstitial | -0.394 |
oho | -0.387 |
ttes | -0.381 |
Token | Mau |
Token ID | 28931 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Dill | +0.107 |
rimp | +0.102 |
Rivals | +0.101 |
Switch | +0.097 |
rans | +0.096 |
Neg logit contributions | |
bys | -0.208 |
dx | -0.179 |
Interstitial | -0.174 |
oho | -0.171 |
ttes | -0.169 |
Token | Mau |
Token ID | 28931 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Dill | +1.819 |
rimp | +1.762 |
Rivals | +1.745 |
Switch | +1.690 |
rans | +1.690 |
Neg logit contributions | |
bys | -2.313 |
dx | -1.943 |
Interstitial | -1.875 |
oho | -1.835 |
ttes | -1.792 |
Token | , |
Token ID | 11 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
Dill | +1.735 |
Rivals | +1.666 |
rimp | +1.664 |
rans | +1.613 |
Switch | +1.609 |
Neg logit contributions | |
bys | -2.391 |
dx | -2.024 |
Interstitial | -1.952 |
oho | -1.919 |
ttes | -1.865 |
Token | and |
Token ID | 290 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Dill | +0.102 |
Rivals | +0.097 |
rimp | +0.097 |
Switch | +0.093 |
rans | +0.092 |
Neg logit contributions | |
bys | -0.153 |
dx | -0.131 |
Interstitial | -0.127 |
oho | -0.125 |
ttes | -0.123 |
Token | denied |
Token ID | 6699 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Dill | +0.298 |
Rivals | +0.284 |
rimp | +0.282 |
Switch | +0.274 |
Anonymous | +0.271 |
Neg logit contributions | |
bys | -0.414 |
dx | -0.353 |
Interstitial | -0.342 |
oho | -0.334 |
ttes | -0.328 |
Token | having |
Token ID | 1719 |
Feature activation | -6.99e-03 |
Pos logit contributions | |
bys | +0.577 |
dx | +0.489 |
Interstitial | +0.475 |
oho | +0.466 |
ttes | +0.459 |
Neg logit contributions | |
Dill | -0.388 |
rimp | -0.370 |
Rivals | -0.370 |
Switch | -0.355 |
rans | -0.352 |
Token | ever |
Token ID | 1683 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
Dill | +0.010 |
Rivals | +0.009 |
rimp | +0.009 |
Switch | +0.009 |
replace | +0.009 |
Neg logit contributions | |
bys | -0.014 |
dx | -0.012 |
Interstitial | -0.012 |
oho | -0.011 |
ttes | -0.011 |
Token | File |
Token ID | 9220 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Dill | +0.365 |
Rivals | +0.349 |
rimp | +0.349 |
Switch | +0.335 |
rans | +0.329 |
Neg logit contributions | |
bys | -0.624 |
dx | -0.531 |
Interstitial | -0.517 |
oho | -0.510 |
ttes | -0.501 |
Token | ) |
Token ID | 8 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Dill | +0.546 |
rimp | +0.521 |
Rivals | +0.515 |
Switch | +0.501 |
rans | +0.494 |
Neg logit contributions | |
bys | -0.900 |
dx | -0.764 |
Interstitial | -0.742 |
oho | -0.735 |
ttes | -0.717 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
bys | +0.477 |
dx | +0.399 |
Interstitial | +0.384 |
oho | +0.380 |
ttes | +0.372 |
Neg logit contributions | |
Dill | -0.364 |
rimp | -0.353 |
Rivals | -0.349 |
Switch | -0.337 |
rans | -0.336 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Dill | +0.239 |
Rivals | +0.232 |
rimp | +0.231 |
Switch | +0.226 |
Marsh | +0.223 |
Neg logit contributions | |
bys | -0.256 |
dx | -0.209 |
Interstitial | -0.205 |
oho | -0.203 |
staking | -0.197 |
Token | L |
Token ID | 43 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Dill | +0.272 |
rimp | +0.264 |
Rivals | +0.261 |
rans | +0.251 |
Marsh | +0.251 |
Neg logit contributions | |
bys | -0.412 |
dx | -0.348 |
Interstitial | -0.336 |
oho | -0.335 |
ttes | -0.328 |
Token | ANS |
Token ID | 15037 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Dill | +0.595 |
rimp | +0.579 |
Rivals | +0.565 |
rans | +0.551 |
Switch | +0.548 |
Neg logit contributions | |
bys | -0.827 |
dx | -0.693 |
