Token | ies |
Token ID | 444 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
═ | +0.129 |
DRAG | +0.116 |
Hour | +0.109 |
backdrop | +0.109 |
GEAR | +0.108 |
Neg logit contributions | |
ochond | -0.088 |
Filip | -0.083 |
amily | -0.072 |
estine | -0.072 |
urers | -0.070 |
Token | for |
Token ID | 329 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
═ | +0.291 |
DRAG | +0.256 |
backdrop | +0.237 |
Hour | +0.237 |
GEAR | +0.234 |
Neg logit contributions | |
ochond | -0.274 |
Filip | -0.262 |
amily | -0.233 |
estine | -0.232 |
urers | -0.226 |
Token | DC |
Token ID | 6257 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ochond | +0.070 |
Filip | +0.068 |
amily | +0.061 |
estine | +0.061 |
urers | +0.059 |
Neg logit contributions | |
═ | -0.059 |
DRAG | -0.051 |
backdrop | -0.046 |
Hour | -0.046 |
GEAR | -0.046 |
Token | 's |
Token ID | 338 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
═ | +0.118 |
DRAG | +0.101 |
Hour | +0.092 |
backdrop | +0.092 |
GEAR | +0.091 |
Neg logit contributions | |
ochond | -0.162 |
Filip | -0.155 |
amily | -0.141 |
estine | -0.141 |
urers | -0.138 |
Token | Vert |
Token ID | 24417 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ochond | +0.034 |
Filip | +0.033 |
amily | +0.030 |
estine | +0.030 |
urers | +0.029 |
Neg logit contributions | |
═ | -0.025 |
DRAG | -0.021 |
backdrop | -0.019 |
Hour | -0.019 |
GEAR | -0.019 |
Token | igo |
Token ID | 14031 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
═ | +1.803 |
DRAG | +1.571 |
backdrop | +1.423 |
Hour | +1.407 |
GEAR | +1.406 |
Neg logit contributions | |
ochond | -2.263 |
Filip | -2.152 |
amily | -1.965 |
estine | -1.960 |
urers | -1.920 |
Token | imprint |
Token ID | 29122 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
═ | +1.951 |
DRAG | +1.638 |
Hour | +1.482 |
backdrop | +1.469 |
GEAR | +1.446 |
Neg logit contributions | |
ochond | -3.497 |
Filip | -3.360 |
amily | -3.077 |
estine | -3.074 |
urers | -3.025 |
Token | and |
Token ID | 290 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
═ | +0.572 |
DRAG | +0.509 |
Hour | +0.474 |
backdrop | +0.473 |
GEAR | +0.469 |
Neg logit contributions | |
ochond | -0.503 |
Filip | -0.478 |
amily | -0.423 |
estine | -0.422 |
urers | -0.411 |
Token | a |
Token ID | 257 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
═ | +0.207 |
DRAG | +0.179 |
backdrop | +0.164 |
Hour | +0.164 |
GEAR | +0.163 |
Neg logit contributions | |
ochond | -0.233 |
Filip | -0.225 |
amily | -0.202 |
estine | -0.201 |
urers | -0.196 |
Token | handful |
Token ID | 10089 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
═ | +0.206 |
DRAG | +0.178 |
Hour | +0.164 |
backdrop | +0.163 |
GEAR | +0.162 |
Neg logit contributions | |
ochond | -0.244 |
Filip | -0.235 |
amily | -0.211 |
estine | -0.210 |
urers | -0.205 |
Token | of |
Token ID | 286 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
═ | +0.040 |
DRAG | +0.035 |
Hour | +0.032 |
backdrop | +0.032 |
GEAR | +0.031 |
Neg logit contributions | |
ochond | -0.052 |
Filip | -0.050 |
amily | -0.046 |
estine | -0.045 |
urers | -0.044 |
Token | Good |
Token ID | 10248 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
═ | +1.395 |
DRAG | +1.244 |
Hour | +1.162 |
backdrop | +1.159 |
GEAR | +1.149 |
Neg logit contributions | |
ochond | -1.154 |
Filip | -1.095 |
amily | -0.965 |
estine | -0.961 |
urers | -0.935 |
Token | rich |
Token ID | 7527 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
═ | +0.347 |
DRAG | +0.315 |
backdrop | +0.300 |
GEAR | +0.295 |
Hour | +0.294 |
Neg logit contributions | |
ochond | -0.173 |
Filip | -0.163 |
estine | -0.143 |
amily | -0.140 |
apeake | -0.133 |
Token | All |
Token ID | 1439 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
═ | +0.283 |
DRAG | +0.245 |
backdrop | +0.225 |
Hour | +0.225 |
GEAR | +0.222 |
Neg logit contributions | |
ochond | -0.338 |
Filip | -0.325 |
amily | -0.292 |
estine | -0.291 |
urers | -0.286 |
Token | - |
Token ID | 12 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
═ | +0.310 |
DRAG | +0.275 |
Hour | +0.256 |
backdrop | +0.255 |
GEAR | +0.253 |
Neg logit contributions | |
ochond | -0.283 |
Filip | -0.269 |
amily | -0.239 |
estine | -0.238 |
urers | -0.232 |
Token | Ter |
Token ID | 15156 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ochond | +0.255 |
Filip | +0.240 |
amily | +0.209 |
estine | +0.208 |
urers | +0.201 |
Neg logit contributions | |
═ | -0.367 |
DRAG | -0.330 |
Hour | -0.310 |
backdrop | -0.309 |
GEAR | -0.307 |
Token | rain |
Token ID | 3201 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
═ | +0.349 |
DRAG | +0.317 |
Hour | +0.299 |
backdrop | +0.298 |
GEAR | +0.296 |
Neg logit contributions | |
ochond | -0.200 |
Filip | -0.188 |
amily | -0.160 |
estine | -0.159 |
urers | -0.153 |
Token | KO |
Token ID | 21054 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
═ | +2.316 |
DRAG | +2.004 |
Hour | +1.833 |
backdrop | +1.824 |
GEAR | +1.807 |
Neg logit contributions | |
ochond | -3.001 |
Filip | -2.876 |
amily | -2.607 |
estine | -2.600 |
urers | -2.542 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
═ | +0.044 |
DRAG | +0.039 |
backdrop | +0.036 |
Hour | +0.036 |
GEAR | +0.036 |
Neg logit contributions | |
ochond | -0.041 |
Filip | -0.039 |
amily | -0.035 |
estine | -0.035 |
urers | -0.034 |
Token | tires |
Token ID | 17920 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
═ | +0.274 |
DRAG | +0.237 |
backdrop | +0.217 |
Hour | +0.217 |
GEAR | +0.214 |
Neg logit contributions | |
ochond | -0.346 |
Filip | -0.332 |
amily | -0.301 |
estine | -0.299 |
urers | -0.294 |
Token | specifically |
Token ID | 5734 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
═ | +1.002 |
DRAG | +0.890 |
Hour | +0.832 |
backdrop | +0.830 |
GEAR | +0.822 |
Neg logit contributions | |
ochond | -0.865 |
Filip | -0.821 |
amily | -0.726 |
estine | -0.723 |
urers | -0.703 |
Token | designed |
Token ID | 3562 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
═ | +0.302 |
DRAG | +0.264 |
Hour | +0.243 |
backdrop | +0.243 |
GEAR | +0.240 |
Neg logit contributions | |
ochond | -0.343 |
Filip | -0.327 |
amily | -0.295 |
estine | -0.294 |
urers | -0.287 |
Token | an |
Token ID | 281 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
ochond | +0.282 |
Filip | +0.270 |
amily | +0.241 |
estine | +0.240 |
urers | +0.235 |
Neg logit contributions | |
═ | -0.277 |
DRAG | -0.244 |
Hour | -0.225 |
backdrop | -0.225 |
GEAR | -0.223 |
Token | all |
Token ID | 477 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
═ | +0.066 |
DRAG | +0.057 |
backdrop | +0.053 |
Hour | +0.052 |
GEAR | +0.052 |
Neg logit contributions | |
ochond | -0.079 |
Filip | -0.075 |
amily | -0.068 |
estine | -0.068 |
urers | -0.066 |
Token | - |
Token ID | 12 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
ochond | +0.049 |
Filip | +0.046 |
estine | +0.042 |
amily | +0.041 |
fooled | +0.040 |
Neg logit contributions | |
═ | -0.053 |
DRAG | -0.047 |
Hour | -0.043 |
backdrop | -0.043 |
GEAR | -0.043 |
Token | new |
Token ID | 3605 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ochond | +0.512 |
Filip | +0.490 |
amily | +0.444 |
estine | +0.443 |
urers | +0.432 |
Neg logit contributions | |
═ | -0.407 |
DRAG | -0.353 |
Hour | -0.324 |
backdrop | -0.322 |
GEAR | -0.318 |
Token | Ter |
Token ID | 3813 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
═ | +0.474 |
DRAG | +0.410 |
Hour | +0.376 |
backdrop | +0.374 |
GEAR | +0.370 |
Neg logit contributions | |
ochond | -0.574 |
Filip | -0.553 |
amily | -0.498 |
estine | -0.496 |
urers | -0.486 |
Token | rain |
Token ID | 3201 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
═ | +0.624 |
DRAG | +0.563 |
Hour | +0.533 |
backdrop | +0.530 |
GEAR | +0.528 |
Neg logit contributions | |
ochond | -0.378 |
Filip | -0.356 |
amily | -0.303 |
estine | -0.303 |
urers | -0.292 |
Token | Management |
Token ID | 8549 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
═ | +1.683 |
DRAG | +1.439 |
Hour | +1.308 |
backdrop | +1.300 |
GEAR | +1.286 |
Neg logit contributions | |
ochond | -2.451 |
Filip | -2.356 |
amily | -2.146 |
estine | -2.140 |
urers | -2.096 |
Token | System |
Token ID | 4482 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
═ | +0.574 |
DRAG | +0.476 |
Hour | +0.423 |
backdrop | +0.423 |
GEAR | +0.416 |
Neg logit contributions | |
ochond | -1.046 |
Filip | -1.010 |
amily | -0.927 |
estine | -0.924 |
urers | -0.908 |
Token | ™ |
Token ID | 8151 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
═ | +0.622 |
DRAG | +0.552 |
Hour | +0.514 |
backdrop | +0.512 |
GEAR | +0.508 |
Neg logit contributions | |
ochond | -0.571 |
Filip | -0.543 |
amily | -0.482 |
estine | -0.481 |
urers | -0.468 |
Token | that |
Token ID | 326 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ochond | +0.173 |
Filip | +0.165 |
amily | +0.147 |
estine | +0.146 |
urers | +0.142 |
Neg logit contributions | |
═ | -0.191 |
DRAG | -0.169 |
Hour | -0.157 |
backdrop | -0.156 |
GEAR | -0.155 |
Token | enables |
Token ID | 13536 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ochond | +0.166 |
Filip | +0.158 |
amily | +0.142 |
estine | +0.141 |
urers | +0.138 |
Neg logit contributions | |
═ | -0.163 |
DRAG | -0.144 |
Hour | -0.134 |
backdrop | -0.133 |
GEAR | -0.132 |
Token | iser |
Token ID | 5847 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
═ | +1.007 |
DRAG | +0.899 |
Hour | +0.839 |
backdrop | +0.838 |
GEAR | +0.831 |
Neg logit contributions | |
ochond | -0.817 |
Filip | -0.773 |
amily | -0.682 |
estine | -0.679 |
urers | -0.660 |
Token | ies |
Token ID | 444 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
═ | +0.129 |
DRAG | +0.116 |
Hour | +0.109 |
backdrop | +0.109 |
GEAR | +0.108 |
Neg logit contributions | |
ochond | -0.088 |
Filip | -0.083 |
amily | -0.072 |
estine | -0.072 |
urers | -0.070 |
Token | for |
Token ID | 329 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
═ | +0.291 |
DRAG | +0.256 |
backdrop | +0.237 |
Hour | +0.237 |
GEAR | +0.234 |
Neg logit contributions | |
ochond | -0.274 |
Filip | -0.262 |
amily | -0.233 |
estine | -0.232 |
urers | -0.226 |
Token | DC |
Token ID | 6257 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ochond | +0.070 |
Filip | +0.068 |
amily | +0.061 |
estine | +0.061 |
urers | +0.059 |
Neg logit contributions | |
═ | -0.059 |
DRAG | -0.051 |
backdrop | -0.046 |
Hour | -0.046 |
GEAR | -0.046 |
Token | 's |
Token ID | 338 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
═ | +0.118 |
DRAG | +0.101 |
Hour | +0.092 |
backdrop | +0.092 |
GEAR | +0.091 |
Neg logit contributions | |
ochond | -0.162 |
Filip | -0.155 |
amily | -0.141 |
estine | -0.141 |
urers | -0.138 |
Token | Vert |
Token ID | 24417 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ochond | +0.034 |
Filip | +0.033 |
amily | +0.030 |
estine | +0.030 |
urers | +0.029 |
Neg logit contributions | |
═ | -0.025 |
DRAG | -0.021 |
backdrop | -0.019 |
Hour | -0.019 |
GEAR | -0.019 |
Token | igo |
Token ID | 14031 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
═ | +1.803 |
DRAG | +1.571 |
backdrop | +1.423 |
Hour | +1.407 |
GEAR | +1.406 |
Neg logit contributions | |
ochond | -2.263 |
Filip | -2.152 |
amily | -1.965 |
estine | -1.960 |
urers | -1.920 |
Token | imprint |
Token ID | 29122 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
═ | +1.951 |
DRAG | +1.638 |
Hour | +1.482 |
backdrop | +1.469 |
GEAR | +1.446 |
Neg logit contributions | |
ochond | -3.497 |
Filip | -3.360 |
amily | -3.077 |
estine | -3.074 |
urers | -3.025 |
Token | and |
Token ID | 290 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
═ | +0.572 |
DRAG | +0.509 |
Hour | +0.474 |
backdrop | +0.473 |
GEAR | +0.469 |
Neg logit contributions | |
ochond | -0.503 |
Filip | -0.478 |
amily | -0.423 |
estine | -0.422 |
urers | -0.411 |
Token | a |
Token ID | 257 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
═ | +0.207 |
DRAG | +0.179 |
backdrop | +0.164 |
Hour | +0.164 |
GEAR | +0.163 |
Neg logit contributions | |
ochond | -0.233 |
Filip | -0.225 |
amily | -0.202 |
estine | -0.201 |
urers | -0.196 |
Token | handful |
Token ID | 10089 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
═ | +0.206 |
DRAG | +0.178 |
Hour | +0.164 |
backdrop | +0.163 |
GEAR | +0.162 |
Neg logit contributions | |
ochond | -0.244 |
Filip | -0.235 |
amily | -0.211 |
estine | -0.210 |
urers | -0.205 |
Token | said |
Token ID | 531 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
═ | +0.310 |
DRAG | +0.269 |
Hour | +0.247 |
backdrop | +0.246 |
GEAR | +0.243 |
Neg logit contributions | |
ochond | -0.385 |
Filip | -0.369 |
amily | -0.334 |
estine | -0.333 |
urers | -0.325 |
Token | . |
Token ID | 13 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
═ | +0.573 |
DRAG | +0.511 |
Hour | +0.481 |
backdrop | +0.479 |
GEAR | +0.471 |
Neg logit contributions | |
ochond | -0.480 |
Filip | -0.455 |
amily | -0.402 |
estine | -0.402 |
urers | -0.390 |
Token |
|
Token ID | 198 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
═ | +0.554 |
DRAG | +0.500 |
Hour | +0.473 |
backdrop | +0.469 |
GEAR | +0.466 |
Neg logit contributions | |
ochond | -0.352 |
Filip | -0.326 |
estine | -0.284 |
amily | -0.283 |
urers | -0.273 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
═ | +0.455 |
DRAG | +0.413 |
Hour | +0.390 |
backdrop | +0.389 |
GEAR | +0.387 |
Neg logit contributions | |
ochond | -0.249 |
Filip | -0.233 |
amily | -0.197 |
estine | -0.196 |
urers | -0.189 |
Token | Ing |
Token ID | 27682 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
═ | +0.392 |
DRAG | +0.352 |
Hour | +0.334 |
backdrop | +0.332 |
GEAR | +0.329 |
Neg logit contributions | |
ochond | -0.227 |
Filip | -0.211 |
amily | -0.181 |
estine | -0.181 |
urers | -0.174 |
Token | raham |
Token ID | 13220 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ochond | +0.010 |
Filip | +0.009 |
estine | +0.007 |
amily | +0.007 |
urers | +0.007 |
Neg logit contributions | |
═ | -0.036 |
DRAG | -0.033 |
backdrop | -0.031 |
Hour | -0.031 |
GEAR | -0.031 |
Token | pressed |
Token ID | 12070 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
═ | +2.155 |
DRAG | +1.914 |
Hour | +1.810 |
backdrop | +1.795 |
GEAR | +1.771 |
Neg logit contributions | |
ochond | -1.772 |
Filip | -1.672 |
amily | -1.487 |
estine | -1.477 |
urers | -1.439 |
Token | him |
Token ID | 683 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
═ | +0.304 |
DRAG | +0.271 |
Hour | +0.253 |
backdrop | +0.253 |
GEAR | +0.250 |
Neg logit contributions | |
ochond | -0.253 |
Filip | -0.240 |
amily | -0.212 |
estine | -0.211 |
urers | -0.205 |
Token | on |
Token ID | 319 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
═ | +0.188 |
DRAG | +0.167 |
Hour | +0.155 |
backdrop | +0.154 |
GEAR | +0.153 |
Neg logit contributions | |
ochond | -0.174 |
Filip | -0.165 |
amily | -0.147 |
estine | -0.146 |
urers | -0.143 |
Token | whether |
Token ID | 1771 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
═ | +0.384 |
DRAG | +0.335 |
Hour | +0.308 |
backdrop | +0.307 |
GEAR | +0.304 |
Neg logit contributions | |
ochond | -0.452 |
Filip | -0.432 |
amily | -0.389 |
estine | -0.389 |
urers | -0.380 |
Token | he |
Token ID | 339 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
═ | +0.467 |
DRAG | +0.415 |
Hour | +0.386 |
backdrop | +0.385 |
GEAR | +0.381 |
Neg logit contributions | |
ochond | -0.433 |
Filip | -0.410 |
amily | -0.365 |
estine | -0.365 |
urers | -0.355 |
Token | was |
Token ID | 373 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
═ | +0.375 |
DRAG | +0.333 |
Hour | +0.309 |
backdrop | +0.309 |
GEAR | +0.306 |
Neg logit contributions | |
ochond | -0.341 |
Filip | -0.325 |
amily | -0.288 |
estine | -0.287 |
urers | -0.280 |
Token | Ragnar |
Token ID | 32797 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
═ | +0.718 |
DRAG | +0.634 |
Hour | +0.589 |
backdrop | +0.587 |
GEAR | +0.581 |
Neg logit contributions | |
ochond | -0.709 |
Filip | -0.675 |
amily | -0.603 |
estine | -0.600 |
urers | -0.586 |
Token | os |
Token ID | 418 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
═ | +0.559 |
DRAG | +0.500 |
Hour | +0.468 |
backdrop | +0.465 |
GEAR | +0.462 |
Neg logit contributions | |
ochond | -0.475 |
Filip | -0.451 |
amily | -0.401 |
estine | -0.398 |
urers | -0.387 |
Token | , |
Token ID | 11 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
═ | +0.682 |
DRAG | +0.606 |
Hour | +0.568 |
backdrop | +0.564 |
GEAR | +0.559 |
Neg logit contributions | |
ochond | -0.616 |
Filip | -0.584 |
amily | -0.520 |
estine | -0.517 |
urers | -0.504 |
Token | and |
Token ID | 290 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
═ | +0.566 |
DRAG | +0.501 |
Hour | +0.468 |
backdrop | +0.464 |
GEAR | +0.460 |
Neg logit contributions | |
ochond | -0.569 |
Filip | -0.540 |
amily | -0.485 |
estine | -0.482 |
urers | -0.471 |
Token | super |
Token ID | 2208 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
═ | +0.600 |
DRAG | +0.533 |
Hour | +0.498 |
backdrop | +0.496 |
GEAR | +0.492 |
Neg logit contributions | |
ochond | -0.543 |
Filip | -0.515 |
amily | -0.459 |
estine | -0.456 |
urers | -0.445 |
Token | - |
Token ID | 12 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
═ | +2.044 |
DRAG | +1.802 |
Hour | +1.689 |
backdrop | +1.678 |
GEAR | +1.668 |
Neg logit contributions | |
ochond | -1.866 |
Filip | -1.779 |
amily | -1.589 |
estine | -1.572 |
urers | -1.536 |
Token | bad |
Token ID | 14774 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
═ | +0.614 |
DRAG | +0.537 |
Hour | +0.499 |
backdrop | +0.496 |
GEAR | +0.492 |
Neg logit contributions | |
ochond | -0.644 |
Filip | -0.616 |
amily | -0.551 |
estine | -0.549 |
urers | -0.535 |
Token | if |
Token ID | 611 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
═ | +0.686 |
DRAG | +0.592 |
Hour | +0.543 |
backdrop | +0.541 |
GEAR | +0.534 |
Neg logit contributions | |
ochond | -0.883 |
Filip | -0.846 |
amily | -0.767 |
estine | -0.764 |
urers | -0.748 |
Token | you |
Token ID | 345 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
═ | +0.647 |
DRAG | +0.579 |
Hour | +0.543 |
backdrop | +0.540 |
GEAR | +0.536 |
Neg logit contributions | |
ochond | -0.535 |
Filip | -0.503 |
amily | -0.448 |
estine | -0.444 |
urers | -0.433 |
Token | hit |
Token ID | 2277 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
═ | +0.533 |
DRAG | +0.473 |
Hour | +0.441 |
backdrop | +0.441 |
GEAR | +0.437 |
Neg logit contributions | |
ochond | -0.448 |
Filip | -0.427 |
estine | -0.374 |
amily | -0.374 |
urers | -0.364 |
Token | to |
Token ID | 284 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
═ | +0.311 |
DRAG | +0.276 |
Hour | +0.257 |
backdrop | +0.256 |
GEAR | +0.253 |
Neg logit contributions | |
ochond | -0.293 |
Filip | -0.279 |
amily | -0.249 |
estine | -0.248 |
urers | -0.242 |
Token | sheep |
Token ID | 15900 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
═ | +0.160 |
DRAG | +0.141 |
Hour | +0.130 |
backdrop | +0.130 |
GEAR | +0.129 |
Neg logit contributions | |
ochond | -0.159 |
Filip | -0.151 |
amily | -0.135 |
estine | -0.135 |
urers | -0.131 |
Token | a |
Token ID | 257 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
═ | +1.037 |
DRAG | +0.917 |
Hour | +0.854 |
backdrop | +0.851 |
GEAR | +0.842 |
Neg logit contributions | |
ochond | -0.997 |
Filip | -0.948 |
amily | -0.847 |
estine | -0.842 |
urers | -0.822 |
Token | minion |
Token ID | 28365 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
═ | +0.393 |
DRAG | +0.342 |
Hour | +0.314 |
backdrop | +0.313 |
GEAR | +0.310 |
Neg logit contributions | |
ochond | -0.458 |
Filip | -0.439 |
amily | -0.395 |
estine | -0.394 |
urers | -0.385 |
Token | was |
Token ID | 373 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
═ | +0.350 |
DRAG | +0.310 |
Hour | +0.289 |
backdrop | +0.288 |
GEAR | +0.285 |
Neg logit contributions | |
ochond | -0.329 |
Filip | -0.313 |
amily | -0.280 |
estine | -0.278 |
urers | -0.271 |
Token | super |
Token ID | 2208 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
═ | +0.648 |
DRAG | +0.573 |
Hour | +0.533 |
backdrop | +0.531 |
GEAR | +0.526 |
Neg logit contributions | |
ochond | -0.617 |
Filip | -0.587 |
amily | -0.523 |
estine | -0.521 |
urers | -0.508 |
Token | - |
Token ID | 12 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
═ | +1.896 |
DRAG | +1.668 |
Hour | +1.547 |
backdrop | +1.541 |
GEAR | +1.528 |
Neg logit contributions | |
ochond | -1.951 |
Filip | -1.861 |
amily | -1.668 |
estine | -1.661 |
urers | -1.622 |
Token | good |
Token ID | 11274 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
═ | +0.689 |
DRAG | +0.609 |
Hour | +0.567 |
backdrop | +0.564 |
GEAR | +0.560 |
Neg logit contributions | |
ochond | -0.652 |
Filip | -0.621 |
amily | -0.553 |
estine | -0.551 |
urers | -0.537 |
Token | if |
Token ID | 611 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
═ | +1.295 |
DRAG | +1.151 |
Hour | +1.078 |
backdrop | +1.075 |
GEAR | +1.065 |
Neg logit contributions | |
ochond | -1.108 |
Filip | -1.053 |
amily | -0.932 |
estine | -0.927 |
urers | -0.903 |
Token | you |
Token ID | 345 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
═ | +0.629 |
DRAG | +0.562 |
Hour | +0.527 |
backdrop | +0.525 |
GEAR | +0.520 |
Neg logit contributions | |
ochond | -0.505 |
Filip | -0.477 |
amily | -0.421 |
estine | -0.418 |
urers | -0.407 |
Token | got |
Token ID | 1392 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
═ | +0.501 |
DRAG | +0.440 |
Hour | +0.409 |
backdrop | +0.407 |
GEAR | +0.405 |
Neg logit contributions | |
ochond | -0.473 |
Filip | -0.454 |
estine | -0.400 |
amily | -0.398 |
fooled | -0.392 |
Token | early |
Token ID | 1903 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
═ | +0.185 |
DRAG | +0.161 |
backdrop | +0.147 |
Hour | +0.146 |
GEAR | +0.145 |
Neg logit contributions | |
ochond | -0.226 |
Filip | -0.217 |
amily | -0.196 |
estine | -0.196 |
urers | -0.191 |
Token | investor |
Token ID | 15811 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
═ | +0.076 |
DRAG | +0.066 |
Hour | +0.061 |
backdrop | +0.061 |
GEAR | +0.060 |
Neg logit contributions | |
ochond | -0.090 |
Filip | -0.086 |
amily | -0.078 |
estine | -0.077 |
urers | -0.076 |
Token | in |
Token ID | 287 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
═ | +0.023 |
DRAG | +0.020 |
Hour | +0.019 |
backdrop | +0.019 |
GEAR | +0.019 |
Neg logit contributions | |
ochond | -0.021 |
Filip | -0.020 |
amily | -0.018 |
estine | -0.018 |
urers | -0.018 |
Token | Ethereum |
Token ID | 20313 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
═ | +0.139 |
DRAG | +0.123 |
Hour | +0.114 |
backdrop | +0.114 |
GEAR | +0.113 |
Neg logit contributions | |
ochond | -0.127 |
Filip | -0.121 |
amily | -0.108 |
estine | -0.107 |
urers | -0.105 |
Token | told |
Token ID | 1297 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
ochond | +0.145 |
Filip | +0.138 |
amily | +0.123 |
estine | +0.123 |
urers | +0.119 |
Neg logit contributions | |
═ | -0.151 |
DRAG | -0.133 |
Hour | -0.124 |
backdrop | -0.123 |
GEAR | -0.122 |
Token | Vice |
Token ID | 11079 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
═ | +0.574 |
DRAG | +0.504 |
Hour | +0.467 |
backdrop | +0.464 |
GEAR | +0.459 |
Neg logit contributions | |
ochond | -0.624 |
Filip | -0.594 |
amily | -0.536 |
estine | -0.534 |
urers | -0.522 |
Token | . |
Token ID | 13 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
═ | +1.928 |
DRAG | +1.699 |
Hour | +1.602 |
backdrop | +1.586 |
GEAR | +1.573 |
Neg logit contributions | |
ochond | -1.763 |
Filip | -1.660 |
amily | -1.492 |
estine | -1.482 |
urers | -1.443 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
═ | +0.505 |
DRAG | +0.453 |
Hour | +0.428 |
backdrop | +0.425 |
GEAR | +0.422 |
Neg logit contributions | |
ochond | -0.348 |
Filip | -0.327 |
amily | -0.285 |
estine | -0.284 |
urers | -0.275 |
Token | I |
Token ID | 40 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
═ | +0.759 |
DRAG | +0.682 |
Hour | +0.643 |
backdrop | +0.641 |
GEAR | +0.635 |
Neg logit contributions | |
ochond | -0.504 |
Filip | -0.474 |
amily | -0.409 |
estine | -0.407 |
urers | -0.395 |
Token | don |
Token ID | 836 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
═ | +0.198 |
DRAG | +0.174 |
Hour | +0.162 |
backdrop | +0.161 |
GEAR | +0.160 |
Neg logit contributions | |
ochond | -0.198 |
Filip | -0.189 |
amily | -0.169 |
estine | -0.168 |
urers | -0.164 |
Token | 't |
Token ID | 470 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
═ | +0.462 |
DRAG | +0.421 |
Hour | +0.396 |
backdrop | +0.396 |
GEAR | +0.393 |
Neg logit contributions | |
ochond | -0.264 |
Filip | -0.248 |
amily | -0.209 |
estine | -0.209 |
urers | -0.201 |
Token | With |
Token ID | 3152 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
═ | +0.023 |
DRAG | +0.021 |
Hour | +0.020 |
backdrop | +0.020 |
GEAR | +0.020 |
Neg logit contributions | |
ochond | -0.016 |
Filip | -0.015 |
amily | -0.013 |
estine | -0.013 |
urers | -0.012 |
Token | filming |
Token ID | 17691 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
ochond | +0.522 |
Filip | +0.502 |
amily | +0.445 |
estine | +0.443 |
urers | +0.432 |
Neg logit contributions | |
═ | -0.542 |
DRAG | -0.477 |
Hour | -0.442 |
backdrop | -0.439 |
GEAR | -0.436 |
Token | for |
Token ID | 329 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
═ | +0.698 |
DRAG | +0.608 |
Hour | +0.562 |
backdrop | +0.556 |
GEAR | +0.554 |
Neg logit contributions | |
ochond | -0.733 |
Filip | -0.704 |
amily | -0.626 |
estine | -0.625 |
urers | -0.610 |
Token | Teen |
Token ID | 21432 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
═ | +0.094 |
DRAG | +0.082 |
backdrop | +0.076 |
Hour | +0.076 |
GEAR | +0.075 |
Neg logit contributions | |
ochond | -0.093 |
Filip | -0.089 |
amily | -0.079 |
estine | -0.079 |
urers | -0.077 |
Token | age |
Token ID | 496 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
═ | +0.585 |
DRAG | +0.517 |
backdrop | +0.477 |
Hour | +0.473 |
GEAR | +0.471 |
Neg logit contributions | |
ochond | -0.566 |
Filip | -0.544 |
amily | -0.483 |
estine | -0.480 |
urers | -0.470 |
Token | Mutant |
Token ID | 35319 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
═ | +0.457 |
DRAG | +0.385 |
backdrop | +0.344 |
Hour | +0.343 |
GEAR | +0.338 |
Neg logit contributions | |
ochond | -0.747 |
Filip | -0.721 |
amily | -0.658 |
estine | -0.656 |
urers | -0.643 |
Token | Ninja |
Token ID | 14152 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
═ | +1.082 |
DRAG | +0.862 |
Hour | +0.742 |
backdrop | +0.738 |
GEAR | +0.724 |
Neg logit contributions | |
ochond | -2.602 |
Filip | -2.517 |
amily | -2.328 |
estine | -2.324 |
urers | -2.285 |
Token | Turtles |
Token ID | 44356 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
═ | +1.493 |
DRAG | +1.294 |
Hour | +1.192 |
backdrop | +1.182 |
GEAR | +1.172 |
Neg logit contributions | |
ochond | -2.003 |
Filip | -1.901 |
amily | -1.748 |
estine | -1.737 |
urers | -1.699 |
Token | II |
Token ID | 2873 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
═ | +0.391 |
DRAG | +0.344 |
Hour | +0.317 |
backdrop | +0.317 |
GEAR | +0.314 |
Neg logit contributions | |
ochond | -0.379 |
Filip | -0.363 |
amily | -0.322 |
estine | -0.321 |
urers | -0.312 |
Token | : |
Token ID | 25 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
═ | +0.295 |
DRAG | +0.257 |
Hour | +0.236 |
backdrop | +0.236 |
GEAR | +0.234 |
Neg logit contributions | |
ochond | -0.329 |
Filip | -0.316 |
amily | -0.283 |
estine | -0.282 |
urers | -0.275 |
Token | Half |
Token ID | 13139 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
═ | +0.088 |
DRAG | +0.077 |
Hour | +0.072 |
backdrop | +0.071 |
GEAR | +0.070 |
Neg logit contributions | |
ochond | -0.103 |
Filip | -0.098 |
amily | -0.089 |
estine | -0.088 |
urers | -0.086 |
Token | but |
Token ID | 475 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
═ | +0.215 |
DRAG | +0.189 |
Hour | +0.175 |
backdrop | +0.175 |
GEAR | +0.173 |
Neg logit contributions | |
ochond | -0.224 |
Filip | -0.214 |
amily | -0.191 |
estine | -0.191 |
urers | -0.186 |
Token | still |
Token ID | 991 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
═ | +0.283 |
DRAG | +0.250 |
Hour | +0.234 |
backdrop | +0.233 |
GEAR | +0.230 |
Neg logit contributions | |
ochond | -0.266 |
Filip | -0.253 |
amily | -0.226 |
estine | -0.225 |
urers | -0.219 |
Token | very |
Token ID | 845 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ochond | +0.115 |
Filip | +0.109 |
amily | +0.098 |
estine | +0.097 |
urers | +0.095 |
Neg logit contributions | |
═ | -0.119 |
DRAG | -0.105 |
Hour | -0.097 |
backdrop | -0.097 |
GEAR | -0.096 |
Token | adorable |
Token ID | 29012 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ochond | +0.149 |
Filip | +0.142 |
amily | +0.127 |
estine | +0.126 |
urers | +0.123 |
Neg logit contributions | |
═ | -0.150 |
DRAG | -0.132 |
Hour | -0.123 |
backdrop | -0.123 |
GEAR | -0.121 |
Token | and |
Token ID | 290 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
═ | +1.177 |
DRAG | +1.052 |
Hour | +0.996 |
backdrop | +0.994 |
GEAR | +0.972 |
Neg logit contributions | |
ochond | -0.862 |
Filip | -0.810 |
estine | -0.710 |
amily | -0.708 |
urers | -0.692 |
Token | tw |
Token ID | 665 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
═ | +0.150 |
DRAG | +0.132 |
Hour | +0.122 |
backdrop | +0.122 |
GEAR | +0.121 |
Neg logit contributions | |
ochond | -0.152 |
Filip | -0.145 |
amily | -0.130 |
estine | -0.129 |
urers | -0.126 |
Token | ee |
Token ID | 1453 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
═ | +1.873 |
DRAG | +1.654 |
Hour | +1.588 |
backdrop | +1.543 |
GEAR | +1.536 |
Neg logit contributions | |
ochond | -1.701 |
Filip | -1.627 |
estine | -1.434 |
amily | -1.403 |
fooled | -1.396 |
Token | ! |
Token ID | 0 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
═ | +0.078 |
DRAG | +0.070 |
Hour | +0.066 |
backdrop | +0.065 |
GEAR | +0.064 |
Neg logit contributions | |
ochond | -0.058 |
Filip | -0.055 |
estine | -0.048 |
amily | -0.047 |
urers | -0.046 |
Token | — |
Token ID | 851 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
═ | +0.345 |
DRAG | +0.307 |
Hour | +0.288 |
backdrop | +0.287 |
GEAR | +0.284 |
Neg logit contributions | |
ochond | -0.289 |
Filip | -0.274 |
amily | -0.242 |
estine | -0.241 |
urers | -0.235 |
Token | living |
Token ID | 2877 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
═ | +0.192 |
DRAG | +0.170 |
Hour | +0.157 |
backdrop | +0.157 |
GEAR | +0.155 |
Neg logit contributions | |
ochond | -0.194 |
Filip | -0.185 |
amily | -0.165 |
estine | -0.165 |
urers | -0.161 |
Token | room |
Token ID | 2119 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
═ | +0.458 |
DRAG | +0.403 |
backdrop | +0.378 |
Hour | +0.378 |
GEAR | +0.370 |
Neg logit contributions | |
ochond | -0.463 |
Filip | -0.438 |
amily | -0.394 |
estine | -0.393 |
urers | -0.385 |
Token | modify |
Token ID | 13096 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
ochond | +0.189 |
Filip | +0.182 |
amily | +0.164 |
estine | +0.164 |
urers | +0.160 |
Neg logit contributions | |
═ | -0.151 |
DRAG | -0.130 |
Hour | -0.120 |
backdrop | -0.119 |
GEAR | -0.118 |
Token | your |
Token ID | 534 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
═ | +0.292 |
DRAG | +0.251 |
Hour | +0.230 |
backdrop | +0.229 |
GEAR | +0.226 |
Neg logit contributions | |
ochond | -0.372 |
Filip | -0.358 |
amily | -0.323 |
estine | -0.322 |
urers | -0.316 |
Token | interior |
Token ID | 11087 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
═ | +0.343 |
DRAG | +0.292 |
Hour | +0.266 |
backdrop | +0.263 |
GEAR | +0.260 |
Neg logit contributions | |
ochond | -0.490 |
Filip | -0.473 |
amily | -0.428 |
estine | -0.427 |
urers | -0.419 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
═ | +0.624 |
DRAG | +0.551 |
Hour | +0.513 |
backdrop | +0.509 |
GEAR | +0.506 |
Neg logit contributions | |
ochond | -0.581 |
Filip | -0.556 |
amily | -0.492 |
estine | -0.491 |
urers | -0.480 |
Token | Susp |
Token ID | 31922 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
═ | +0.163 |
DRAG | +0.143 |
backdrop | +0.132 |
Hour | +0.131 |
GEAR | +0.130 |
Neg logit contributions | |
ochond | -0.169 |
Filip | -0.164 |
amily | -0.145 |
estine | -0.145 |
urers | -0.142 |
Token | ension |
Token ID | 3004 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
═ | +1.693 |
DRAG | +1.500 |
Hour | +1.404 |
backdrop | +1.394 |
GEAR | +1.384 |
Neg logit contributions | |
ochond | -1.541 |
Filip | -1.468 |
estine | -1.298 |
amily | -1.297 |
fooled | -1.252 |
Token | and |
Token ID | 290 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
═ | +1.728 |
DRAG | +1.514 |
Hour | +1.399 |
backdrop | +1.394 |
GEAR | +1.382 |
Neg logit contributions | |
ochond | -1.885 |
Filip | -1.799 |
amily | -1.618 |
estine | -1.614 |
urers | -1.573 |
Token | engine |
Token ID | 3113 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
═ | +0.224 |
DRAG | +0.190 |
Hour | +0.171 |
backdrop | +0.171 |
GEAR | +0.168 |
Neg logit contributions | |
ochond | -0.322 |
Filip | -0.312 |
amily | -0.282 |
estine | -0.281 |
urers | -0.277 |
Token | performance |
Token ID | 2854 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
═ | +0.244 |
DRAG | +0.212 |
Hour | +0.195 |
backdrop | +0.194 |
GEAR | +0.192 |
Neg logit contributions | |
ochond | -0.288 |
Filip | -0.277 |
amily | -0.249 |
estine | -0.248 |
urers | -0.243 |
Token | can |
Token ID | 460 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
═ | +0.784 |
DRAG | +0.687 |
Hour | +0.635 |
backdrop | +0.632 |
GEAR | +0.626 |
Neg logit contributions | |
ochond | -0.816 |
Filip | -0.782 |
amily | -0.698 |
estine | -0.694 |
urers | -0.681 |
Token | be |
Token ID | 307 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
═ | +0.179 |
DRAG | +0.156 |
Hour | +0.143 |
backdrop | +0.142 |
GEAR | +0.141 |
Neg logit contributions | |
ochond | -0.214 |
Filip | -0.205 |
amily | -0.185 |
estine | -0.185 |
urers | -0.181 |
Token | Film |
Token ID | 13741 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
═ | +0.473 |
DRAG | +0.393 |
backdrop | +0.351 |
Hour | +0.347 |
GEAR | +0.346 |
Neg logit contributions | |
ochond | -0.816 |
Filip | -0.786 |
amily | -0.725 |
estine | -0.720 |
urers | -0.711 |
Token | Channel |
Token ID | 11102 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
═ | +0.314 |
DRAG | +0.269 |
Hour | +0.245 |
backdrop | +0.244 |
GEAR | +0.241 |
Neg logit contributions | |
ochond | -0.450 |
Filip | -0.433 |
amily | -0.394 |
estine | -0.392 |
urers | -0.385 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
═ | +0.561 |
DRAG | +0.498 |
Hour | +0.465 |
backdrop | +0.462 |
GEAR | +0.458 |
Neg logit contributions | |
ochond | -0.523 |
Filip | -0.497 |
amily | -0.441 |
estine | -0.440 |
urers | -0.429 |
Token | The |
Token ID | 383 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
═ | +0.292 |
DRAG | +0.257 |
Hour | +0.238 |
backdrop | +0.238 |
GEAR | +0.235 |
Neg logit contributions | |
ochond | -0.295 |
Filip | -0.281 |
amily | -0.251 |
estine | -0.250 |
urers | -0.244 |
Token | Sund |
Token ID | 3309 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
═ | +0.333 |
DRAG | +0.286 |
backdrop | +0.261 |
Hour | +0.260 |
GEAR | +0.257 |
Neg logit contributions | |
ochond | -0.440 |
Filip | -0.423 |
amily | -0.383 |
estine | -0.382 |
urers | -0.374 |
Token | ance |
Token ID | 590 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
═ | +0.653 |
DRAG | +0.551 |
backdrop | +0.489 |
Hour | +0.485 |
GEAR | +0.480 |
Neg logit contributions | |
ochond | -1.123 |
Filip | -1.083 |
amily | -0.995 |
estine | -0.992 |
urers | -0.974 |
Token | Channel |
Token ID | 11102 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
═ | +1.147 |
DRAG | +0.929 |
Hour | +0.855 |
backdrop | +0.814 |
GEAR | +0.803 |
Neg logit contributions | |
ochond | -2.450 |
Filip | -2.340 |
amily | -2.183 |
estine | -2.169 |
urers | -2.145 |
Token | , |
Token ID | 11 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