Interstitial | -0.671 |
oho | -0.660 |
ttes | -0.649 |
Token | ING |
Token ID | 2751 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
Dill | +1.589 |
Rivals | +1.540 |
Switch | +1.497 |
rimp | +1.484 |
Union | +1.437 |
Neg logit contributions | |
bys | -3.450 |
Interstitial | -2.984 |
dx | -2.958 |
oho | -2.952 |
ttes | -2.893 |
Token | , |
Token ID | 11 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
bys | +0.146 |
dx | +0.121 |
Interstitial | +0.116 |
oho | +0.115 |
ttes | +0.112 |
Neg logit contributions | |
Dill | -0.122 |
rimp | -0.119 |
Rivals | -0.118 |
Switch | -0.114 |
rans | -0.113 |
Token | MI |
Token ID | 15789 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
Dill | +0.417 |
rimp | +0.403 |
Rivals | +0.400 |
Switch | +0.386 |
rans | +0.382 |
Neg logit contributions | |
bys | -0.581 |
dx | -0.488 |
Interstitial | -0.471 |
oho | -0.467 |
ttes | -0.457 |
Token | -- |
Token ID | 1377 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Dill | +1.122 |
rimp | +1.088 |
Rivals | +1.082 |
Switch | +1.051 |
rans | +1.042 |
Neg logit contributions | |
bys | -1.310 |
dx | -1.082 |
Interstitial | -1.051 |
oho | -1.029 |
ttes | -1.004 |
Token | The |
Token ID | 383 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
bys | +0.261 |
dx | +0.224 |
Interstitial | +0.216 |
oho | +0.215 |
ttes | +0.210 |
Neg logit contributions | |
Dill | -0.148 |
rimp | -0.143 |
Rivals | -0.141 |
Switch | -0.135 |
rans | -0.134 |
Token | " |
Token ID | 1 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Dill | +0.121 |
rimp | +0.118 |
Rivals | +0.116 |
Marsh | +0.113 |
rans | +0.112 |
Neg logit contributions | |
bys | -0.193 |
dx | -0.164 |
oho | -0.158 |
Interstitial | -0.158 |
ttes | -0.155 |
Token | The |
Token ID | 464 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
Dill | +0.281 |
rimp | +0.271 |
Rivals | +0.269 |
Marsh | +0.263 |
Switch | +0.259 |
Neg logit contributions | |
bys | -0.410 |
dx | -0.344 |
oho | -0.334 |
Interstitial | -0.330 |
ttes | -0.326 |
Token | tools |
Token ID | 4899 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Dill | +0.088 |
rimp | +0.084 |
Rivals | +0.083 |
Switch | +0.081 |
replace | +0.080 |
Neg logit contributions | |
bys | -0.140 |
dx | -0.119 |
Interstitial | -0.117 |
oho | -0.114 |
ttes | -0.112 |
Token | can |
Token ID | 460 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Dill | +0.480 |
rimp | +0.461 |
Rivals | +0.458 |
replace | +0.447 |
Switch | +0.443 |
Neg logit contributions | |
bys | -0.590 |
dx | -0.491 |
Interstitial | -0.481 |
oho | -0.471 |
ttes | -0.457 |
Token | be |
Token ID | 307 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Dill | +0.151 |
rimp | +0.147 |
Rivals | +0.143 |
replace | +0.141 |
rans | +0.139 |
Neg logit contributions | |
bys | -0.253 |
dx | -0.216 |
Interstitial | -0.211 |
oho | -0.207 |
ttes | -0.203 |
Token | replaced |
Token ID | 6928 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
bys | +0.647 |
dx | +0.549 |
Interstitial | +0.535 |
oho | +0.525 |
ttes | +0.515 |
Neg logit contributions | |
Dill | -0.410 |
rimp | -0.389 |
Rivals | -0.389 |
replace | -0.377 |
Switch | -0.376 |
Token | , |
Token ID | 11 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
Dill | +1.780 |
replace | +1.692 |
rimp | +1.665 |
Switch | +1.633 |
Rivals | +1.630 |
Neg logit contributions | |
bys | -2.692 |
Interstitial | -2.319 |
dx | -2.316 |
oho | -2.223 |
ttes | -2.160 |
Token | the |
Token ID | 262 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Dill | +0.035 |
rimp | +0.034 |
Rivals | +0.033 |
replace | +0.033 |
Switch | +0.032 |