═ | +0.831 |
DRAG | +0.733 |
Hour | +0.686 |
backdrop | +0.677 |
GEAR | +0.670 |
Neg logit contributions | |
ochond | -0.846 |
Filip | -0.804 |
amily | -0.721 |
estine | -0.716 |
urers | -0.701 |
Token | and |
Token ID | 290 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
═ | +0.295 |
DRAG | +0.257 |
Hour | +0.236 |
backdrop | +0.236 |
GEAR | +0.233 |
Neg logit contributions | |
ochond | -0.348 |
Filip | -0.333 |
amily | -0.300 |
estine | -0.299 |
urers | -0.293 |
Token | WE |
Token ID | 12887 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
═ | +0.194 |
DRAG | +0.169 |
Hour | +0.155 |
backdrop | +0.155 |
GEAR | +0.153 |
Neg logit contributions | |
ochond | -0.229 |
Filip | -0.220 |
amily | -0.198 |
estine | -0.197 |
urers | -0.193 |
Token | tv |
Token ID | 31557 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
═ | +0.885 |
DRAG | +0.790 |
Hour | +0.740 |
backdrop | +0.737 |
GEAR | +0.731 |
Neg logit contributions | |
ochond | -0.715 |
Filip | -0.677 |
amily | -0.595 |
estine | -0.594 |
urers | -0.577 |
Token | . |
Token ID | 13 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ochond | +0.162 |
Filip | +0.153 |
amily | +0.135 |
estine | +0.134 |
urers | +0.131 |
Neg logit contributions | |
═ | -0.199 |
DRAG | -0.178 |
Hour | -0.168 |
backdrop | -0.166 |
GEAR | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
═ | +0.316 |
DRAG | +0.285 |
Hour | +0.268 |
backdrop | +0.267 |
GEAR | +0.265 |
Neg logit contributions | |
ochond | -0.213 |
Filip | -0.200 |
amily | -0.174 |
estine | -0.173 |
urers | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
═ | +0.147 |
DRAG | +0.133 |
Hour | +0.126 |
backdrop | +0.126 |
GEAR | +0.125 |
Neg logit contributions | |
ochond | -0.079 |
Filip | -0.075 |
amily | -0.063 |
estine | -0.062 |
urers | -0.060 |
Token | The |
Token ID | 464 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
═ | +0.116 |
DRAG | +0.104 |
Hour | +0.098 |
backdrop | +0.098 |
GEAR | +0.097 |
Neg logit contributions | |
ochond | -0.079 |
Filip | -0.074 |
amily | -0.065 |
estine | -0.064 |
urers | -0.063 |
Token | Walking |
Token ID | 21276 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
═ | +0.085 |
DRAG | +0.069 |
Hour | +0.060 |
backdrop | +0.059 |
GEAR | +0.059 |
Neg logit contributions | |
ochond | -0.175 |
Filip | -0.169 |
amily | -0.156 |
estine | -0.155 |
urers | -0.153 |
Token | Dead |
Token ID | 5542 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
═ | +0.970 |
DRAG | +0.778 |
backdrop | +0.676 |
GEAR | +0.668 |
Hour | +0.657 |
Neg logit contributions | |
ochond | -1.883 |
Filip | -1.834 |
amily | -1.674 |
estine | -1.672 |
urers | -1.638 |
Token | is |
Token ID | 318 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
═ | +1.837 |
DRAG | +1.644 |
Hour | +1.548 |
backdrop | +1.535 |
GEAR | +1.512 |
Neg logit contributions | |
ochond | -1.738 |
Filip | -1.636 |
amily | -1.464 |
estine | -1.457 |
urers | -1.422 |
Token | coming |
Token ID | 2406 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
═ | +0.366 |
DRAG | +0.323 |
Hour | +0.300 |
backdrop | +0.299 |
GEAR | +0.296 |
Neg logit contributions | |
ochond | -0.373 |
Filip | -0.355 |
amily | -0.318 |
estine | -0.317 |
urers | -0.309 |
Token | back |
Token ID | 736 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
═ | +0.634 |
DRAG | +0.565 |
Hour | +0.528 |
backdrop | +0.526 |
GEAR | +0.520 |
Neg logit contributions | |
ochond | -0.636 |
Filip | -0.596 |
amily | -0.540 |
estine | -0.537 |
urers | -0.524 |
Token | to |
Token ID | 284 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ochond | +0.144 |
Filip | +0.136 |
amily | +0.122 |
estine | +0.122 |
urers | +0.118 |
Neg logit contributions | |
═ | -0.153 |
DRAG | -0.136 |
Hour | -0.127 |
backdrop | -0.127 |
GEAR | -0.126 |
Token | Horror |
Token ID | 22732 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
═ | +0.117 |
DRAG | +0.103 |
Hour | +0.095 |
backdrop | +0.095 |
GEAR | +0.094 |
Neg logit contributions | |
ochond | -0.133 |
Filip | -0.127 |
amily | -0.114 |
estine | -0.114 |
urers | -0.111 |
Token | 4 |
Token ID | 19 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
═ | +0.248 |
DRAG | +0.222 |
Hour | +0.207 |
backdrop | +0.207 |
GEAR | +0.205 |
Neg logit contributions | |
ochond | -0.194 |
Filip | -0.184 |
amily | -0.161 |
estine | -0.161 |
urers | -0.156 |
Token | SS |
Token ID | 6723 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
═ | +0.307 |
DRAG | +0.273 |
Hour | +0.254 |
backdrop | +0.253 |
GEAR | +0.251 |
Neg logit contributions | |
ochond | -0.282 |
Filip | -0.268 |
amily | -0.239 |
estine | -0.238 |
urers | -0.232 |
Token | BN |
Token ID | 15766 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
═ | +1.236 |
DRAG | +1.108 |
Hour | +1.039 |
backdrop | +1.029 |
GEAR | +1.028 |
Neg logit contributions | |
ochond | -0.955 |
Filip | -0.903 |
estine | -0.796 |
amily | -0.790 |
urers | -0.766 |
Token | , |
Token ID | 11 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
═ | +0.463 |
DRAG | +0.402 |
Hour | +0.369 |
backdrop | +0.367 |
GEAR | +0.364 |
Neg logit contributions | |
ochond | -0.578 |
Filip | -0.552 |
amily | -0.500 |
estine | -0.499 |
urers | -0.487 |
Token | 6 |
Token ID | 718 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
═ | +0.392 |
DRAG | +0.348 |
Hour | +0.324 |
backdrop | +0.323 |
GEAR | +0.321 |
Neg logit contributions | |
ochond | -0.351 |
Filip | -0.334 |
amily | -0.296 |
estine | -0.295 |
urers | -0.287 |
Token | Rub |
Token ID | 6256 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
═ | +0.383 |
DRAG | +0.334 |
Hour | +0.306 |
backdrop | +0.305 |
GEAR | +0.302 |
Neg logit contributions | |
ochond | -0.460 |
Filip | -0.441 |
amily | -0.398 |
estine | -0.397 |
urers | -0.388 |
Token | is |
Token ID | 271 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
═ | +2.154 |
DRAG | +1.926 |
Hour | +1.825 |
backdrop | +1.811 |
GEAR | +1.795 |
Neg logit contributions | |
ochond | -1.398 |
Filip | -1.338 |
amily | -1.151 |
estine | -1.146 |
urers | -1.106 |
Token | class |
Token ID | 1398 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
═ | +0.503 |
DRAG | +0.445 |
Hour | +0.414 |
backdrop | +0.413 |
GEAR | +0.409 |
Neg logit contributions | |
ochond | -0.473 |
Filip | -0.451 |
amily | -0.401 |
estine | -0.399 |
urers | -0.390 |
Token | SS |
Token ID | 6723 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
═ | +0.825 |
DRAG | +0.731 |
Hour | +0.679 |
backdrop | +0.675 |
GEAR | +0.669 |
Neg logit contributions | |
ochond | -0.813 |
Filip | -0.771 |
amily | -0.692 |
estine | -0.688 |
urers | -0.671 |
Token | N |
Token ID | 45 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
═ | +1.229 |
DRAG | +1.114 |
Hour | +1.054 |
backdrop | +1.045 |
GEAR | +1.041 |
Neg logit contributions | |
ochond | -0.756 |
Filip | -0.705 |
estine | -0.607 |
amily | -0.605 |
urers | -0.580 |
Token | ), |
Token ID | 828 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ochond | +0.463 |
Filip | +0.442 |
amily | +0.394 |
estine | +0.393 |
urers | +0.383 |
Neg logit contributions | |
═ | -0.468 |
DRAG | -0.412 |
Hour | -0.382 |
backdrop | -0.382 |
GEAR | -0.378 |
Token | corps |
Token ID | 16812 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
═ | +0.450 |
DRAG | +0.385 |
Hour | +0.350 |
backdrop | +0.347 |
GEAR | +0.346 |
Neg logit contributions | |
ochond | -0.632 |
Filip | -0.611 |
amily | -0.553 |
estine | -0.550 |
urers | -0.540 |
Token | to |
Token ID | 284 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ochond | +0.228 |
Filip | +0.217 |
amily | +0.192 |
estine | +0.191 |
urers | +0.186 |
Neg logit contributions | |
═ | -0.258 |
DRAG | -0.229 |
Hour | -0.213 |
backdrop | -0.213 |
GEAR | -0.211 |
Token | � |
Token ID | 564 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
═ | +0.199 |
DRAG | +0.177 |
Hour | +0.166 |
backdrop | +0.165 |
GEAR | +0.163 |
Neg logit contributions | |
ochond | -0.177 |
Filip | -0.167 |
amily | -0.149 |
estine | -0.149 |
urers | -0.144 |
Token | � |
Token ID | 250 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
═ | +0.109 |
DRAG | +0.090 |
Hour | +0.080 |
backdrop | +0.080 |
GEAR | +0.079 |
Neg logit contributions | |
ochond | -0.209 |
Filip | -0.202 |
amily | -0.186 |
estine | -0.185 |
urers | -0.182 |
Token | rub |
Token ID | 25089 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
═ | +0.645 |
DRAG | +0.572 |
Hour | +0.536 |
backdrop | +0.533 |
GEAR | +0.528 |
Neg logit contributions | |
ochond | -0.553 |
Filip | -0.525 |
amily | -0.462 |
estine | -0.462 |
urers | -0.449 |
Token | ble |
Token ID | 903 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
═ | +1.543 |
DRAG | +1.364 |
Hour | +1.284 |
backdrop | +1.283 |
GEAR | +1.269 |
Neg logit contributions | |
ochond | -1.278 |
Filip | -1.222 |
amily | -1.070 |
estine | -1.068 |
urers | -1.042 |
Token | . |
Token ID | 13 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
═ | +1.823 |
DRAG | +1.619 |
backdrop | +1.514 |
Hour | +1.506 |
GEAR | +1.492 |
Neg logit contributions | |
ochond | -1.731 |
Filip | -1.627 |
amily | -1.469 |
estine | -1.462 |
urers | -1.421 |
Token | � |
Token ID | 447 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
═ | +0.521 |
DRAG | +0.466 |
Hour | +0.438 |
backdrop | +0.436 |
GEAR | +0.433 |
Neg logit contributions | |
ochond | -0.393 |
Filip | -0.370 |
amily | -0.325 |
estine | -0.323 |
urers | -0.314 |
Token | � |
Token ID | 251 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
═ | +0.400 |
DRAG | +0.328 |
Hour | +0.292 |
backdrop | +0.287 |
GEAR | +0.284 |
Neg logit contributions | |
ochond | -0.806 |
Filip | -0.775 |
amily | -0.713 |
estine | -0.712 |
urers | -0.702 |
Token | He |
Token ID | 679 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
═ | +0.432 |
DRAG | +0.386 |
Hour | +0.362 |
backdrop | +0.360 |
GEAR | +0.358 |
Neg logit contributions | |
ochond | -0.340 |
Filip | -0.321 |
amily | -0.282 |
estine | -0.281 |
urers | -0.274 |
Token | also |
Token ID | 635 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
═ | +0.470 |
DRAG | +0.413 |
Hour | +0.382 |
backdrop | +0.381 |
GEAR | +0.377 |
Neg logit contributions | |
ochond | -0.493 |
Filip | -0.471 |
amily | -0.422 |
estine | -0.420 |
urers | -0.410 |
Token | things |
Token ID | 1243 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
═ | +0.154 |
DRAG | +0.136 |
Hour | +0.126 |
backdrop | +0.126 |
GEAR | +0.124 |
Neg logit contributions | |
ochond | -0.149 |
Filip | -0.142 |
amily | -0.127 |
estine | -0.126 |
urers | -0.123 |
Token | fresh |
Token ID | 4713 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
═ | +0.050 |
DRAG | +0.044 |
Hour | +0.041 |
GEAR | +0.040 |
backdrop | +0.040 |
Neg logit contributions | |
ochond | -0.053 |
Filip | -0.052 |
amily | -0.046 |
estine | -0.046 |
urers | -0.045 |
Token | with |
Token ID | 351 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
═ | +0.068 |
DRAG | +0.060 |
Hour | +0.056 |
backdrop | +0.056 |
GEAR | +0.055 |
Neg logit contributions | |
ochond | -0.064 |
Filip | -0.061 |
amily | -0.054 |
estine | -0.054 |
urers | -0.053 |
Token | The |
Token ID | 383 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
ochond | +0.041 |
Filip | +0.039 |
amily | +0.035 |
estine | +0.035 |
urers | +0.034 |
Neg logit contributions | |
═ | -0.041 |
DRAG | -0.036 |
Hour | -0.034 |
backdrop | -0.034 |
GEAR | -0.033 |
Token | Walking |
Token ID | 21276 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
═ | +0.156 |
DRAG | +0.121 |
Hour | +0.101 |
backdrop | +0.100 |
GEAR | +0.098 |
Neg logit contributions | |
ochond | -0.444 |
Filip | -0.431 |
amily | -0.400 |
estine | -0.399 |
urers | -0.393 |
Token | Dead |
Token ID | 5542 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
═ | +0.979 |
DRAG | +0.791 |
backdrop | +0.686 |
GEAR | +0.679 |
Hour | +0.666 |
Neg logit contributions | |
ochond | -1.895 |
Filip | -1.851 |
amily | -1.685 |
estine | -1.682 |
urers | -1.647 |
Token | in |
Token ID | 287 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
═ | +1.785 |
DRAG | +1.573 |
Hour | +1.469 |
backdrop | +1.467 |
GEAR | +1.445 |
Neg logit contributions | |
ochond | -1.769 |
Filip | -1.681 |
amily | -1.503 |
estine | -1.499 |
urers | -1.463 |
Token | each |
Token ID | 1123 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
═ | +0.293 |
DRAG | +0.257 |
Hour | +0.239 |
backdrop | +0.238 |
GEAR | +0.235 |
Neg logit contributions | |
ochond | -0.304 |
Filip | -0.290 |
amily | -0.260 |
estine | -0.259 |
urers | -0.253 |
Token | incarnation |
Token ID | 29185 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
═ | +0.072 |
DRAG | +0.061 |
Hour | +0.055 |
GEAR | +0.055 |
backdrop | +0.055 |
Neg logit contributions | |
ochond | -0.099 |
Filip | -0.095 |
amily | -0.086 |
estine | -0.086 |
urers | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
═ | +0.276 |
DRAG | +0.243 |
Hour | +0.226 |
backdrop | +0.226 |
GEAR | +0.223 |
Neg logit contributions | |
ochond | -0.273 |
Filip | -0.260 |
amily | -0.233 |
estine | -0.231 |
urers | -0.226 |
Token | including |
Token ID | 1390 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
═ | +0.134 |
DRAG | +0.118 |
Hour | +0.109 |
backdrop | +0.109 |
GEAR | +0.108 |
Neg logit contributions | |
ochond | -0.139 |
Filip | -0.134 |
amily | -0.119 |
estine | -0.119 |
urers | -0.116 |
Token | but |
Token ID | 475 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
═ | +0.144 |
DRAG | +0.127 |
Hour | +0.118 |
backdrop | +0.117 |
GEAR | +0.116 |
Neg logit contributions | |
ochond | -0.145 |
Filip | -0.138 |
amily | -0.124 |
estine | -0.123 |
urers | -0.120 |
Token | occasionally |
Token ID | 10491 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
═ | +0.310 |
DRAG | +0.275 |
Hour | +0.256 |
backdrop | +0.255 |
GEAR | +0.253 |
Neg logit contributions | |
ochond | -0.277 |
Filip | -0.264 |
amily | -0.234 |
estine | -0.233 |
urers | -0.227 |
Token | , |
Token ID | 11 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
═ | +0.441 |
DRAG | +0.392 |
Hour | +0.366 |
backdrop | +0.364 |
GEAR | +0.361 |
Neg logit contributions | |
ochond | -0.382 |
Filip | -0.363 |
amily | -0.321 |
estine | -0.320 |
urers | -0.312 |
Token | Dungeons |
Token ID | 25461 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
═ | +0.309 |
DRAG | +0.273 |
Hour | +0.254 |
backdrop | +0.254 |
GEAR | +0.252 |
Neg logit contributions | |
ochond | -0.279 |
Filip | -0.267 |
amily | -0.237 |
estine | -0.235 |
urers | -0.230 |
Token | and |
Token ID | 290 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
═ | +0.033 |
DRAG | +0.029 |
Hour | +0.027 |
backdrop | +0.027 |
GEAR | +0.026 |
Neg logit contributions | |
ochond | -0.039 |
Filip | -0.038 |
amily | -0.034 |
estine | -0.034 |
urers | -0.033 |
Token | Dragons |
Token ID | 19075 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
═ | +0.169 |
DRAG | +0.125 |
backdrop | +0.109 |
Hour | +0.107 |
GEAR | +0.107 |
Neg logit contributions | |
ochond | -0.457 |
Filip | -0.445 |
estine | -0.413 |
amily | -0.410 |
urers | -0.406 |
Token | players |
Token ID | 1938 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
═ | +1.768 |
DRAG | +1.570 |
Hour | +1.460 |
backdrop | +1.453 |
GEAR | +1.437 |
Neg logit contributions | |
ochond | -1.762 |
Filip | -1.675 |
estine | -1.496 |
amily | -1.494 |
urers | -1.454 |
Token | do |
Token ID | 466 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
ochond | +0.117 |
Filip | +0.112 |
amily | +0.100 |
estine | +0.100 |
urers | +0.097 |
Neg logit contributions | |
═ | -0.113 |
DRAG | -0.099 |
Hour | -0.091 |
backdrop | -0.091 |
GEAR | -0.090 |
Token | not |
Token ID | 407 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
═ | +0.244 |
DRAG | +0.215 |
Hour | +0.199 |
backdrop | +0.198 |
GEAR | +0.196 |
Neg logit contributions | |
ochond | -0.258 |
Filip | -0.246 |
amily | -0.221 |
estine | -0.220 |
urers | -0.215 |
Token | take |
Token ID | 1011 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
═ | +0.059 |
DRAG | +0.051 |
Hour | +0.047 |
backdrop | +0.047 |
GEAR | +0.047 |
Neg logit contributions | |
ochond | -0.062 |
Filip | -0.060 |
estine | -0.053 |
amily | -0.053 |
urers | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ochond | +0.058 |
Filip | +0.055 |
amily | +0.049 |
estine | +0.049 |
urers | +0.048 |
Neg logit contributions | |
═ | -0.061 |
DRAG | -0.054 |
Hour | -0.050 |
backdrop | -0.050 |
GEAR | -0.050 |
Token | series |
Token ID | 2168 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
═ | +0.045 |
DRAG | +0.038 |
backdrop | +0.034 |
GEAR | +0.034 |
Hour | +0.033 |
Neg logit contributions | |
ochond | -0.065 |
Filip | -0.063 |
estine | -0.057 |
amily | -0.057 |
urers | -0.056 |
Token | Natural |
Token ID | 12068 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
═ | +0.485 |
DRAG | +0.419 |
Hour | +0.384 |
backdrop | +0.383 |
GEAR | +0.379 |
Neg logit contributions | |
ochond | -0.598 |
Filip | -0.574 |
amily | -0.518 |
estine | -0.517 |
urers | -0.505 |
Token | World |
Token ID | 2159 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
═ | +0.513 |
DRAG | +0.447 |
Hour | +0.406 |
backdrop | +0.405 |
GEAR | +0.403 |
Neg logit contributions | |
ochond | -0.572 |
Filip | -0.551 |
estine | -0.493 |
amily | -0.491 |
urers | -0.482 |
Token | episode |
Token ID | 4471 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
═ | +0.870 |
DRAG | +0.773 |
Hour | +0.723 |
backdrop | +0.719 |
GEAR | +0.713 |
Neg logit contributions | |
ochond | -0.769 |
Filip | -0.730 |
amily | -0.648 |
estine | -0.644 |
urers | -0.629 |
Token | " |
Token ID | 366 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
═ | +1.054 |
DRAG | +0.926 |
Hour | +0.857 |
backdrop | +0.853 |
GEAR | +0.845 |
Neg logit contributions | |
ochond | -1.124 |
Filip | -1.073 |
amily | -0.963 |
estine | -0.959 |
urers | -0.937 |
Token | Snow |
Token ID | 28974 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
═ | +0.308 |
DRAG | +0.278 |
Hour | +0.263 |
backdrop | +0.261 |
GEAR | +0.259 |
Neg logit contributions | |