Neg logit contributions | |
bys | -0.054 |
dx | -0.045 |
Interstitial | -0.044 |
oho | -0.044 |
ttes | -0.043 |
Token | bike |
Token ID | 7161 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
Dill | +0.194 |
rimp | +0.185 |
Rivals | +0.184 |
Switch | +0.178 |
replace | +0.176 |
Neg logit contributions | |
bys | -0.322 |
dx | -0.274 |
Interstitial | -0.269 |
oho | -0.264 |
ttes | -0.257 |
Token | cannot |
Token ID | 2314 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
Dill | +0.562 |
rimp | +0.535 |
Rivals | +0.533 |
replace | +0.523 |
Switch | +0.515 |
Neg logit contributions | |
bys | -0.917 |
dx | -0.780 |
Interstitial | -0.768 |
oho | -0.749 |
ttes | -0.728 |
Token | ," |
Token ID | 553 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Dill | +0.027 |
rimp | +0.026 |
Rivals | +0.025 |
replace | +0.024 |
Switch | +0.024 |
Neg logit contributions | |
bys | -0.048 |
dx | -0.041 |
Interstitial | -0.041 |
oho | -0.040 |
ttes | -0.039 |
Token | I |
Token ID | 40 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
bys | +0.009 |
dx | +0.008 |
oho | +0.007 |
Interstitial | +0.007 |
ttes | +0.007 |
Neg logit contributions | |
Dill | -0.006 |
rimp | -0.006 |
Rivals | -0.006 |
Marsh | -0.005 |
Switch | -0.005 |
Token | can |
Token ID | 460 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Dill | +0.202 |
rimp | +0.196 |
Rivals | +0.193 |
Switch | +0.186 |
rans | +0.184 |
Neg logit contributions | |
bys | -0.320 |
dx | -0.272 |
Interstitial | -0.263 |
oho | -0.260 |
ttes | -0.254 |
Token | guarantee |
Token ID | 9149 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Dill | +0.267 |
rimp | +0.260 |
Rivals | +0.255 |
Switch | +0.249 |
replace | +0.249 |
Neg logit contributions | |
bys | -0.407 |
dx | -0.346 |
Interstitial | -0.337 |
oho | -0.330 |
ttes | -0.323 |
Token | that |
Token ID | 326 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Dill | +0.387 |
rimp | +0.370 |
Rivals | +0.366 |
Switch | +0.355 |
replace | +0.348 |
Neg logit contributions | |
bys | -0.658 |
dx | -0.564 |
Interstitial | -0.548 |
oho | -0.538 |
ttes | -0.527 |
Token | it |
Token ID | 340 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Dill | +0.208 |
rimp | +0.197 |
Rivals | +0.196 |
Switch | +0.191 |
replace | +0.187 |
Neg logit contributions | |
bys | -0.347 |
dx | -0.297 |
Interstitial | -0.289 |
oho | -0.283 |
ttes | -0.278 |
Token | tastes |
Token ID | 18221 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Dill | +0.235 |
rimp | +0.229 |
Rivals | +0.224 |
rans | +0.217 |
Switch | +0.217 |
Neg logit contributions | |
bys | -0.342 |
dx | -0.289 |
Interstitial | -0.281 |
oho | -0.276 |
ttes | -0.271 |
Token | as |
Token ID | 355 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Dill | +1.852 |
rimp | +1.759 |
Rivals | +1.732 |
replace | +1.721 |
Switch | +1.686 |
Neg logit contributions | |
bys | -2.950 |
dx | -2.524 |
Interstitial | -2.487 |
oho | -2.371 |
ttes | -2.345 |
Token | incredible |
Token ID | 8082 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
bys | +0.318 |
dx | +0.272 |
Interstitial | +0.264 |
oho | +0.259 |
ttes | +0.256 |
Neg logit contributions | |
Dill | -0.187 |
rimp | -0.180 |
Rivals | -0.178 |
Switch | -0.171 |
rans | -0.169 |
Token | as |
Token ID | 355 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
Dill | +0.278 |
rimp | +0.269 |
Rivals | +0.265 |
Switch | +0.256 |
rans | +0.255 |
Neg logit contributions | |
bys | -0.389 |
dx | -0.327 |
Interstitial | -0.319 |
oho | -0.312 |
ttes | -0.307 |
Token | it |
Token ID | 340 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