ochond | -0.197 |
Filip | -0.184 |
amily | -0.159 |
estine | -0.158 |
urers | -0.153 |
Token | Leopard |
Token ID | 49072 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
═ | +1.499 |
DRAG | +1.300 |
Hour | +1.197 |
backdrop | +1.186 |
GEAR | +1.172 |
Neg logit contributions | |
ochond | -1.991 |
Filip | -1.903 |
amily | -1.736 |
estine | -1.724 |
urers | -1.691 |
Token | – |
Token ID | 784 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
═ | +1.649 |
DRAG | +1.449 |
Hour | +1.344 |
backdrop | +1.336 |
GEAR | +1.323 |
Neg logit contributions | |
ochond | -1.780 |
Filip | -1.696 |
amily | -1.526 |
estine | -1.519 |
urers | -1.485 |
Token | Beyond |
Token ID | 12197 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
═ | +0.030 |
DRAG | +0.026 |
Hour | +0.024 |
backdrop | +0.024 |
GEAR | +0.023 |
Neg logit contributions | |
ochond | -0.035 |
Filip | -0.034 |
amily | -0.030 |
estine | -0.030 |
urers | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
═ | +0.556 |
DRAG | +0.488 |
Hour | +0.452 |
backdrop | +0.450 |
GEAR | +0.446 |
Neg logit contributions | |
ochond | -0.591 |
Filip | -0.564 |
amily | -0.506 |
estine | -0.504 |
urers | -0.492 |
Token | Myth |
Token ID | 18900 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
═ | +0.257 |
DRAG | +0.219 |
GEAR | +0.196 |
Hour | +0.195 |
backdrop | +0.195 |
Neg logit contributions | |
ochond | -0.366 |
Filip | -0.354 |
estine | -0.320 |
amily | -0.320 |
urers | -0.313 |
Token | filming |
Token ID | 17691 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
ochond | +0.522 |
Filip | +0.502 |
amily | +0.445 |
estine | +0.443 |
urers | +0.432 |
Neg logit contributions | |
═ | -0.542 |
DRAG | -0.477 |
Hour | -0.442 |
backdrop | -0.439 |
GEAR | -0.436 |
Token | for |
Token ID | 329 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
═ | +0.698 |
DRAG | +0.608 |
Hour | +0.562 |
backdrop | +0.556 |
GEAR | +0.554 |
Neg logit contributions | |
ochond | -0.733 |
Filip | -0.704 |
amily | -0.626 |
estine | -0.625 |
urers | -0.610 |
Token | Teen |
Token ID | 21432 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
═ | +0.094 |
DRAG | +0.082 |
backdrop | +0.076 |
Hour | +0.076 |
GEAR | +0.075 |
Neg logit contributions | |
ochond | -0.093 |
Filip | -0.089 |
amily | -0.079 |
estine | -0.079 |
urers | -0.077 |
Token | age |
Token ID | 496 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
═ | +0.585 |
DRAG | +0.517 |
backdrop | +0.477 |
Hour | +0.473 |
GEAR | +0.471 |
Neg logit contributions | |
ochond | -0.566 |
Filip | -0.544 |
amily | -0.483 |
estine | -0.480 |
urers | -0.470 |
Token | Mutant |
Token ID | 35319 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
═ | +0.457 |
DRAG | +0.385 |
backdrop | +0.344 |
Hour | +0.343 |
GEAR | +0.338 |
Neg logit contributions | |
ochond | -0.747 |
Filip | -0.721 |
amily | -0.658 |
estine | -0.656 |
urers | -0.643 |
Token | Ninja |
Token ID | 14152 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
═ | +1.082 |
DRAG | +0.862 |
Hour | +0.742 |
backdrop | +0.738 |
GEAR | +0.724 |
Neg logit contributions | |
ochond | -2.602 |
Filip | -2.517 |
amily | -2.328 |
estine | -2.324 |
urers | -2.285 |
Token | Turtles |
Token ID | 44356 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
═ | +1.493 |
DRAG | +1.294 |
Hour | +1.192 |
backdrop | +1.182 |
GEAR | +1.172 |
Neg logit contributions | |
ochond | -2.003 |
Filip | -1.901 |
amily | -1.748 |
estine | -1.737 |
urers | -1.699 |
Token | II |
Token ID | 2873 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
═ | +0.391 |
DRAG | +0.344 |
Hour | +0.317 |
backdrop | +0.317 |
GEAR | +0.314 |
Neg logit contributions | |
ochond | -0.379 |
Filip | -0.363 |
amily | -0.322 |
estine | -0.321 |
urers | -0.312 |
Token | : |
Token ID | 25 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
═ | +0.295 |
DRAG | +0.257 |
Hour | +0.236 |
backdrop | +0.236 |
GEAR | +0.234 |
Neg logit contributions | |
ochond | -0.329 |
Filip | -0.316 |
amily | -0.283 |
estine | -0.282 |
urers | -0.275 |
Token | Half |
Token ID | 13139 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
═ | +0.088 |
DRAG | +0.077 |
Hour | +0.072 |
backdrop | +0.071 |
GEAR | +0.070 |
Neg logit contributions | |
ochond | -0.103 |
Filip | -0.098 |
amily | -0.089 |
estine | -0.088 |
urers | -0.086 |
Token | Shell |
Token ID | 17537 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
═ | +0.819 |
DRAG | +0.726 |
Hour | +0.685 |
backdrop | +0.676 |
GEAR | +0.672 |
Neg logit contributions | |
ochond | -0.737 |
Filip | -0.696 |
amily | -0.621 |
estine | -0.618 |
urers | -0.602 |
Token | , |
Token ID | 11 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
═ | +0.458 |
DRAG | +0.398 |
Hour | +0.371 |
backdrop | +0.367 |
GEAR | +0.366 |
Neg logit contributions | |
ochond | -0.541 |
Filip | -0.514 |
amily | -0.464 |
estine | -0.462 |
urers | -0.453 |
Token | and |
Token ID | 290 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
ochond | +0.028 |
Filip | +0.027 |
amily | +0.024 |
estine | +0.024 |
urers | +0.023 |
Neg logit contributions | |
═ | -0.023 |
DRAG | -0.020 |
backdrop | -0.018 |
Hour | -0.018 |
GEAR | -0.018 |
Token | Ethics |
Token ID | 25092 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
═ | +0.063 |
DRAG | +0.053 |
backdrop | +0.048 |
Hour | +0.048 |
GEAR | +0.047 |
Neg logit contributions | |
ochond | -0.098 |
Filip | -0.096 |
amily | -0.087 |
estine | -0.087 |
urers | -0.085 |
Token | at |
Token ID | 379 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
═ | +0.615 |
DRAG | +0.539 |
Hour | +0.502 |
backdrop | +0.500 |
GEAR | +0.492 |
Neg logit contributions | |
ochond | -0.663 |
Filip | -0.630 |
amily | -0.566 |
estine | -0.565 |
urers | -0.552 |
Token | Silicon |
Token ID | 18210 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
═ | +0.168 |
DRAG | +0.150 |
Hour | +0.139 |
backdrop | +0.139 |
GEAR | +0.138 |
Neg logit contributions | |
ochond | -0.150 |
Filip | -0.143 |
amily | -0.127 |
estine | -0.126 |
urers | -0.123 |
Token | Valley |
Token ID | 6916 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
═ | +0.100 |
DRAG | +0.076 |
Hour | +0.064 |
backdrop | +0.063 |
GEAR | +0.062 |
Neg logit contributions | |
ochond | -0.297 |
Filip | -0.288 |
amily | -0.267 |
estine | -0.267 |
urers | -0.263 |
Token | � |
Token ID | 447 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
═ | +1.528 |
DRAG | +1.319 |
Hour | +1.227 |
GEAR | +1.206 |
backdrop | +1.205 |
Neg logit contributions | |
ochond | -1.955 |
Filip | -1.853 |
amily | -1.681 |
estine | -1.679 |
urers | -1.643 |
Token | � |
Token ID | 247 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
═ | +0.193 |
DRAG | +0.160 |
Hour | +0.144 |
backdrop | +0.143 |
GEAR | +0.141 |
Neg logit contributions | |
ochond | -0.352 |
Filip | -0.339 |
amily | -0.310 |
estine | -0.310 |
urers | -0.305 |
Token | s |
Token ID | 82 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
═ | +0.102 |
DRAG | +0.090 |
Hour | +0.084 |
backdrop | +0.084 |
GEAR | +0.083 |
Neg logit contributions | |
ochond | -0.095 |
Filip | -0.091 |
amily | -0.080 |
estine | -0.080 |
urers | -0.078 |
Token | Sing |
Token ID | 5573 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
═ | +0.108 |
DRAG | +0.094 |
Hour | +0.087 |
backdrop | +0.087 |
GEAR | +0.086 |
Neg logit contributions | |
ochond | -0.126 |
Filip | -0.121 |
amily | -0.109 |
estine | -0.109 |
urers | -0.106 |
Token | ularity |
Token ID | 33737 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
═ | +1.426 |
DRAG | +1.259 |
Hour | +1.173 |
backdrop | +1.165 |
GEAR | +1.157 |
Neg logit contributions | |
ochond | -1.382 |
Filip | -1.319 |
amily | -1.175 |
estine | -1.170 |
urers | -1.139 |
Token | week |
Token ID | 1285 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ochond | +0.423 |
Filip | +0.407 |
amily | +0.375 |
estine | +0.374 |
urers | +0.368 |
Neg logit contributions | |
═ | -0.216 |
DRAG | -0.178 |
Hour | -0.158 |
backdrop | -0.158 |
GEAR | -0.154 |
Token | – |
Token ID | 784 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
ochond | +0.169 |
Filip | +0.161 |
amily | +0.144 |
estine | +0.143 |
urers | +0.141 |
Neg logit contributions | |
═ | -0.175 |
DRAG | -0.154 |
Hour | -0.144 |
backdrop | -0.143 |
GEAR | -0.141 |
Token | those |
Token ID | 883 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ochond | +0.375 |
Filip | +0.358 |
amily | +0.322 |
estine | +0.321 |
urers | +0.314 |
Neg logit contributions | |
═ | -0.335 |
DRAG | -0.293 |
Hour | -0.270 |
backdrop | -0.269 |
GEAR | -0.267 |
Token | who |
Token ID | 508 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
ochond | +0.205 |
Filip | +0.190 |
amily | +0.164 |
estine | +0.163 |
urers | +0.156 |
Neg logit contributions | |
═ | -0.347 |
DRAG | -0.315 |
Hour | -0.298 |
backdrop | -0.298 |
GEAR | -0.294 |
Token | r |
Token ID | 374 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
ochond | +0.598 |
Filip | +0.573 |
amily | +0.512 |
estine | +0.511 |
urers | +0.499 |
Neg logit contributions | |
═ | -0.556 |
DRAG | -0.486 |
Hour | -0.449 |
backdrop | -0.447 |
GEAR | -0.443 |
Token | auc |
Token ID | 14272 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
ochond | +0.631 |
Filip | +0.597 |
amily | +0.520 |
estine | +0.518 |
urers | +0.503 |
Neg logit contributions | |
═ | -0.861 |
DRAG | -0.773 |
Hour | -0.725 |
backdrop | -0.723 |
GEAR | -0.717 |
Token | ously |
Token ID | 3481 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ochond | +1.361 |
Filip | +1.261 |
estine | +1.040 |
amily | +1.039 |
urers | +0.991 |
Neg logit contributions | |
═ | -2.931 |
DRAG | -2.676 |
Hour | -2.536 |
backdrop | -2.528 |
GEAR | -2.513 |
Token | celebrated |
Token ID | 13943 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ochond | +1.245 |
Filip | +1.193 |
amily | +1.064 |
estine | +1.063 |
urers | +1.037 |
Neg logit contributions | |
═ | -1.203 |
DRAG | -1.055 |
Hour | -0.975 |
backdrop | -0.967 |
GEAR | -0.964 |
Token | the |
Token ID | 262 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
ochond | +0.469 |
Filip | +0.442 |
amily | +0.396 |
estine | +0.393 |
urers | +0.384 |
Neg logit contributions | |
═ | -0.505 |
DRAG | -0.448 |
Hour | -0.420 |
backdrop | -0.418 |
GEAR | -0.412 |
Token | dism |
Token ID | 18099 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
ochond | +0.391 |
Filip | +0.375 |
amily | +0.336 |
estine | +0.335 |
urers | +0.327 |
Neg logit contributions | |
═ | -0.354 |
DRAG | -0.310 |
Hour | -0.285 |
backdrop | -0.284 |
GEAR | -0.282 |
Token | ember |
Token ID | 1491 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ochond | +0.602 |
Filip | +0.576 |
amily | +0.518 |
estine | +0.516 |
urers | +0.504 |
Neg logit contributions | |
═ | -0.536 |
DRAG | -0.469 |
Hour | -0.433 |
backdrop | -0.431 |
GEAR | -0.426 |
Token | Av |
Token ID | 5184 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ochond | +0.134 |
Filip | +0.128 |
amily | +0.114 |
estine | +0.114 |
urers | +0.111 |
Neg logit contributions | |
═ | -0.132 |
DRAG | -0.116 |
Hour | -0.108 |
backdrop | -0.108 |
GEAR | -0.107 |
Token | ond |
Token ID | 623 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
═ | +0.233 |
DRAG | +0.209 |
Hour | +0.197 |
backdrop | +0.195 |
GEAR | +0.194 |
Neg logit contributions | |
ochond | -0.178 |
Filip | -0.169 |
amily | -0.147 |
estine | -0.147 |
urers | -0.143 |
Token | ale |
Token ID | 1000 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
ochond | +0.191 |
Filip | +0.182 |
amily | +0.162 |
estine | +0.161 |
urers | +0.157 |
Neg logit contributions | |
═ | -0.206 |
DRAG | -0.183 |
Hour | -0.170 |
backdrop | -0.169 |
GEAR | -0.168 |
Token | man |
Token ID | 582 |
Feature activation | +2.72e-03 |
Pos logit contributions | |
═ | +0.228 |
DRAG | +0.202 |
Hour | +0.187 |
backdrop | +0.186 |
GEAR | +0.184 |
Neg logit contributions | |
ochond | -0.233 |
Filip | -0.221 |
amily | -0.198 |
estine | -0.198 |
urers | -0.193 |
Token | returned |
Token ID | 4504 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
═ | +0.003 |
DRAG | +0.002 |
Hour | +0.002 |
backdrop | +0.002 |
GEAR | +0.002 |
Neg logit contributions | |
ochond | -0.002 |
Filip | -0.002 |
amily | -0.002 |
estine | -0.002 |
urers | -0.002 |
Token | home |
Token ID | 1363 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ochond | +0.911 |
Filip | +0.860 |
amily | +0.767 |
estine | +0.766 |
urers | +0.743 |
Neg logit contributions | |
═ | -1.018 |
DRAG | -0.902 |
Hour | -0.848 |
backdrop | -0.844 |
GEAR | -0.837 |
Token | last |
Token ID | 938 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ochond | +1.970 |
Filip | +1.876 |
amily | +1.691 |
estine | +1.685 |
urers | +1.646 |
Neg logit contributions | |
═ | -1.773 |
DRAG | -1.551 |
Hour | -1.436 |
backdrop | -1.430 |
GEAR | -1.414 |
Token | week |
Token ID | 1285 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ochond | +0.691 |
Filip | +0.667 |
amily | +0.610 |
estine | +0.609 |
urers | +0.598 |
Neg logit contributions | |
═ | -0.401 |
DRAG | -0.336 |
Hour | -0.300 |
backdrop | -0.299 |
GEAR | -0.295 |
Token | to |
Token ID | 284 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
ochond | +0.221 |
Filip | +0.207 |
amily | +0.186 |
estine | +0.186 |
urers | +0.181 |
Neg logit contributions | |
═ | -0.229 |
DRAG | -0.202 |
Hour | -0.190 |
backdrop | -0.189 |
GEAR | -0.186 |
Token | discover |
Token ID | 7073 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
ochond | +0.431 |
Filip | +0.410 |
amily | +0.365 |
estine | +0.364 |
urers | +0.355 |
Neg logit contributions | |
═ | -0.459 |
DRAG | -0.408 |
Hour | -0.379 |
backdrop | -0.378 |
GEAR | -0.375 |
Token | his |
Token ID | 465 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ochond | +0.421 |
Filip | +0.399 |
amily | +0.359 |
estine | +0.358 |
urers | +0.348 |
Neg logit contributions | |
═ | -0.409 |
DRAG | -0.360 |
Hour | -0.335 |
backdrop | -0.334 |
GEAR | -0.331 |
Token | fish |
Token ID | 5916 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
ochond | +0.254 |
Filip | +0.239 |
amily | +0.213 |
estine | +0.212 |
urers | +0.206 |
Neg logit contributions | |
═ | -0.297 |
DRAG | -0.265 |
Hour | -0.248 |
backdrop | -0.247 |
GEAR | -0.245 |
Token | bowl |
Token ID | 9396 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ochond | +0.803 |
Filip | +0.760 |
amily | +0.668 |
estine | +0.665 |
urers | +0.646 |
Neg logit contributions | |
═ | -1.032 |
DRAG | -0.922 |
Hour | -0.864 |
backdrop | -0.862 |
GEAR | -0.855 |
Token | and |
Token ID | 290 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ochond | +1.158 |
Filip | +1.103 |
amily | +0.986 |
estine | +0.982 |
urers | +0.958 |
Neg logit contributions | |
═ | -1.171 |
DRAG | -1.033 |
Hour | -0.958 |
backdrop | -0.956 |
GEAR | -0.947 |
Token | the |
Token ID | 262 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ochond | +0.326 |
Filip | +0.310 |
amily | +0.277 |
estine | +0.275 |
urers | +0.269 |
Neg logit contributions | |
═ | -0.339 |
DRAG | -0.300 |
Hour | -0.279 |
backdrop | -0.278 |
GEAR | -0.275 |
Token | f |
Token ID | 277 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ochond | +0.300 |
Filip | +0.286 |
amily | +0.254 |
estine | +0.252 |
urers | +0.246 |
Neg logit contributions | |
═ | -0.335 |
DRAG | -0.297 |
Hour | -0.277 |
backdrop | -0.276 |
GEAR | -0.274 |
Token | auc |
Token ID | 14272 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ochond | +0.079 |
Filip | +0.069 |
estine | +0.045 |
amily | +0.045 |
fooled | +0.042 |
Neg logit contributions | |
═ | -0.368 |
DRAG | -0.339 |
Hour | -0.328 |
backdrop | -0.327 |
GEAR | -0.323 |
Token | et |
Token ID | 316 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ochond | +1.469 |
Filip | +1.377 |
amily | +1.197 |
estine | +1.193 |
urers | +1.152 |
Neg logit contributions | |
═ | -2.247 |
DRAG | -2.039 |
backdrop | -1.896 |
Hour | -1.895 |
GEAR | -1.891 |
Token | are |
Token ID | 389 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
ochond | +1.085 |
Filip | +1.036 |
amily | +0.923 |
estine | +0.920 |
urers | +0.898 |
Neg logit contributions | |
═ | -1.098 |
DRAG | -0.969 |
Hour | -0.898 |
backdrop | -0.895 |
GEAR | -0.888 |
Token | separate |
Token ID | 4553 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
ochond | +0.070 |
Filip | +0.066 |
amily | +0.059 |
estine | +0.059 |
urers | +0.057 |
Neg logit contributions | |
═ | -0.072 |
DRAG | -0.064 |
Hour | -0.060 |
backdrop | -0.059 |
GEAR | -0.059 |
Token | : |
Token ID | 25 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
ochond | +0.061 |
Filip | +0.058 |
amily | +0.052 |
estine | +0.051 |
urers | +0.050 |
Neg logit contributions | |
═ | -0.061 |
DRAG | -0.054 |
Hour | -0.050 |
backdrop | -0.050 |
GEAR | -0.050 |
Token | you |
Token ID | 345 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
ochond | +0.263 |
Filip | +0.248 |
amily | +0.221 |
estine | +0.221 |
urers | +0.215 |
Neg logit contributions | |
═ | -0.298 |
DRAG | -0.266 |
Hour | -0.249 |
backdrop | -0.247 |
GEAR | -0.245 |
Token | - |
Token ID | 12 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
ochond | +0.781 |
Filip | +0.743 |
amily | +0.660 |
estine | +0.658 |
urers | +0.642 |
Neg logit contributions | |
═ | -0.849 |
DRAG | -0.752 |
Hour | -0.700 |
backdrop | -0.699 |
GEAR | -0.692 |
Token | tra |
Token ID | 9535 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ochond | +0.684 |
Filip | +0.650 |
amily | +0.576 |
estine | +0.574 |
urers | +0.559 |
Neg logit contributions | |
═ | -0.779 |
DRAG | -0.692 |
Hour | -0.646 |
backdrop | -0.644 |
GEAR | -0.638 |
Token | umat |
Token ID | 27798 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
═ | +0.631 |
DRAG | +0.563 |
Hour | +0.531 |
backdrop | +0.528 |
GEAR | +0.520 |
Neg logit contributions | |
ochond | -0.490 |
Filip | -0.461 |
estine | -0.404 |
amily | -0.403 |
urers | -0.390 |
Token | izing |
Token ID | 2890 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
ochond | +0.261 |
Filip | +0.248 |
amily | +0.218 |
estine | +0.217 |
urers | +0.210 |
Neg logit contributions | |
═ | -0.337 |
DRAG | -0.300 |
Hour | -0.284 |
backdrop | -0.283 |
GEAR | -0.279 |
Token | f |
Token ID | 277 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
═ | +0.221 |
DRAG | +0.194 |
Hour | +0.179 |
backdrop | +0.179 |
GEAR | +0.177 |
Neg logit contributions | |
ochond | -0.238 |
Filip | -0.227 |
amily | -0.204 |
estine | -0.203 |
urers | -0.198 |
Token | auc |
Token ID | 14272 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ochond | +0.026 |
Filip | +0.024 |
amily | +0.017 |
estine | +0.017 |
fooled | +0.016 |
Neg logit contributions | |
═ | -0.094 |
DRAG | -0.087 |
Hour | -0.083 |
backdrop | -0.083 |
GEAR | -0.082 |
Token | et |
Token ID | 316 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ochond | +1.446 |
Filip | +1.357 |
amily | +1.178 |
estine | +1.176 |
urers | +1.128 |
Neg logit contributions | |
═ | -2.243 |
DRAG | -2.034 |
backdrop | -1.887 |
GEAR | -1.887 |
Hour | -1.885 |
Token | . |
Token ID | 13 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ochond | +1.003 |
Filip | +0.957 |
amily | +0.853 |
estine | +0.850 |
urers | +0.829 |
Neg logit contributions | |
═ | -1.035 |
DRAG | -0.914 |
Hour | -0.848 |
backdrop | -0.845 |
GEAR | -0.838 |
Token |
|
Token ID | 198 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
ochond | +0.261 |
Filip | +0.245 |
amily | +0.212 |
estine | +0.211 |
urers | +0.204 |
Neg logit contributions | |
═ | -0.405 |
DRAG | -0.365 |
Hour | -0.345 |
backdrop | -0.343 |
GEAR | -0.340 |
Token |
|
Token ID | 198 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
ochond | +0.302 |
Filip | +0.283 |
amily | +0.237 |
estine | +0.237 |
urers | +0.228 |
Neg logit contributions | |
═ | -0.556 |
DRAG | -0.506 |
Hour | -0.477 |
backdrop | -0.477 |
GEAR | -0.474 |
Token | In |
Token ID | 818 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
ochond | +0.320 |
Filip | +0.301 |
amily | +0.260 |
estine | +0.259 |
urers | +0.252 |
Neg logit contributions | |
═ | -0.499 |
DRAG | -0.448 |
Hour | -0.423 |
backdrop | -0.422 |
GEAR | -0.418 |
Token | with |
Token ID | 351 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
ochond | +0.575 |
Filip | +0.551 |
amily | +0.493 |
estine | +0.492 |
urers | +0.480 |
Neg logit contributions | |
═ | -0.532 |
DRAG | -0.467 |
Hour | -0.429 |
backdrop | -0.428 |
GEAR | -0.425 |
Token | a |
Token ID | 257 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ochond | +0.487 |
Filip | +0.465 |
amily | +0.415 |
estine | +0.413 |
urers | +0.403 |
Neg logit contributions | |
═ | -0.495 |
DRAG | -0.436 |
Hour | -0.405 |
backdrop | -0.404 |
GEAR | -0.400 |
Token | video |
Token ID | 2008 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
ochond | +0.119 |
Filip | +0.115 |
amily | +0.104 |
estine | +0.104 |
urers | +0.102 |
Neg logit contributions | |
═ | -0.089 |
DRAG | -0.077 |
Hour | -0.070 |
backdrop | -0.070 |
GEAR | -0.069 |
Token | shot |
Token ID | 2823 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
═ | +0.415 |
DRAG | +0.360 |
Hour | +0.331 |
backdrop | +0.330 |
GEAR | +0.326 |
Neg logit contributions | |
ochond | -0.517 |
Filip | -0.495 |
amily | -0.448 |
estine | -0.447 |
urers | -0.437 |
Token | by |
Token ID | 416 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
ochond | +0.237 |
Filip | +0.226 |
amily | +0.202 |
estine | +0.201 |
urers | +0.196 |
Neg logit contributions | |
═ | -0.235 |
DRAG | -0.207 |
Hour | -0.191 |
backdrop | -0.190 |
GEAR | -0.189 |
Token | Lan |
Token ID | 14730 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ochond | +0.057 |
Filip | +0.054 |
amily | +0.048 |
estine | +0.048 |
urers | +0.047 |
Neg logit contributions | |
═ | -0.057 |
DRAG | -0.051 |
Hour | -0.047 |
backdrop | -0.047 |
GEAR | -0.046 |
Token | ell |
Token ID | 695 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ochond | +1.718 |
Filip | +1.635 |
amily | +1.449 |
estine | +1.447 |
urers | +1.404 |
Neg logit contributions | |
═ | -1.948 |
DRAG | -1.728 |
backdrop | -1.606 |
Hour | -1.602 |
GEAR | -1.592 |
Token | Stewart |
Token ID | 13671 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
ochond | +0.145 |
Filip | +0.139 |
amily | +0.123 |
estine | +0.123 |
urers | +0.120 |
Neg logit contributions | |
═ | -0.150 |
DRAG | -0.133 |
Hour | -0.123 |
backdrop | -0.123 |
GEAR | -0.122 |
Token | Mir |
Token ID | 7381 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
═ | +0.329 |
DRAG | +0.292 |
Hour | +0.270 |
backdrop | +0.270 |
GEAR | +0.268 |
Neg logit contributions | |
ochond | -0.303 |
Filip | -0.290 |
amily | -0.257 |
estine | -0.256 |
urers | -0.249 |
Token | abe |
Token ID | 11231 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
ochond | +0.642 |
Filip | +0.611 |
amily | +0.540 |
estine | +0.540 |
urers | +0.524 |
Neg logit contributions | |
═ | -0.733 |
DRAG | -0.652 |
Hour | -0.605 |
backdrop | -0.605 |
GEAR | -0.600 |
Token | au |
Token ID | 559 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
═ | +0.643 |
DRAG | +0.582 |
Hour | +0.551 |
backdrop | +0.546 |
GEAR | +0.539 |
Neg logit contributions | |
ochond | -0.428 |
Filip | -0.403 |
amily | -0.348 |
estine | -0.347 |
urers | -0.337 |
Token | - |
Token ID | 12 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
ochond | +0.081 |
Filip | +0.078 |
amily | +0.068 |
estine | +0.068 |
urers | +0.065 |
Neg logit contributions | |
═ | -0.103 |
DRAG | -0.093 |
Hour | -0.085 |
backdrop | -0.085 |
GEAR | -0.085 |
Token | the |
Token ID | 1169 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
ochond | +0.417 |
Filip | +0.398 |
amily | +0.356 |
estine | +0.355 |
urers | +0.347 |
Neg logit contributions | |
═ | -0.402 |
DRAG | -0.354 |
Hour | -0.327 |
backdrop | -0.326 |
GEAR | -0.323 |
Token | - |
Token ID | 12 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ochond | +0.023 |
Filip | +0.022 |
amily | +0.019 |
estine | +0.019 |
urers | +0.019 |
Neg logit contributions | |
═ | -0.029 |
DRAG | -0.026 |
Hour | -0.024 |
backdrop | -0.024 |
GEAR | -0.024 |
Token | box |
Token ID | 3524 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ochond | +0.515 |
Filip | +0.493 |
amily | +0.447 |
estine | +0.445 |
urers | +0.436 |
Neg logit contributions | |
═ | -0.401 |
DRAG | -0.346 |
Hour | -0.317 |
backdrop | -0.316 |
GEAR | -0.313 |
Token | credit |
Token ID | 3884 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
ochond | +0.380 |
Filip | +0.367 |
estine | +0.331 |
amily | +0.330 |
urers | +0.322 |
Neg logit contributions | |
═ | -0.296 |
DRAG | -0.253 |
Hour | -0.230 |
backdrop | -0.229 |
GEAR | -0.227 |
Token | card |
Token ID | 2657 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ochond | +0.677 |
Filip | +0.649 |
estine | +0.578 |
amily | +0.577 |
urers | +0.563 |
Neg logit contributions | |
═ | -0.641 |
DRAG | -0.560 |
Hour | -0.516 |
GEAR | -0.514 |
backdrop | -0.513 |
Token | processing |
Token ID | 7587 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ochond | +1.934 |
Filip | +1.878 |
estine | +1.687 |
amily | +1.670 |
urers | +1.638 |
Neg logit contributions | |
═ | -1.618 |
DRAG | -1.392 |
Hour | -1.269 |
GEAR | -1.259 |
backdrop | -1.259 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
ochond | +0.420 |
Filip | +0.401 |
amily | +0.356 |
estine | +0.355 |
urers | +0.346 |
Neg logit contributions | |
═ | -0.446 |
DRAG | -0.394 |
Hour | -0.366 |
backdrop | -0.365 |
GEAR | -0.362 |
Token | and |
Token ID | 290 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
═ | +0.019 |
DRAG | +0.016 |
Hour | +0.015 |
backdrop | +0.015 |
GEAR | +0.015 |
Neg logit contributions | |
ochond | -0.022 |
Filip | -0.021 |
amily | -0.019 |
estine | -0.019 |
urers | -0.018 |
Token | detailed |
Token ID | 6496 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
ochond | +0.048 |
Filip | +0.046 |
amily | +0.041 |
estine | +0.041 |
urers | +0.040 |
Neg logit contributions | |
═ | -0.041 |
DRAG | -0.035 |
Hour | -0.032 |
backdrop | -0.032 |
GEAR | -0.032 |
Token | reporting |
Token ID | 6447 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
ochond | +0.321 |
Filip | +0.310 |
estine | +0.280 |
amily | +0.279 |
urers | +0.273 |
Neg logit contributions | |
═ | -0.247 |
DRAG | -0.210 |
Hour | -0.190 |
backdrop | -0.190 |
GEAR | -0.188 |
Token | when |
Token ID | 618 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
ochond | +0.070 |
Filip | +0.067 |
amily | +0.061 |
estine | +0.061 |
urers | +0.060 |
Neg logit contributions | |
═ | -0.054 |
DRAG | -0.047 |
Hour | -0.043 |
backdrop | -0.043 |
GEAR | -0.042 |
Token | Warm |
Token ID | 25692 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ochond | +0.039 |
Filip | +0.037 |
amily | +0.034 |
estine | +0.034 |
urers | +0.033 |
Neg logit contributions | |
═ | -0.029 |
DRAG | -0.025 |
Hour | -0.023 |
backdrop | -0.023 |
GEAR | -0.023 |
Token | b |
Token ID | 65 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
═ | +0.253 |
DRAG | +0.220 |
backdrop | +0.199 |
Hour | +0.198 |
GEAR | +0.197 |
Neg logit contributions | |
ochond | -0.327 |
Filip | -0.312 |
amily | -0.284 |
estine | -0.283 |
urers | -0.276 |
Token | ier |
Token ID | 959 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
═ | +0.308 |
DRAG | +0.283 |
Hour | +0.270 |
backdrop | +0.269 |
GEAR | +0.267 |
Neg logit contributions | |
ochond | -0.118 |
Filip | -0.109 |
amily | -0.087 |
estine | -0.086 |
urers | -0.082 |
Token | returned |
Token ID | 4504 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ochond | +0.867 |
Filip | +0.826 |
amily | +0.729 |
estine | +0.729 |
urers | +0.708 |
Neg logit contributions | |
═ | -0.990 |
DRAG | -0.879 |
Hour | -0.817 |
backdrop | -0.815 |
GEAR | -0.809 |
Token | home |
Token ID | 1363 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ochond | +0.856 |
Filip | +0.805 |
amily | +0.712 |
estine | +0.706 |
urers | +0.688 |
Neg logit contributions | |
═ | -1.095 |
DRAG | -0.979 |
Hour | -0.922 |
backdrop | -0.917 |
GEAR | -0.908 |
Token | last |
Token ID | 938 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
ochond | +1.735 |
Filip | +1.651 |
amily | +1.475 |
estine | +1.469 |
urers | +1.434 |
Neg logit contributions | |
═ | -1.770 |
DRAG | -1.562 |
Hour | -1.452 |
backdrop | -1.447 |
GEAR | -1.432 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ochond | +0.524 |
Filip | +0.504 |
amily | +0.463 |
estine | +0.461 |
urers | +0.453 |
Neg logit contributions | |
═ | -0.303 |
DRAG | -0.255 |
Hour | -0.228 |
backdrop | -0.227 |
GEAR | -0.224 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ochond | +0.146 |
Filip | +0.138 |
amily | +0.124 |
estine | +0.124 |
urers | +0.121 |
Neg logit contributions | |
═ | -0.141 |
DRAG | -0.124 |
Hour | -0.116 |
backdrop | -0.115 |
GEAR | -0.113 |
Token | he |
Token ID | 339 |
Feature activation | +5.64e-03 |
Pos logit contributions | |
ochond | +0.117 |
Filip | +0.111 |
amily | +0.100 |
estine | +0.099 |
urers | +0.096 |
Neg logit contributions | |
═ | -0.123 |
DRAG | -0.109 |
Hour | -0.102 |
backdrop | -0.102 |
GEAR | -0.101 |
Token | was |
Token ID | 373 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
═ | +0.005 |
DRAG | +0.005 |
Hour | +0.005 |
backdrop | +0.005 |
GEAR | +0.004 |
Neg logit contributions | |
ochond | -0.005 |
Filip | -0.005 |
amily | -0.004 |
estine | -0.004 |
urers | -0.004 |
Token | ball |
Token ID | 1894 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
ochond | +0.679 |
Filip | +0.644 |
amily | +0.566 |
estine | +0.565 |
fooled | +0.553 |
Neg logit contributions | |
═ | -0.776 |
DRAG | -0.684 |
Hour | -0.638 |
GEAR | -0.629 |
backdrop | -0.628 |
Token | by |
Token ID | 416 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
ochond | +0.493 |
Filip | +0.470 |
amily | +0.416 |
estine | +0.416 |
urers | +0.405 |
Neg logit contributions | |
═ | -0.525 |
DRAG | -0.464 |
Hour | -0.431 |
backdrop | -0.428 |
GEAR | -0.425 |
Token | moving |
Token ID | 3867 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
═ | +0.049 |
DRAG | +0.042 |
Hour | +0.039 |
backdrop | +0.038 |
GEAR | +0.038 |
Neg logit contributions | |
ochond | -0.062 |
Filip | -0.060 |
amily | -0.054 |
estine | -0.054 |
urers | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
ochond | +0.029 |
Filip | +0.028 |
amily | +0.025 |
estine | +0.025 |
urers | +0.024 |
Neg logit contributions | |
═ | -0.029 |
DRAG | -0.026 |
Hour | -0.024 |
backdrop | -0.024 |
GEAR | -0.024 |
Token | Game |
Token ID | 3776 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
ochond | +0.079 |
Filip | +0.075 |
estine | +0.067 |
amily | +0.067 |
urers | +0.066 |
Neg logit contributions | |
═ | -0.077 |
DRAG | -0.067 |
Hour | -0.061 |
backdrop | -0.061 |
GEAR | -0.061 |
Token | Pad |
Token ID | 26114 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ochond | +0.199 |
Filip | +0.181 |
amily | +0.143 |
estine | +0.141 |
urers | +0.134 |
Neg logit contributions | |
═ | -0.562 |
DRAG | -0.517 |
Hour | -0.494 |
backdrop | -0.493 |
GEAR | -0.490 |
Token | around |
Token ID | 1088 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
ochond | +1.681 |
Filip | +1.604 |
estine | +1.423 |
amily | +1.418 |
urers | +1.384 |
Neg logit contributions | |
═ | -1.775 |
DRAG | -1.556 |
Hour | -1.441 |
backdrop | -1.421 |
GEAR | -1.411 |
Token | in |
Token ID | 287 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ochond | +0.556 |
Filip | +0.531 |
amily | +0.469 |
estine | +0.468 |
urers | +0.456 |
Neg logit contributions | |
═ | -0.613 |
DRAG | -0.543 |
Hour | -0.504 |
backdrop | -0.502 |
GEAR | -0.498 |
Token | real |
Token ID | 1103 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
ochond | +0.196 |
Filip | +0.187 |
amily | +0.168 |
estine | +0.167 |
urers | +0.163 |
Neg logit contributions | |
═ | -0.186 |
DRAG | -0.163 |
Hour | -0.150 |
backdrop | -0.150 |
GEAR | -0.149 |
Token | space |
Token ID | 2272 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
ochond | +0.327 |
Filip | +0.312 |
amily | +0.281 |
estine | +0.280 |
urers | +0.274 |
Neg logit contributions | |
═ | -0.290 |
DRAG | -0.254 |
Hour | -0.234 |
backdrop | -0.234 |
GEAR | -0.231 |
Token | and |
Token ID | 290 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
ochond | +0.247 |
Filip | +0.235 |
amily | +0.206 |
estine | +0.206 |
urers | +0.201 |
Neg logit contributions | |
═ | -0.288 |
DRAG | -0.257 |
Hour | -0.239 |
backdrop | -0.238 |
GEAR | -0.236 |
Token | the |
Token ID | 262 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
═ | +0.142 |
DRAG | +0.126 |
Hour | +0.117 |
backdrop | +0.117 |
GEAR | +0.116 |
Neg logit contributions | |
ochond | -0.135 |
Filip | -0.128 |
amily | -0.114 |
estine | -0.114 |
urers | -0.111 |
Token | ram |
Token ID | 15770 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
═ | +0.024 |
DRAG | +0.021 |
Hour | +0.019 |
backdrop | +0.019 |
GEAR | +0.019 |
Neg logit contributions | |
ochond | -0.026 |
Filip | -0.025 |
amily | -0.022 |
estine | -0.022 |
urers | -0.022 |
Token | sh |
Token ID | 1477 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ochond | +0.331 |
Filip | +0.313 |
amily | +0.270 |
estine | +0.270 |
urers | +0.261 |
Neg logit contributions | |
═ | -0.476 |
DRAG | -0.428 |
backdrop | -0.404 |
Hour | -0.404 |
GEAR | -0.398 |
Token | ackle |
Token ID | 20523 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
ochond | +0.143 |
Filip | +0.139 |
estine | +0.126 |
amily | +0.123 |
fooled | +0.121 |
Neg logit contributions | |
═ | -0.129 |
DRAG | -0.113 |
Hour | -0.105 |
backdrop | -0.103 |
GEAR | -0.103 |
Token | family |
Token ID | 1641 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
ochond | +0.031 |
Filip | +0.030 |
amily | +0.027 |
estine | +0.026 |
urers | +0.026 |
Neg logit contributions | |
═ | -0.029 |
DRAG | -0.025 |
Hour | -0.023 |
backdrop | -0.023 |
GEAR | -0.023 |
Token | home |
Token ID | 1363 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ochond | +0.330 |
Filip | +0.312 |
amily | +0.272 |
estine | +0.272 |
urers | +0.264 |
Neg logit contributions | |
═ | -0.445 |
DRAG | -0.400 |
backdrop | -0.375 |
Hour | -0.375 |
GEAR | -0.371 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
ochond | +1.629 |
Filip | +1.550 |
amily | +1.373 |
estine | +1.367 |
urers | +1.332 |
Neg logit contributions | |
═ | -1.824 |
DRAG | -1.620 |
Hour | -1.508 |
backdrop | -1.503 |
GEAR | -1.492 |
Token | Its |
Token ID | 6363 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
ochond | +0.142 |
Filip | +0.135 |
amily | +0.119 |
estine | +0.118 |
urers | +0.115 |
Neg logit contributions | |
═ | -0.172 |
DRAG | -0.153 |
Hour | -0.143 |
backdrop | -0.143 |
GEAR | -0.141 |
Token | waters |
Token ID | 10150 |
Feature activation | -5.81e-03 |
Pos logit contributions | |
ochond | +0.178 |
Filip | +0.170 |
amily | +0.153 |
estine | +0.153 |
urers | +0.149 |
Neg logit contributions | |
═ | -0.158 |
DRAG | -0.138 |
Hour | -0.127 |
backdrop | -0.126 |
GEAR | -0.125 |
Token | are |
Token ID | 389 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ochond | +0.006 |
Filip | +0.005 |
amily | +0.005 |
estine | +0.005 |
urers | +0.005 |
Neg logit contributions | |
═ | -0.005 |
DRAG | -0.005 |
Hour | -0.004 |
backdrop | -0.004 |
GEAR | -0.004 |
Token | contaminated |
Token ID | 23543 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
═ | +0.110 |
DRAG | +0.097 |
backdrop | +0.091 |
Hour | +0.091 |
GEAR | +0.089 |
Neg logit contributions | |
ochond | -0.107 |
Filip | -0.101 |
amily | -0.091 |
estine | -0.090 |
urers | -0.088 |
Token | ones |
Token ID | 3392 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
ochond | +1.019 |
Filip | +0.973 |
amily | +0.867 |
estine | +0.865 |
urers | +0.843 |
Neg logit contributions | |
═ | -1.036 |
DRAG | -0.913 |
Hour | -0.842 |
backdrop | -0.841 |
GEAR | -0.835 |
Token | might |
Token ID | 1244 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
ochond | +0.465 |
Filip | +0.442 |
amily | +0.396 |
estine | +0.395 |
urers | +0.384 |
Neg logit contributions | |
═ | -0.475 |
DRAG | -0.421 |
Hour | -0.394 |
backdrop | -0.392 |
GEAR | -0.387 |
Token | no |