bys | +0.107 |
dx | +0.091 |
Interstitial | +0.088 |
oho | +0.087 |
ttes | +0.086 |
Neg logit contributions | |
Dill | -0.065 |
rimp | -0.062 |
Rivals | -0.061 |
Switch | -0.059 |
replace | -0.058 |
Token | looks |
Token ID | 3073 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Dill | +0.155 |
rimp | +0.151 |
Rivals | +0.148 |
rans | +0.143 |
Switch | +0.143 |
Neg logit contributions | |
bys | -0.218 |
dx | -0.183 |
Interstitial | -0.179 |
oho | -0.174 |
ttes | -0.170 |
Token | changes |
Token ID | 2458 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
Dill | +0.137 |
rimp | +0.131 |
Rivals | +0.130 |
Switch | +0.126 |
rans | +0.124 |
Neg logit contributions | |
bys | -0.230 |
dx | -0.197 |
Interstitial | -0.192 |
oho | -0.189 |
ttes | -0.185 |
Token | needed |
Token ID | 2622 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
bys | +1.126 |
dx | +0.952 |
Interstitial | +0.920 |
oho | +0.909 |
ttes | +0.888 |
Neg logit contributions | |
Dill | -0.775 |
rimp | -0.747 |
Rivals | -0.741 |
Switch | -0.715 |
rans | -0.711 |
Token | to |
Token ID | 284 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Dill | +0.476 |
rimp | +0.459 |
Rivals | +0.455 |
replace | +0.448 |
Switch | +0.444 |
Neg logit contributions | |
bys | -0.646 |
dx | -0.544 |
Interstitial | -0.527 |
oho | -0.516 |
ttes | -0.503 |
Token | make |
Token ID | 787 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Dill | +0.216 |
rimp | +0.209 |
Rivals | +0.209 |
replace | +0.203 |
Switch | +0.202 |
Neg logit contributions | |
bys | -0.346 |
dx | -0.296 |
Interstitial | -0.289 |
oho | -0.283 |
ttes | -0.275 |
Token | sure |
Token ID | 1654 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
Dill | +0.144 |
rimp | +0.137 |
Rivals | +0.137 |
Switch | +0.132 |
rans | +0.130 |
Neg logit contributions | |
bys | -0.271 |
dx | -0.233 |
Interstitial | -0.228 |
oho | -0.223 |
ttes | -0.219 |
Token | future |
Token ID | 2003 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Dill | +0.135 |
rimp | +0.129 |
Rivals | +0.129 |
Switch | +0.124 |
rans | +0.124 |
Neg logit contributions | |
bys | -0.204 |
dx | -0.173 |
Interstitial | -0.169 |
oho | -0.166 |
ttes | -0.162 |
Token | expenses |
Token ID | 9307 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Dill | +1.852 |
rimp | +1.773 |
Rivals | +1.771 |
Switch | +1.728 |
rans | +1.705 |
Neg logit contributions | |
bys | -3.125 |
dx | -2.700 |
Interstitial | -2.641 |
oho | -2.582 |
ttes | -2.511 |
Token | are |
Token ID | 389 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
bys | +0.653 |
dx | +0.551 |
Interstitial | +0.536 |
oho | +0.527 |
ttes | +0.513 |
Neg logit contributions | |
Dill | -0.465 |
rimp | -0.450 |
Rivals | -0.445 |
Switch | -0.431 |
rans | -0.429 |
Token | fully |
Token ID | 3938 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
Dill | +0.357 |
rimp | +0.343 |
Rivals | +0.340 |
Switch | +0.330 |
rans | +0.328 |
Neg logit contributions | |
bys | -0.542 |
dx | -0.458 |
Interstitial | -0.443 |
oho | -0.438 |
ttes | -0.429 |
Token | compliant |
Token ID | 31332 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
Dill | +1.112 |
rimp | +1.071 |
Rivals | +1.062 |
Switch | +1.035 |
rans | +1.032 |
Neg logit contributions | |
bys | -1.419 |
dx | -1.180 |
Interstitial | -1.146 |
oho | -1.125 |
ttes | -1.098 |
Token | with |
Token ID | 351 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
Dill | +1.030 |
rimp | +1.000 |
Rivals | +0.986 |
Switch | +0.961 |
rans | +0.957 |
Neg logit contributions | |
bys | -1.417 |
dx | -1.184 |
Interstitial | -1.151 |
oho | -1.137 |
ttes | -1.105 |