Token ID | 645 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ochond | +0.522 |
Filip | +0.499 |
amily | +0.445 |
estine | +0.445 |
urers | +0.434 |
Neg logit contributions | |
═ | -0.487 |
DRAG | -0.424 |
Hour | -0.391 |
backdrop | -0.388 |
GEAR | -0.386 |
Token | longer |
Token ID | 2392 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
ochond | +0.304 |
Filip | +0.291 |
estine | +0.263 |
amily | +0.263 |
urers | +0.256 |
Neg logit contributions | |
═ | -0.251 |
DRAG | -0.218 |
Hour | -0.198 |
backdrop | -0.198 |
GEAR | -0.197 |
Token | get |
Token ID | 651 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
ochond | +0.566 |
Filip | +0.544 |
estine | +0.486 |
amily | +0.485 |
urers | +0.472 |
Neg logit contributions | |
═ | -0.510 |
DRAG | -0.442 |
Hour | -0.403 |
GEAR | -0.402 |
backdrop | -0.401 |
Token | home |
Token ID | 1363 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ochond | +0.648 |
Filip | +0.616 |
amily | +0.552 |
estine | +0.550 |
urers | +0.536 |
Neg logit contributions | |
═ | -0.650 |
DRAG | -0.573 |
Hour | -0.535 |
backdrop | -0.533 |
GEAR | -0.526 |
Token | first |
Token ID | 717 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
ochond | +1.645 |
Filip | +1.571 |
amily | +1.390 |
estine | +1.389 |
urers | +1.353 |
Neg logit contributions | |
═ | -1.767 |
DRAG | -1.572 |
backdrop | -1.449 |
Hour | -1.449 |
GEAR | -1.440 |
Token | . |
Token ID | 13 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
ochond | +0.657 |
Filip | +0.624 |
amily | +0.549 |
estine | +0.549 |
urers | +0.534 |
Neg logit contributions | |
═ | -0.786 |
DRAG | -0.702 |
backdrop | -0.649 |
Hour | -0.648 |
GEAR | -0.645 |
Token |
|
Token ID | 198 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
ochond | +0.417 |
Filip | +0.400 |
amily | +0.348 |
estine | +0.346 |
urers | +0.337 |
Neg logit contributions | |
═ | -0.521 |
DRAG | -0.463 |
backdrop | -0.432 |
Hour | -0.427 |
GEAR | -0.426 |
Token |
|
Token ID | 198 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ochond | +0.218 |
Filip | +0.205 |
estine | +0.170 |
amily | +0.170 |
urers | +0.163 |
Neg logit contributions | |
═ | -0.415 |
DRAG | -0.378 |
backdrop | -0.355 |
Hour | -0.355 |
GEAR | -0.353 |
Token | But |
Token ID | 1537 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
ochond | +0.206 |
Filip | +0.193 |
amily | +0.167 |
estine | +0.166 |
urers | +0.160 |
Neg logit contributions | |
═ | -0.328 |
DRAG | -0.294 |
Hour | -0.280 |
backdrop | -0.278 |
GEAR | -0.276 |
Token | genuinely |
Token ID | 17170 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
ochond | +0.007 |
Filip | +0.007 |
amily | +0.006 |
estine | +0.006 |
urers | +0.006 |
Neg logit contributions | |
═ | -0.007 |
DRAG | -0.006 |
Hour | -0.006 |
backdrop | -0.006 |
GEAR | -0.005 |
Token | frightening |
Token ID | 23101 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ochond | +0.494 |
Filip | +0.474 |
amily | +0.425 |
estine | +0.422 |
urers | +0.415 |
Neg logit contributions | |
═ | -0.451 |
DRAG | -0.392 |
Hour | -0.360 |
backdrop | -0.359 |
GEAR | -0.359 |
Token | or |
Token ID | 393 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
ochond | +0.156 |
Filip | +0.148 |
amily | +0.132 |
estine | +0.132 |
urers | +0.128 |
Neg logit contributions | |
═ | -0.165 |
DRAG | -0.146 |
Hour | -0.136 |
backdrop | -0.135 |
GEAR | -0.134 |
Token | disturbing |
Token ID | 14851 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
═ | +0.017 |
DRAG | +0.015 |
Hour | +0.013 |
backdrop | +0.013 |
GEAR | +0.013 |
Neg logit contributions | |
ochond | -0.018 |
Filip | -0.017 |
amily | -0.015 |
estine | -0.015 |
urers | -0.015 |
Token | about |
Token ID | 546 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
ochond | +0.106 |
Filip | +0.101 |
amily | +0.090 |
estine | +0.089 |
urers | +0.087 |
Neg logit contributions | |
═ | -0.120 |
DRAG | -0.107 |
Hour | -0.099 |
backdrop | -0.099 |
GEAR | -0.098 |
Token | Lovecraft |
Token ID | 37655 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ochond | +0.022 |
Filip | +0.021 |
amily | +0.018 |
estine | +0.018 |
urers | +0.018 |
Neg logit contributions | |
═ | -0.027 |
DRAG | -0.024 |
Hour | -0.023 |
backdrop | -0.023 |
GEAR | -0.022 |
Token | � |
Token ID | 447 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ochond | +1.451 |
Filip | +1.372 |
amily | +1.198 |
estine | +1.193 |
urers | +1.157 |
Neg logit contributions | |
═ | -1.963 |
DRAG | -1.763 |
Hour | -1.652 |
backdrop | -1.647 |
GEAR | -1.636 |
Token | � |
Token ID | 247 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
═ | +0.103 |
DRAG | +0.089 |
backdrop | +0.080 |
Hour | +0.079 |
GEAR | +0.078 |
Neg logit contributions | |
ochond | -0.153 |
Filip | -0.148 |
amily | -0.136 |
estine | -0.135 |
owers | -0.131 |
Token | s |
Token ID | 82 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
ochond | +0.157 |
Filip | +0.150 |
amily | +0.135 |
estine | +0.134 |
urers | +0.132 |
Neg logit contributions | |
═ | -0.138 |
DRAG | -0.120 |
Hour | -0.111 |
backdrop | -0.111 |
GEAR | -0.109 |
Token | writing |
Token ID | 3597 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ochond | +0.026 |
Filip | +0.025 |
amily | +0.023 |
estine | +0.022 |
urers | +0.022 |
Neg logit contributions | |
═ | -0.017 |
DRAG | -0.014 |
Hour | -0.013 |
backdrop | -0.013 |
GEAR | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
═ | +0.149 |
DRAG | +0.132 |
Hour | +0.123 |
backdrop | +0.123 |
GEAR | +0.122 |
Neg logit contributions | |
ochond | -0.130 |
Filip | -0.124 |
amily | -0.110 |
estine | -0.109 |
urers | -0.106 |
Token | instead |
Token ID | 2427 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ochond | +0.123 |
Filip | +0.118 |
amily | +0.105 |
estine | +0.105 |
urers | +0.103 |
Neg logit contributions | |
═ | -0.118 |
DRAG | -0.104 |
Hour | -0.096 |
backdrop | -0.096 |
GEAR | -0.095 |
Token | of |
Token ID | 286 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
ochond | +0.441 |
Filip | +0.423 |
amily | +0.382 |
estine | +0.381 |
urers | +0.373 |
Neg logit contributions | |
═ | -0.359 |
DRAG | -0.311 |
Hour | -0.286 |
backdrop | -0.285 |
GEAR | -0.281 |
Token | going |
Token ID | 1016 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
ochond | +0.084 |
Filip | +0.080 |
amily | +0.072 |
estine | +0.071 |
urers | +0.070 |
Neg logit contributions | |
═ | -0.080 |
DRAG | -0.070 |
Hour | -0.065 |
backdrop | -0.064 |
GEAR | -0.064 |
Token | through |
Token ID | 832 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
═ | +0.045 |
DRAG | +0.039 |
Hour | +0.036 |
backdrop | +0.036 |
GEAR | +0.036 |
Neg logit contributions | |
ochond | -0.047 |
Filip | -0.044 |
amily | -0.040 |
estine | -0.040 |
urers | -0.039 |
Token | std |
Token ID | 14367 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
ochond | +0.219 |
Filip | +0.208 |
amily | +0.185 |
estine | +0.185 |
urers | +0.180 |
Neg logit contributions | |
═ | -0.236 |
DRAG | -0.209 |
Hour | -0.195 |
backdrop | -0.194 |
GEAR | -0.192 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ochond | +0.501 |
Filip | +0.472 |
amily | +0.408 |
estine | +0.404 |
urers | +0.394 |
Neg logit contributions | |
═ | -0.771 |
DRAG | -0.695 |
Hour | -0.655 |
backdrop | -0.654 |
GEAR | -0.647 |
Token | ist |
Token ID | 396 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
ochond | +1.528 |
Filip | +1.446 |
amily | +1.273 |
estine | +1.271 |
urers | +1.231 |
Neg logit contributions | |
═ | -1.877 |
DRAG | -1.678 |
Hour | -1.566 |
backdrop | -1.560 |
GEAR | -1.555 |
Token | ream |
Token ID | 1476 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
ochond | +0.553 |
Filip | +0.527 |
amily | +0.468 |
estine | +0.465 |
urers | +0.457 |
Neg logit contributions | |
═ | -0.572 |
DRAG | -0.503 |
Hour | -0.470 |
backdrop | -0.467 |
GEAR | -0.462 |
Token | . |
Token ID | 13 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ochond | +0.424 |
Filip | +0.403 |
amily | +0.356 |
estine | +0.354 |
urers | +0.346 |
Neg logit contributions | |
═ | -0.497 |
DRAG | -0.441 |
Hour | -0.413 |
backdrop | -0.412 |
GEAR | -0.407 |
Token | I |
Token ID | 314 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ochond | +0.150 |
Filip | +0.142 |
amily | +0.125 |
estine | +0.125 |
urers | +0.121 |
Neg logit contributions | |
═ | -0.180 |
DRAG | -0.160 |
Hour | -0.150 |
backdrop | -0.149 |
GEAR | -0.148 |
Token | also |
Token ID | 635 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
ochond | +0.190 |
Filip | +0.181 |
amily | +0.161 |
estine | +0.160 |
urers | +0.157 |
Neg logit contributions | |
═ | -0.196 |
DRAG | -0.174 |
Hour | -0.161 |
backdrop | -0.161 |
GEAR | -0.160 |
Token | Experimental |
Token ID | 32286 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
ochond | +0.237 |
Filip | +0.228 |
amily | +0.205 |
estine | +0.205 |
urers | +0.200 |
Neg logit contributions | |
═ | -0.190 |
DRAG | -0.164 |
Hour | -0.150 |
backdrop | -0.150 |
GEAR | -0.148 |
Token | subjects |
Token ID | 7481 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
═ | +0.294 |
DRAG | +0.251 |
Hour | +0.227 |
backdrop | +0.226 |
GEAR | +0.224 |
Neg logit contributions | |
ochond | -0.427 |
Filip | -0.410 |
amily | -0.373 |
estine | -0.372 |
urers | -0.365 |
Token | Three |
Token ID | 7683 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
ochond | +0.086 |
Filip | +0.082 |
amily | +0.073 |
estine | +0.073 |
urers | +0.071 |
Neg logit contributions | |
═ | -0.087 |
DRAG | -0.077 |
Hour | -0.071 |
backdrop | -0.071 |
GEAR | -0.070 |
Token | female |
Token ID | 4048 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
═ | +0.389 |
DRAG | +0.345 |
Hour | +0.322 |
backdrop | +0.321 |
GEAR | +0.317 |
Neg logit contributions | |
ochond | -0.360 |
Filip | -0.342 |
amily | -0.305 |
estine | -0.304 |
urers | -0.296 |
Token | r |
Token ID | 374 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
═ | +0.144 |
DRAG | +0.127 |
Hour | +0.118 |
backdrop | +0.118 |
GEAR | +0.117 |
Neg logit contributions | |
ochond | -0.138 |
Filip | -0.131 |
amily | -0.117 |
estine | -0.116 |
urers | -0.114 |
Token | hes |
Token ID | 956 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ochond | +0.448 |
Filip | +0.414 |
amily | +0.340 |
estine | +0.337 |
urers | +0.323 |
Neg logit contributions | |
═ | -1.013 |
DRAG | -0.927 |
Hour | -0.878 |
backdrop | -0.878 |
GEAR | -0.873 |
Token | us |
Token ID | 385 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
ochond | +1.063 |
Filip | +0.987 |
amily | +0.816 |
estine | +0.811 |
urers | +0.769 |
Neg logit contributions | |
═ | -2.322 |
DRAG | -2.119 |
Hour | -2.016 |
backdrop | -2.013 |
GEAR | -1.997 |
Token | monkeys |
Token ID | 26697 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ochond | +0.656 |
Filip | +0.621 |
estine | +0.555 |
amily | +0.554 |
urers | +0.534 |
Neg logit contributions | |
═ | -0.745 |
DRAG | -0.663 |
Hour | -0.619 |
backdrop | -0.617 |
GEAR | -0.610 |
Token | ( |
Token ID | 357 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
═ | +0.107 |
DRAG | +0.094 |
Hour | +0.088 |
backdrop | +0.088 |
GEAR | +0.087 |
Neg logit contributions | |
ochond | -0.098 |
Filip | -0.093 |
amily | -0.082 |
estine | -0.082 |
urers | -0.080 |
Token | Mac |
Token ID | 14155 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ochond | +0.157 |
Filip | +0.148 |
amily | +0.128 |
estine | +0.128 |
urers | +0.124 |
Neg logit contributions | |
═ | -0.228 |
DRAG | -0.206 |
Hour | -0.193 |
backdrop | -0.193 |
GEAR | -0.191 |
Token | aca |
Token ID | 22260 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
ochond | +1.217 |
Filip | +1.156 |
amily | +1.022 |
estine | +1.013 |
urers | +0.991 |
Neg logit contributions | |
═ | -1.411 |
DRAG | -1.251 |
Hour | -1.169 |
backdrop | -1.167 |
GEAR | -1.158 |
Token | � |
Token ID | 447 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ochond | +1.246 |
Filip | +1.188 |
amily | +1.060 |
estine | +1.056 |
urers | +1.030 |
Neg logit contributions | |
═ | -1.266 |
DRAG | -1.118 |
Hour | -1.037 |
backdrop | -1.034 |
GEAR | -1.025 |
Token | � |
Token ID | 247 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ochond | +0.132 |
Filip | +0.128 |
amily | +0.118 |
estine | +0.116 |
owers | +0.114 |
Neg logit contributions | |
═ | -0.089 |
DRAG | -0.077 |
backdrop | -0.069 |
Hour | -0.068 |
GEAR | -0.067 |
Token | s |
Token ID | 82 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
ochond | +0.142 |
Filip | +0.135 |
amily | +0.122 |
estine | +0.121 |
urers | +0.119 |
Neg logit contributions | |
═ | -0.128 |
DRAG | -0.112 |
Hour | -0.103 |
backdrop | -0.103 |
GEAR | -0.102 |
Token | Drew |
Token ID | 18624 |
Feature activation | +1.70e-03 |
Pos logit contributions | |
═ | +0.007 |
DRAG | +0.007 |
Hour | +0.006 |
backdrop | +0.006 |
GEAR | +0.006 |
Neg logit contributions | |
ochond | -0.007 |
Filip | -0.006 |
amily | -0.006 |
estine | -0.006 |
urers | -0.005 |
Token | P |
Token ID | 350 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
═ | +0.002 |
DRAG | +0.002 |
backdrop | +0.001 |
Hour | +0.001 |
GEAR | +0.001 |
Neg logit contributions | |
ochond | -0.002 |
Filip | -0.001 |
amily | -0.001 |
estine | -0.001 |
urers | -0.001 |
Token | omer |
Token ID | 12057 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ochond | +0.228 |
Filip | +0.216 |
estine | +0.187 |
amily | +0.187 |
urers | +0.182 |
Neg logit contributions | |
═ | -0.319 |
DRAG | -0.287 |
Hour | -0.270 |
backdrop | -0.269 |
GEAR | -0.266 |
Token | anz |
Token ID | 35410 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
ochond | +1.550 |
Filip | +1.473 |
amily | +1.299 |
estine | +1.297 |
urers | +1.257 |
Neg logit contributions | |
═ | -1.846 |
DRAG | -1.640 |
Hour | -1.531 |
backdrop | -1.530 |
GEAR | -1.517 |
Token | and |
Token ID | 290 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
═ | +0.076 |
DRAG | +0.066 |
Hour | +0.062 |
backdrop | +0.061 |
GEAR | +0.061 |
Neg logit contributions | |
ochond | -0.078 |
Filip | -0.074 |
amily | -0.066 |
estine | -0.066 |
urers | -0.064 |
Token | potentially |
Token ID | 6196 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ochond | +0.058 |
Filip | +0.054 |
amily | +0.048 |
estine | +0.048 |
urers | +0.046 |
Neg logit contributions | |
═ | -0.074 |
DRAG | -0.066 |
Hour | -0.062 |
backdrop | -0.061 |
GEAR | -0.061 |
Token | Oakland |
Token ID | 12369 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ochond | +0.155 |
Filip | +0.146 |
amily | +0.131 |
estine | +0.130 |
urers | +0.126 |
Neg logit contributions | |
═ | -0.174 |
DRAG | -0.155 |
Hour | -0.144 |
backdrop | -0.144 |
GEAR | -0.142 |
Token | � |
Token ID | 447 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ochond | +0.495 |
Filip | +0.470 |
amily | +0.417 |
estine | +0.416 |
urers | +0.405 |
Neg logit contributions | |
═ | -0.558 |
DRAG | -0.495 |
Hour | -0.462 |
backdrop | -0.460 |
GEAR | -0.456 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
═ | +0.131 |
DRAG | +0.116 |
Hour | +0.107 |
backdrop | +0.107 |
GEAR | +0.106 |
Neg logit contributions | |
ochond | -0.122 |
Filip | -0.117 |
estine | -0.104 |
amily | -0.103 |
urers | -0.101 |
Token | Kart |
Token ID | 32872 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
ochond | +0.014 |
Filip | +0.014 |
estine | +0.012 |
amily | +0.012 |
urers | +0.012 |
Neg logit contributions | |
═ | -0.015 |
DRAG | -0.013 |
backdrop | -0.012 |
GEAR | -0.012 |
Hour | -0.012 |
Token | ing |
Token ID | 278 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
ochond | +0.066 |
Filip | +0.063 |
amily | +0.056 |
estine | +0.055 |
urers | +0.054 |
Neg logit contributions | |
═ | -0.072 |
DRAG | -0.064 |
Hour | -0.059 |
backdrop | -0.059 |
GEAR | -0.059 |
Token | has |
Token ID | 468 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
═ | +0.657 |
DRAG | +0.581 |
Hour | +0.540 |
backdrop | +0.538 |
GEAR | +0.533 |
Neg logit contributions | |
ochond | -0.637 |
Filip | -0.606 |
amily | -0.541 |
estine | -0.539 |
urers | -0.525 |
Token | bo |
Token ID | 1489 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
═ | +0.202 |
DRAG | +0.180 |
Hour | +0.167 |
backdrop | +0.166 |
GEAR | +0.165 |
Neg logit contributions | |
ochond | -0.192 |
Filip | -0.182 |
amily | -0.163 |
estine | -0.162 |
urers | -0.158 |
Token | omed |
Token ID | 12657 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
═ | +0.119 |
DRAG | +0.108 |
Hour | +0.101 |
backdrop | +0.101 |
GEAR | +0.100 |
Neg logit contributions | |
ochond | -0.081 |
Filip | -0.077 |
amily | -0.067 |
estine | -0.066 |
urers | -0.064 |
Token | since |
Token ID | 1201 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
ochond | +1.568 |
Filip | +1.502 |
estine | +1.316 |
amily | +1.313 |
urers | +1.284 |
Neg logit contributions | |
═ | -1.794 |
DRAG | -1.595 |
Hour | -1.476 |
backdrop | -1.475 |
GEAR | -1.466 |
Token | Hamilton |
Token ID | 11582 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
═ | +0.037 |
DRAG | +0.033 |
Hour | +0.031 |
backdrop | +0.031 |
GEAR | +0.031 |
Neg logit contributions | |
ochond | -0.033 |
Filip | -0.031 |
amily | -0.028 |
estine | -0.028 |
urers | -0.027 |
Token | rose |
Token ID | 8278 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ochond | +0.117 |
Filip | +0.111 |
amily | +0.099 |
estine | +0.098 |
urers | +0.096 |
Neg logit contributions | |
═ | -0.126 |
DRAG | -0.112 |
Hour | -0.104 |
backdrop | -0.104 |
GEAR | -0.103 |
Token | to |
Token ID | 284 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
═ | +0.498 |
DRAG | +0.439 |
Hour | +0.411 |
backdrop | +0.408 |
GEAR | +0.405 |
Neg logit contributions | |
ochond | -0.498 |
Filip | -0.471 |
amily | -0.425 |
estine | -0.421 |
urers | -0.412 |
Token | prominence |
Token ID | 31198 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
═ | +0.182 |
DRAG | +0.156 |
Hour | +0.142 |
backdrop | +0.142 |
GEAR | +0.140 |
Neg logit contributions | |
ochond | -0.251 |
Filip | -0.241 |
amily | -0.219 |
estine | -0.218 |
urers | -0.214 |
Token | further |
Token ID | 2252 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
═ | +0.217 |
DRAG | +0.188 |
Hour | +0.173 |
backdrop | +0.172 |
GEAR | +0.171 |
Neg logit contributions | |
ochond | -0.253 |
Filip | -0.243 |
amily | -0.218 |
estine | -0.217 |
urers | -0.213 |
Token | verification |
Token ID | 19637 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ochond | +0.293 |
Filip | +0.283 |
amily | +0.253 |
estine | +0.252 |
fooled | +0.247 |
Neg logit contributions | |
═ | -0.245 |
DRAG | -0.212 |
Hour | -0.195 |
backdrop | -0.191 |
GEAR | -0.191 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ochond | +0.265 |
Filip | +0.252 |
amily | +0.221 |
estine | +0.220 |
urers | +0.214 |
Neg logit contributions | |
═ | -0.322 |
DRAG | -0.287 |
Hour | -0.268 |
backdrop | -0.267 |
GEAR | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ochond | +0.145 |
Filip | +0.137 |
amily | +0.121 |
estine | +0.121 |
urers | +0.117 |
Neg logit contributions | |
═ | -0.178 |
DRAG | -0.159 |
Hour | -0.148 |
backdrop | -0.148 |
GEAR | -0.147 |
Token |
|
Token ID | 198 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
ochond | +0.156 |
Filip | +0.146 |
amily | +0.123 |
estine | +0.123 |
urers | +0.118 |
Neg logit contributions | |
═ | -0.280 |
DRAG | -0.254 |
Hour | -0.240 |
backdrop | -0.240 |
GEAR | -0.238 |
Token | ** |
Token ID | 1174 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ochond | +0.204 |
Filip | +0.192 |
amily | +0.166 |
estine | +0.165 |
urers | +0.160 |
Neg logit contributions | |
═ | -0.323 |
DRAG | -0.290 |
Hour | -0.274 |
backdrop | -0.273 |
GEAR | -0.271 |
Token | In |
Token ID | 554 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ochond | +1.575 |
Filip | +1.508 |
amily | +1.328 |
estine | +1.326 |
urers | +1.291 |
Neg logit contributions | |
═ | -1.765 |
DRAG | -1.564 |
Hour | -1.456 |
backdrop | -1.453 |
GEAR | -1.440 |
Token | many |
Token ID | 867 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ochond | +0.196 |
Filip | +0.187 |
amily | +0.169 |
estine | +0.168 |
urers | +0.164 |
Neg logit contributions | |
═ | -0.171 |
DRAG | -0.149 |
Hour | -0.137 |
backdrop | -0.137 |
GEAR | -0.136 |
Token | banks |
Token ID | 6341 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
ochond | +0.188 |
Filip | +0.180 |
amily | +0.161 |
estine | +0.161 |
urers | +0.157 |
Neg logit contributions | |
═ | -0.176 |
DRAG | -0.155 |
Hour | -0.143 |
backdrop | -0.143 |
GEAR | -0.141 |
Token | one |
Token ID | 530 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
ochond | +0.588 |
Filip | +0.554 |
amily | +0.497 |
estine | +0.492 |
urers | +0.478 |
Neg logit contributions | |
═ | -0.633 |
DRAG | -0.561 |
backdrop | -0.525 |
Hour | -0.522 |
GEAR | -0.515 |
Token | doesn |
Token ID | 1595 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
ochond | +0.101 |
Filip | +0.096 |
amily | +0.087 |
estine | +0.087 |
urers | +0.085 |
Neg logit contributions | |
═ | -0.086 |
DRAG | -0.075 |
Hour | -0.069 |
backdrop | -0.068 |
GEAR | -0.068 |
Token | when |
Token ID | 618 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
ochond | +0.334 |
Filip | +0.319 |
amily | +0.285 |
estine | +0.284 |
urers | +0.277 |
Neg logit contributions | |
═ | -0.330 |
DRAG | -0.290 |
Hour | -0.269 |
backdrop | -0.268 |
GEAR | -0.265 |
Token | you |
Token ID | 345 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
ochond | +0.006 |
Filip | +0.006 |
amily | +0.005 |
estine | +0.005 |
urers | +0.005 |
Neg logit contributions | |
═ | -0.007 |
DRAG | -0.006 |
Hour | -0.006 |
backdrop | -0.006 |
GEAR | -0.006 |
Token | turn |
Token ID | 1210 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
═ | +0.008 |
DRAG | +0.007 |
Hour | +0.006 |
backdrop | +0.006 |
GEAR | +0.006 |
Neg logit contributions | |
ochond | -0.008 |
Filip | -0.008 |
amily | -0.007 |
estine | -0.007 |
urers | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
ochond | +0.523 |
Filip | +0.493 |
amily | +0.444 |
estine | +0.441 |
urers | +0.430 |
Neg logit contributions | |
═ | -0.544 |
DRAG | -0.483 |
backdrop | -0.450 |
Hour | -0.450 |
GEAR | -0.444 |
Token | f |
Token ID | 277 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
═ | +0.009 |
DRAG | +0.008 |
Hour | +0.007 |
backdrop | +0.007 |
GEAR | +0.007 |
Neg logit contributions | |
ochond | -0.009 |
Filip | -0.009 |
amily | -0.008 |
estine | -0.008 |
urers | -0.008 |
Token | auc |
Token ID | 14272 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
═ | +0.197 |
DRAG | +0.182 |
backdrop | +0.175 |
Hour | +0.175 |
GEAR | +0.173 |
Neg logit contributions | |
ochond | -0.048 |
Filip | -0.041 |
amily | -0.029 |
estine | -0.029 |
fooled | -0.027 |
Token | et |
Token ID | 316 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
ochond | +1.362 |
Filip | +1.285 |
amily | +1.115 |
estine | +1.111 |
urers | +1.076 |
Neg logit contributions | |
═ | -1.988 |
DRAG | -1.791 |
Hour | -1.680 |
backdrop | -1.677 |
GEAR | -1.665 |
Token | on |
Token ID | 319 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
ochond | +0.838 |
Filip | +0.798 |
amily | +0.710 |
estine | +0.708 |
urers | +0.690 |
Neg logit contributions | |
═ | -0.893 |
DRAG | -0.791 |
Hour | -0.735 |
backdrop | -0.733 |
GEAR | -0.726 |
Token | , |
Token ID | 11 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
═ | +0.083 |
DRAG | +0.073 |
Hour | +0.068 |
backdrop | +0.068 |
GEAR | +0.067 |
Neg logit contributions | |
ochond | -0.080 |
Filip | -0.076 |
amily | -0.068 |
estine | -0.068 |
urers | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | -6.78e-03 |
Pos logit contributions | |
═ | +0.071 |
DRAG | +0.064 |
Hour | +0.059 |
backdrop | +0.059 |
GEAR | +0.058 |
Neg logit contributions | |
ochond | -0.063 |
Filip | -0.060 |
amily | -0.053 |
estine | -0.053 |
urers | -0.052 |
Token | water |
Token ID | 1660 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
ochond | +0.006 |
Filip | +0.006 |
amily | +0.006 |
estine | +0.005 |
urers | +0.005 |
Neg logit contributions | |
═ | -0.006 |
DRAG | -0.006 |
Hour | -0.005 |
backdrop | -0.005 |
GEAR | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
ochond | +0.132 |
Filip | +0.125 |
amily | +0.111 |
estine | +0.110 |
urers | +0.107 |
Neg logit contributions | |
═ | -0.156 |
DRAG | -0.139 |
Hour | -0.130 |
backdrop | -0.129 |
GEAR | -0.128 |
Token | player |
Token ID | 2137 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
ochond | +0.087 |
Filip | +0.083 |
amily | +0.074 |
estine | +0.074 |
urers | +0.073 |
Neg logit contributions | |
═ | -0.074 |
DRAG | -0.064 |
Hour | -0.059 |
backdrop | -0.059 |
GEAR | -0.058 |
Token | holds |
Token ID | 6622 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ochond | +0.559 |
Filip | +0.534 |
amily | +0.478 |
estine | +0.476 |
urers | +0.465 |
Neg logit contributions | |
═ | -0.538 |
DRAG | -0.473 |
Hour | -0.438 |
backdrop | -0.436 |
GEAR | -0.432 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ochond | +0.228 |
Filip | +0.217 |
amily | +0.192 |
estine | +0.191 |
urers | +0.186 |
Neg logit contributions | |
═ | -0.253 |
DRAG | -0.225 |
Hour | -0.209 |
backdrop | -0.209 |
GEAR | -0.207 |
Token | Game |
Token ID | 3776 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ochond | +0.113 |
Filip | +0.108 |
estine | +0.097 |
amily | +0.097 |
urers | +0.095 |
Neg logit contributions | |
═ | -0.097 |
DRAG | -0.084 |
Hour | -0.077 |
backdrop | -0.077 |
GEAR | -0.076 |
Token | Pad |
Token ID | 26114 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ochond | +0.165 |
Filip | +0.149 |
amily | +0.114 |
estine | +0.113 |
urers | +0.105 |
Neg logit contributions | |
═ | -0.516 |
DRAG | -0.476 |
Hour | -0.452 |
backdrop | -0.452 |
GEAR | -0.449 |
Token | to |
Token ID | 284 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ochond | +1.589 |
Filip | +1.517 |
estine | +1.344 |
amily | +1.341 |
urers | +1.308 |
Neg logit contributions | |
═ | -1.706 |
DRAG | -1.504 |
Hour | -1.394 |
backdrop | -1.381 |
GEAR | -1.373 |
Token | track |
Token ID | 2610 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ochond | +0.166 |
Filip | +0.159 |
amily | +0.144 |
estine | +0.143 |
urers | +0.140 |
Neg logit contributions | |
═ | -0.141 |
DRAG | -0.123 |
Hour | -0.113 |
backdrop | -0.113 |
GEAR | -0.111 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
═ | +0.149 |
DRAG | +0.133 |
Hour | +0.124 |
backdrop | +0.124 |
GEAR | +0.123 |
Neg logit contributions | |
ochond | -0.127 |
Filip | -0.120 |
amily | -0.106 |
estine | -0.106 |
urers | -0.103 |
Token | catch |
Token ID | 4929 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
ochond | +0.121 |
Filip | +0.117 |
estine | +0.105 |
amily | +0.105 |
urers | +0.103 |
Neg logit contributions | |
═ | -0.093 |
DRAG | -0.080 |
Hour | -0.073 |
backdrop | -0.072 |
GEAR | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
═ | +0.059 |
DRAG | +0.052 |
Hour | +0.049 |
backdrop | +0.049 |
GEAR | +0.048 |
Neg logit contributions | |
ochond | -0.047 |
Filip | -0.045 |
amily | -0.040 |
estine | -0.039 |
urers | -0.038 |
Token | - |
Token ID | 12 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
═ | +0.260 |
DRAG | +0.231 |
Hour | +0.216 |
backdrop | +0.215 |
GEAR | +0.213 |
Neg logit contributions | |
ochond | -0.229 |
Filip | -0.218 |
amily | -0.193 |
estine | -0.192 |
urers | -0.187 |
Token | cool |
Token ID | 24494 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ochond | +0.321 |
Filip | +0.306 |
amily | +0.272 |
estine | +0.271 |
urers | +0.264 |
Neg logit contributions | |
═ | -0.342 |
DRAG | -0.303 |
Hour | -0.282 |
backdrop | -0.281 |
GEAR | -0.278 |
Token | factor |
Token ID | 5766 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
═ | +0.604 |
DRAG | +0.526 |
Hour | +0.484 |
backdrop | +0.482 |
GEAR | +0.477 |
Neg logit contributions | |
ochond | -0.709 |
Filip | -0.679 |
amily | -0.612 |
estine | -0.610 |
urers | -0.596 |
Token | of |
Token ID | 286 |
Feature activation | -6.05e-03 |
Pos logit contributions | |
═ | +0.360 |
DRAG | +0.318 |
Hour | +0.297 |
backdrop | +0.297 |
GEAR | +0.292 |
Neg logit contributions | |
ochond | -0.349 |
Filip | -0.331 |
amily | -0.297 |
estine | -0.296 |
urers | -0.288 |
Token | having |
Token ID | 1719 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ochond | +0.006 |
Filip | +0.005 |
amily | +0.005 |
estine | +0.005 |
urers | +0.005 |
Neg logit contributions | |
═ | -0.006 |
DRAG | -0.005 |
Hour | -0.005 |
backdrop | -0.005 |
GEAR | -0.005 |
Token | home |
Token ID | 1363 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
═ | +0.313 |
DRAG | +0.279 |
Hour | +0.260 |
backdrop | +0.259 |
GEAR | +0.255 |
Neg logit contributions | |
ochond | -0.308 |
Filip | -0.291 |
amily | -0.264 |
estine | -0.262 |
urers | -0.255 |
Token | red |
Token ID | 445 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ochond | +1.647 |
Filip | +1.570 |
amily | +1.401 |
estine | +1.396 |
urers | +1.363 |
Neg logit contributions | |
═ | -1.650 |
DRAG | -1.454 |
Hour | -1.348 |
backdrop | -1.342 |
GEAR | -1.332 |
Token | to |
Token ID | 284 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
ochond | +0.094 |
Filip | +0.089 |
amily | +0.079 |
estine | +0.079 |
urers | +0.077 |
Neg logit contributions | |
═ | -0.106 |
DRAG | -0.094 |
Hour | -0.088 |
backdrop | -0.088 |
GEAR | -0.087 |
Token | lead |
Token ID | 1085 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ochond | +0.092 |
Filip | +0.087 |
amily | +0.079 |
estine | +0.079 |
urers | +0.077 |
Neg logit contributions | |
═ | -0.084 |
DRAG | -0.074 |
Hour | -0.069 |
backdrop | -0.069 |
GEAR | -0.067 |
Token | off |
Token ID | 572 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
ochond | +0.951 |
Filip | +0.903 |
amily | +0.805 |
estine | +0.802 |
urers | +0.782 |
Neg logit contributions | |
═ | -1.027 |
DRAG | -0.911 |
Hour | -0.849 |
backdrop | -0.845 |
GEAR | -0.837 |
Token | Game |
Token ID | 3776 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
ochond | +0.500 |
Filip | +0.475 |
amily | +0.424 |
estine | +0.422 |
urers | +0.412 |
Neg logit contributions | |
═ | -0.528 |
DRAG | -0.467 |
Hour | -0.436 |
backdrop | -0.434 |
GEAR | -0.429 |
Token | � |
Token ID | 447 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ochond | +1.383 |
Filip | +1.316 |
amily | +1.168 |
estine | +1.164 |
urers | +1.135 |
Neg logit contributions | |
═ | -1.508 |
DRAG | -1.337 |
Hour | -1.245 |
backdrop | -1.241 |
GEAR | -1.229 |
Token | � |
Token ID | 247 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
═ | +0.144 |
DRAG | +0.123 |
backdrop | +0.110 |
Hour | +0.109 |
GEAR | +0.108 |
Neg logit contributions | |
ochond | -0.231 |
Filip | -0.223 |
amily | -0.205 |
estine | -0.204 |
urers | -0.199 |
Token | s |
Token ID | 82 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
═ | +0.015 |
DRAG | +0.014 |
Hour | +0.013 |
backdrop | +0.013 |
GEAR | +0.012 |
Neg logit contributions | |
ochond | -0.016 |
Filip | -0.016 |
amily | -0.014 |
estine | -0.014 |
urers | -0.014 |
Token | work |
Token ID | 670 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
═ | +0.080 |
DRAG | +0.069 |
Hour | +0.063 |
backdrop | +0.063 |
GEAR | +0.063 |
Neg logit contributions | |
ochond | -0.100 |
Filip | -0.096 |
amily | -0.087 |
estine | -0.087 |
urers | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
═ | +0.144 |
DRAG | +0.128 |
Hour | +0.120 |
backdrop | +0.120 |
GEAR | +0.118 |
Neg logit contributions | |
ochond | -0.117 |
Filip | -0.111 |
amily | -0.097 |
estine | -0.097 |
urers | -0.094 |
Token | Lovecraft |
Token ID | 37655 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
ochond | +0.032 |
Filip | +0.031 |
amily | +0.027 |
estine | +0.027 |
urers | +0.027 |
Neg logit contributions | |
═ | -0.033 |
DRAG | -0.029 |
backdrop | -0.027 |
Hour | -0.027 |
GEAR | -0.027 |
Token | might |
Token ID | 1244 |
Feature activation | +4.57e-03 |
Pos logit contributions | |
ochond | +1.482 |
Filip | +1.406 |
amily | +1.238 |
estine | +1.233 |
urers | +1.199 |
Neg logit contributions | |
═ | -1.812 |
DRAG | -1.619 |
Hour | -1.511 |
backdrop | -1.507 |
GEAR | -1.496 |
Token | have |
Token ID | 423 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
═ | +0.004 |
DRAG | +0.004 |
backdrop | +0.003 |
Hour | +0.003 |
GEAR | +0.003 |
Neg logit contributions | |
ochond | -0.004 |
Filip | -0.004 |
amily | -0.004 |
estine | -0.004 |
urers | -0.004 |
Token | seen |
Token ID | 1775 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ochond | +0.196 |
Filip | +0.186 |
amily | +0.166 |
estine | +0.166 |
urers | +0.162 |
Neg logit contributions | |
═ | -0.204 |
DRAG | -0.181 |
Hour | -0.168 |
backdrop | -0.168 |
GEAR | -0.166 |
Token | himself |
Token ID | 2241 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
═ | +0.115 |
DRAG | +0.101 |
Hour | +0.094 |
backdrop | +0.094 |
GEAR | +0.093 |
Neg logit contributions | |
ochond | -0.113 |
Filip | -0.107 |
amily | -0.096 |
estine | -0.096 |
urers | -0.093 |
Token | as |
Token ID | 355 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
ochond | +0.063 |
Filip | +0.060 |
amily | +0.054 |
estine | +0.053 |
urers | +0.052 |
Neg logit contributions | |
═ | -0.060 |
DRAG | -0.052 |
Hour | -0.049 |
backdrop | -0.048 |
GEAR | -0.048 |
Token | on |
Token ID | 319 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
═ | +0.198 |
DRAG | +0.175 |
Hour | +0.163 |
backdrop | +0.163 |
GEAR | +0.161 |
Neg logit contributions | |
ochond | -0.181 |
Filip | -0.172 |
amily | -0.153 |
estine | -0.152 |
urers | -0.148 |
Token | social |
Token ID | 1919 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
═ | +0.361 |
DRAG | +0.326 |
Hour | +0.307 |
backdrop | +0.306 |
GEAR | +0.303 |
Neg logit contributions | |
ochond | -0.243 |
Filip | -0.228 |
amily | -0.198 |
estine | -0.197 |
urers | -0.190 |
Token | issues |
Token ID | 2428 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
═ | +0.613 |
DRAG | +0.533 |
Hour | +0.490 |
backdrop | +0.490 |
GEAR | +0.481 |
Neg logit contributions | |
ochond | -0.766 |
Filip | -0.732 |
amily | -0.664 |
estine | -0.661 |
urers | -0.646 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
═ | +0.499 |
DRAG | +0.441 |
Hour | +0.410 |
backdrop | +0.409 |
GEAR | +0.404 |
Neg logit contributions | |
ochond | -0.479 |
Filip | -0.456 |
amily | -0.407 |
estine | -0.405 |
urers | -0.395 |
Token | ( |
Token ID | 357 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
═ | +0.236 |
DRAG | +0.209 |
Hour | +0.193 |
backdrop | +0.193 |
GEAR | +0.191 |
Neg logit contributions | |
ochond | -0.222 |
Filip | -0.212 |
amily | -0.188 |
estine | -0.188 |
urers | -0.183 |
Token | Photo |
Token ID | 6191 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
═ | +0.293 |
DRAG | +0.258 |
Hour | +0.239 |
backdrop | +0.238 |
GEAR | +0.235 |
Neg logit contributions | |
ochond | -0.307 |
Filip | -0.291 |
amily | -0.263 |
estine | -0.262 |
urers | -0.256 |
Token | by |
Token ID | 416 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
═ | +1.521 |
DRAG | +1.331 |
Hour | +1.248 |
backdrop | +1.246 |
GEAR | +1.221 |
Neg logit contributions | |
ochond | -1.677 |
Filip | -1.573 |
amily | -1.446 |
estine | -1.432 |
urers | -1.397 |
Token | REUTERS |
Token ID | 15862 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
═ | +0.814 |
DRAG | +0.719 |
Hour | +0.667 |
backdrop | +0.664 |
GEAR | +0.657 |
Neg logit contributions | |
ochond | -0.840 |
Filip | -0.797 |
amily | -0.718 |
estine | -0.715 |
urers | -0.697 |
Token | / |
Token ID | 14 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
═ | +0.854 |
DRAG | +0.739 |
backdrop | +0.675 |
Hour | +0.670 |
GEAR | +0.665 |
Neg logit contributions | |
ochond | -1.073 |
Filip | -1.038 |
estine | -0.927 |
amily | -0.925 |
urers | -0.905 |
Token | Gary |
Token ID | 33820 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
═ | +1.661 |
DRAG | +1.503 |
Hour | +1.443 |
backdrop | +1.410 |
GEAR | +1.400 |
Neg logit contributions | |
ochond | -0.951 |
Filip | -0.860 |
amily | -0.762 |
estine | -0.755 |
urers | -0.734 |
Token | Cameron |
Token ID | 10821 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
ochond | +0.092 |
Filip | +0.088 |
amily | +0.079 |
estine | +0.078 |
urers | +0.077 |
Neg logit contributions | |
═ | -0.085 |
DRAG | -0.074 |
Hour | -0.068 |
backdrop | -0.068 |
GEAR | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
═ | +0.311 |
DRAG | +0.276 |
Hour | +0.257 |
backdrop | +0.256 |
GEAR | +0.253 |
Neg logit contributions | |
ochond | -0.293 |
Filip | -0.279 |
amily | -0.249 |
estine | -0.248 |
urers | -0.242 |
Token | sheep |
Token ID | 15900 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
═ | +0.160 |
DRAG | +0.141 |
Hour | +0.130 |
backdrop | +0.130 |
GEAR | +0.129 |
Neg logit contributions | |
ochond | -0.159 |
Filip | -0.151 |
amily | -0.135 |
estine | -0.135 |
urers | -0.131 |
Token | a |
Token ID | 257 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
═ | +1.037 |
DRAG | +0.917 |
Hour | +0.854 |
backdrop | +0.851 |
GEAR | +0.842 |
Neg logit contributions | |
ochond | -0.997 |
Filip | -0.948 |
amily | -0.847 |
estine | -0.842 |
urers | -0.822 |
Token | minion |
Token ID | 28365 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
═ | +0.393 |
DRAG | +0.342 |
Hour | +0.314 |
backdrop | +0.313 |
GEAR | +0.310 |
Neg logit contributions | |
ochond | -0.458 |
Filip | -0.439 |
amily | -0.395 |
estine | -0.394 |
urers | -0.385 |
Token | was |
Token ID | 373 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
═ | +0.350 |
DRAG | +0.310 |
Hour | +0.289 |
backdrop | +0.288 |
GEAR | +0.285 |
Neg logit contributions | |
ochond | -0.329 |
Filip | -0.313 |
amily | -0.280 |
estine | -0.278 |
urers | -0.271 |
Token | super |
Token ID | 2208 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
═ | +0.648 |
DRAG | +0.573 |
Hour | +0.533 |
backdrop | +0.531 |
GEAR | +0.526 |
Neg logit contributions | |
ochond | -0.617 |
Filip | -0.587 |
amily | -0.523 |
estine | -0.521 |
urers | -0.508 |
Token | - |
Token ID | 12 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
═ | +1.896 |
DRAG | +1.668 |
Hour | +1.547 |
backdrop | +1.541 |
GEAR | +1.528 |
Neg logit contributions | |
ochond | -1.951 |
Filip | -1.861 |
amily | -1.668 |
estine | -1.661 |
urers | -1.622 |
Token | good |
Token ID | 11274 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
═ | +0.689 |
DRAG | +0.609 |
Hour | +0.567 |
backdrop | +0.564 |
GEAR | +0.560 |
Neg logit contributions | |
ochond | -0.652 |
Filip | -0.621 |
amily | -0.553 |
estine | -0.551 |
urers | -0.537 |
Token | if |
Token ID | 611 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
═ | +1.295 |
DRAG | +1.151 |
Hour | +1.078 |
backdrop | +1.075 |
GEAR | +1.065 |
Neg logit contributions | |
ochond | -1.108 |
Filip | -1.053 |
amily | -0.932 |
estine | -0.927 |
urers | -0.903 |
Token | you |
Token ID | 345 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
═ | +0.629 |
DRAG | +0.562 |
Hour | +0.527 |
backdrop | +0.525 |
GEAR | +0.520 |
Neg logit contributions | |
ochond | -0.505 |
Filip | -0.477 |
amily | -0.421 |
estine | -0.418 |
urers | -0.407 |
Token | got |
Token ID | 1392 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
═ | +0.501 |
DRAG | +0.440 |
Hour | +0.409 |
backdrop | +0.407 |
GEAR | +0.405 |
Neg logit contributions | |
ochond | -0.473 |
Filip | -0.454 |
estine | -0.400 |
amily | -0.398 |
fooled | -0.392 |
Token | � |
Token ID | 247 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
═ | +0.103 |
DRAG | +0.088 |
backdrop | +0.079 |
Hour | +0.078 |
GEAR | +0.077 |
Neg logit contributions | |
ochond | -0.171 |
Filip | -0.166 |
amily | -0.153 |
estine | -0.152 |
urers | -0.148 |
Token | t |
Token ID | 83 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
═ | +0.016 |
DRAG | +0.014 |
Hour | +0.013 |
backdrop | +0.013 |
GEAR | +0.013 |
Neg logit contributions | |
ochond | -0.016 |
Filip | -0.015 |
amily | -0.013 |
estine | -0.013 |
urers | -0.013 |
Token | stopped |
Token ID | 5025 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
═ | +0.227 |
DRAG | +0.201 |
Hour | +0.188 |
backdrop | +0.187 |
GEAR | +0.186 |
Neg logit contributions | |
ochond | -0.200 |
Filip | -0.190 |
amily | -0.169 |
estine | -0.168 |
urers | -0.164 |
Token | Sch |
Token ID | 3059 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
═ | +0.307 |
DRAG | +0.273 |
Hour | +0.254 |
backdrop | +0.253 |
GEAR | +0.251 |
Neg logit contributions | |
ochond | -0.281 |
Filip | -0.267 |
amily | -0.237 |
estine | -0.236 |
urers | -0.230 |
Token | um |
Token ID | 388 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
═ | +0.664 |
DRAG | +0.586 |
Hour | +0.542 |
backdrop | +0.541 |
GEAR | +0.536 |
Neg logit contributions | |
ochond | -0.666 |
Filip | -0.634 |
amily | -0.568 |
estine | -0.566 |
urers | -0.552 |
Token | acher |
Token ID | 3493 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
═ | +0.341 |
DRAG | +0.307 |
backdrop | +0.284 |
Hour | +0.284 |
GEAR | +0.281 |
Neg logit contributions | |
ochond | -0.278 |
Filip | -0.262 |
amily | -0.233 |
estine | -0.233 |
urers | -0.228 |
Token | from |
Token ID | 422 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
═ | +2.005 |
DRAG | +1.789 |
Hour | +1.696 |
backdrop | +1.688 |
GEAR | +1.669 |
Neg logit contributions | |
ochond | -1.384 |
Filip | -1.298 |
estine | -1.132 |
amily | -1.129 |
urers | -1.098 |
Token | asking |
Token ID | 4737 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
═ | +0.290 |
DRAG | +0.252 |
Hour | +0.231 |
backdrop | +0.231 |
GEAR | +0.229 |
Neg logit contributions | |
ochond | -0.347 |
Filip | -0.333 |
amily | -0.300 |
estine | -0.298 |
urers | -0.291 |
Token | .) |
Token ID | 2014 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
═ | +0.266 |
DRAG | +0.236 |
Hour | +0.220 |
backdrop | +0.219 |
GEAR | +0.217 |
Neg logit contributions | |
ochond | -0.250 |
Filip | -0.238 |
amily | -0.212 |
estine | -0.211 |
urers | -0.206 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ochond | +0.453 |
Filip | +0.434 |
amily | +0.383 |
estine | +0.382 |
urers | +0.371 |
Neg logit contributions | |
═ | -0.496 |
DRAG | -0.439 |
backdrop | -0.407 |
Hour | -0.407 |
GEAR | -0.404 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ochond | +0.091 |
Filip | +0.085 |
estine | +0.071 |
amily | +0.071 |
urers | +0.068 |
Neg logit contributions | |
═ | -0.170 |
DRAG | -0.155 |
Hour | -0.146 |
backdrop | -0.145 |
GEAR | -0.145 |
Token | series |
Token ID | 2168 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
═ | +0.045 |
DRAG | +0.038 |
backdrop | +0.034 |
GEAR | +0.034 |
Hour | +0.033 |
Neg logit contributions | |
ochond | -0.065 |
Filip | -0.063 |
estine | -0.057 |
amily | -0.057 |
urers | -0.056 |
Token | Natural |
Token ID | 12068 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
═ | +0.485 |
DRAG | +0.419 |
Hour | +0.384 |
backdrop | +0.383 |
GEAR | +0.379 |
Neg logit contributions | |
ochond | -0.598 |
Filip | -0.574 |
amily | -0.518 |
estine | -0.517 |
urers | -0.505 |
Token | World |
Token ID | 2159 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
═ | +0.513 |
DRAG | +0.447 |
Hour | +0.406 |
backdrop | +0.405 |
GEAR | +0.403 |
Neg logit contributions | |
ochond | -0.572 |
Filip | -0.551 |
estine | -0.493 |
amily | -0.491 |
urers | -0.482 |
Token | episode |
Token ID | 4471 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
═ | +0.870 |
DRAG | +0.773 |
Hour | +0.723 |
backdrop | +0.719 |
GEAR | +0.713 |
Neg logit contributions | |
ochond | -0.769 |
Filip | -0.730 |
amily | -0.648 |
estine | -0.644 |
urers | -0.629 |
Token | " |
Token ID | 366 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
═ | +1.054 |
DRAG | +0.926 |
Hour | +0.857 |
backdrop | +0.853 |
GEAR | +0.845 |
Neg logit contributions | |
ochond | -1.124 |
Filip | -1.073 |
amily | -0.963 |
estine | -0.959 |
urers | -0.937 |
Token | Snow |
Token ID | 28974 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
═ | +0.308 |
DRAG | +0.278 |
Hour | +0.263 |
backdrop | +0.261 |
GEAR | +0.259 |
Neg logit contributions | |
ochond | -0.197 |
Filip | -0.184 |
amily | -0.159 |
estine | -0.158 |
urers | -0.153 |
Token | Leopard |
Token ID | 49072 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
═ | +1.499 |
DRAG | +1.300 |
Hour | +1.197 |
backdrop | +1.186 |
GEAR | +1.172 |
Neg logit contributions | |
ochond | -1.991 |
Filip | -1.903 |
amily | -1.736 |
estine | -1.724 |
urers | -1.691 |
Token | – |
Token ID | 784 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
═ | +1.649 |
DRAG | +1.449 |
Hour | +1.344 |
backdrop | +1.336 |
GEAR | +1.323 |
Neg logit contributions | |
ochond | -1.780 |
Filip | -1.696 |
amily | -1.526 |
estine | -1.519 |
urers | -1.485 |
Token | Beyond |
Token ID | 12197 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
═ | +0.030 |
DRAG | +0.026 |
Hour | +0.024 |
backdrop | +0.024 |
GEAR | +0.023 |
Neg logit contributions | |
ochond | -0.035 |
Filip | -0.034 |
amily | -0.030 |
estine | -0.030 |
urers | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
═ | +0.556 |
DRAG | +0.488 |
Hour | +0.452 |
backdrop | +0.450 |
GEAR | +0.446 |
Neg logit contributions | |
ochond | -0.591 |
Filip | -0.564 |
amily | -0.506 |
estine | -0.504 |
urers | -0.492 |
Token | Myth |
Token ID | 18900 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
═ | +0.257 |
DRAG | +0.219 |
GEAR | +0.196 |
Hour | +0.195 |
backdrop | +0.195 |
Neg logit contributions | |
ochond | -0.366 |
Filip | -0.354 |
estine | -0.320 |
amily | -0.320 |
urers | -0.313 |
Token | so |
Token ID | 523 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
═ | +0.306 |
DRAG | +0.270 |
Hour | +0.252 |
backdrop | +0.251 |
GEAR | +0.248 |
Neg logit contributions | |
ochond | -0.296 |
Filip | -0.282 |
amily | -0.251 |
estine | -0.251 |
urers | -0.244 |
Token | he |
Token ID | 339 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
═ | +0.223 |
DRAG | +0.198 |
Hour | +0.185 |
backdrop | +0.184 |
GEAR | +0.183 |
Neg logit contributions | |
ochond | -0.192 |
Filip | -0.182 |
amily | -0.161 |
estine | -0.160 |
urers | -0.156 |
Token | 's |
Token ID | 338 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
═ | +0.273 |
DRAG | +0.242 |
Hour | +0.225 |
backdrop | +0.225 |
GEAR | +0.222 |
Neg logit contributions | |
ochond | -0.245 |
Filip | -0.233 |
amily | -0.207 |
estine | -0.206 |
urers | -0.201 |
Token | kicking |
Token ID | 17997 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
═ | +0.600 |
DRAG | +0.527 |
Hour | +0.488 |
backdrop | +0.487 |
GEAR | +0.481 |
Neg logit contributions | |
ochond | -0.637 |
Filip | -0.607 |
amily | -0.546 |
estine | -0.544 |
urers | -0.531 |
Token | and |
Token ID | 290 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
═ | +0.469 |
DRAG | +0.417 |
backdrop | +0.390 |
Hour | +0.390 |
GEAR | +0.384 |
Neg logit contributions | |
ochond | -0.412 |
Filip | -0.388 |
amily | -0.347 |
estine | -0.346 |
urers | -0.336 |
Token | tw |
Token ID | 665 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
═ | +0.201 |
DRAG | +0.180 |
Hour | +0.169 |
backdrop | +0.168 |
GEAR | +0.167 |
Neg logit contributions | |
ochond | -0.150 |
Filip | -0.142 |
amily | -0.124 |
estine | -0.123 |
urers | -0.119 |
Token | itching |
Token ID | 19811 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
═ | +1.987 |
DRAG | +1.783 |
Hour | +1.714 |
GEAR | +1.678 |
backdrop | +1.676 |
Neg logit contributions | |
ochond | -1.388 |
Filip | -1.312 |
estine | -1.147 |
amily | -1.124 |
fooled | -1.104 |
Token | away |
Token ID | 1497 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
═ | +1.363 |
DRAG | +1.207 |
Hour | +1.125 |
backdrop | +1.122 |
GEAR | +1.110 |
Neg logit contributions | |
ochond | -1.276 |
Filip | -1.212 |
amily | -1.082 |
estine | -1.077 |
urers | -1.049 |
Token | . |
Token ID | 13 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
ochond | +0.230 |
Filip | +0.219 |
amily | +0.194 |
estine | +0.194 |
urers | +0.189 |
Neg logit contributions | |
═ | -0.254 |
DRAG | -0.226 |
Hour | -0.210 |
backdrop | -0.209 |
GEAR | -0.207 |
Token | There |
Token ID | 1318 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
═ | +0.238 |
DRAG | +0.212 |
backdrop | +0.198 |
Hour | +0.198 |
GEAR | +0.196 |
Neg logit contributions | |
ochond | -0.201 |
Filip | -0.192 |
amily | -0.169 |
estine | -0.168 |
urers | -0.163 |
Token | 's |
Token ID | 338 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
ochond | +0.040 |
Filip | +0.038 |
estine | +0.034 |
amily | +0.034 |
urers | +0.033 |
Neg logit contributions | |
═ | -0.040 |
DRAG | -0.035 |
backdrop | -0.032 |
Hour | -0.032 |
GEAR | -0.032 |
Token | Bitcoin |
Token ID | 6185 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
═ | +0.070 |
DRAG | +0.061 |
Hour | +0.056 |
backdrop | +0.056 |
GEAR | +0.055 |
Neg logit contributions | |
ochond | -0.078 |
Filip | -0.074 |
amily | -0.067 |
estine | -0.066 |
urers | -0.065 |
Token | Core |
Token ID | 7231 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
═ | +0.102 |
DRAG | +0.089 |
Hour | +0.083 |
backdrop | +0.083 |
GEAR | +0.082 |
Neg logit contributions | |
ochond | -0.105 |
Filip | -0.101 |
amily | -0.090 |
estine | -0.090 |
urers | -0.088 |
Token | we |
Token ID | 356 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ochond | +0.506 |
Filip | +0.482 |
amily | +0.428 |
estine | +0.427 |
urers | +0.416 |
Neg logit contributions | |
═ | -0.542 |
DRAG | -0.480 |
Hour | -0.447 |
backdrop | -0.445 |
GEAR | -0.441 |
Token | should |
Token ID | 815 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
═ | +0.534 |
DRAG | +0.471 |
Hour | +0.436 |
backdrop | +0.434 |
GEAR | +0.430 |
Neg logit contributions | |
ochond | -0.546 |
Filip | -0.521 |
amily | -0.466 |
estine | -0.465 |
urers | -0.454 |
Token | keep |
Token ID | 1394 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
═ | +0.213 |
DRAG | +0.186 |
Hour | +0.172 |
backdrop | +0.170 |
GEAR | +0.169 |
Neg logit contributions | |
ochond | -0.226 |
Filip | -0.216 |
estine | -0.193 |
amily | -0.192 |
urers | -0.188 |
Token | patches |
Token ID | 16082 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
═ | +0.303 |
DRAG | +0.266 |
Hour | +0.246 |
backdrop | +0.245 |
GEAR | +0.243 |
Neg logit contributions | |
ochond | -0.327 |
Filip | -0.312 |
amily | -0.280 |
estine | -0.279 |
urers | -0.273 |
Token | ready |
Token ID | 3492 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
═ | +0.694 |
DRAG | +0.610 |
Hour | +0.564 |
backdrop | +0.562 |
GEAR | +0.557 |
Neg logit contributions | |
ochond | -0.728 |
Filip | -0.695 |
amily | -0.623 |
estine | -0.621 |
urers | -0.606 |
Token | to |
Token ID | 284 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ochond | +0.580 |
Filip | +0.553 |
amily | +0.490 |
estine | +0.489 |
urers | +0.476 |
Neg logit contributions | |
═ | -0.634 |
DRAG | -0.563 |
Hour | -0.521 |
backdrop | -0.520 |
GEAR | -0.516 |
Token | implement |
Token ID | 3494 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
═ | +0.012 |
DRAG | +0.010 |
Hour | +0.009 |
backdrop | +0.009 |
GEAR | +0.009 |
Neg logit contributions | |
ochond | -0.013 |
Filip | -0.013 |
amily | -0.011 |
estine | -0.011 |
urers | -0.011 |
Token | them |
Token ID | 606 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
ochond | +0.119 |
Filip | +0.114 |
amily | +0.101 |
estine | +0.101 |
urers | +0.098 |
Neg logit contributions | |
═ | -0.121 |
DRAG | -0.107 |
Hour | -0.099 |
backdrop | -0.099 |
GEAR | -0.098 |
Token | as |
Token ID | 355 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ochond | +0.331 |
Filip | +0.316 |
amily | +0.280 |
estine | +0.280 |
urers | +0.273 |
Neg logit contributions | |
═ | -0.355 |
DRAG | -0.314 |
Hour | -0.291 |
backdrop | -0.291 |
GEAR | -0.288 |
Token | number |
Token ID | 1271 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
═ | +0.079 |
DRAG | +0.068 |
Hour | +0.062 |
backdrop | +0.062 |
GEAR | +0.061 |
Neg logit contributions | |
ochond | -0.100 |
Filip | -0.097 |
estine | -0.087 |
amily | -0.087 |
urers | -0.085 |
Token | of |
Token ID | 286 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
ochond | +0.318 |
Filip | +0.306 |
amily | +0.280 |
estine | +0.278 |
urers | +0.272 |
Neg logit contributions | |
═ | -0.227 |
DRAG | -0.195 |
Hour | -0.178 |
backdrop | -0.176 |
GEAR | -0.174 |
Token | points |
Token ID | 2173 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ochond | +0.018 |
Filip | +0.017 |
amily | +0.015 |
estine | +0.015 |
urers | +0.015 |
Neg logit contributions | |
═ | -0.015 |
DRAG | -0.013 |
backdrop | -0.012 |
Hour | -0.012 |
GEAR | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
ochond | +0.182 |
Filip | +0.173 |
amily | +0.155 |
estine | +0.154 |
urers | +0.151 |
Neg logit contributions | |
═ | -0.184 |
DRAG | -0.163 |
Hour | -0.151 |
backdrop | -0.151 |
GEAR | -0.149 |
Token | user |
Token ID | 2836 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
ochond | +0.067 |
Filip | +0.064 |
amily | +0.057 |
estine | +0.057 |
urers | +0.055 |
Neg logit contributions | |
═ | -0.073 |
DRAG | -0.065 |
Hour | -0.060 |
backdrop | -0.060 |
GEAR | -0.060 |
Token | earned |
Token ID | 7366 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
ochond | +0.493 |
Filip | +0.473 |
estine | +0.425 |
amily | +0.425 |
urers | +0.415 |
Neg logit contributions | |
═ | -0.406 |
DRAG | -0.352 |
backdrop | -0.322 |
Hour | -0.321 |
GEAR | -0.318 |
Token | in |
Token ID | 287 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
═ | +0.342 |
DRAG | +0.303 |
Hour | +0.282 |
backdrop | +0.281 |
GEAR | +0.279 |
Neg logit contributions | |
ochond | -0.319 |
Filip | -0.304 |
amily | -0.271 |
estine | -0.269 |
urers | -0.263 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
═ | +0.010 |
DRAG | +0.009 |
Hour | +0.008 |
backdrop | +0.008 |
GEAR | +0.008 |
Neg logit contributions | |
ochond | -0.010 |
Filip | -0.010 |
amily | -0.009 |
estine | -0.009 |
urers | -0.009 |
Token | past |
Token ID | 1613 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
═ | +0.146 |
DRAG | +0.129 |
Hour | +0.119 |
backdrop | +0.119 |
GEAR | +0.118 |
Neg logit contributions | |
ochond | -0.145 |
Filip | -0.138 |
amily | -0.123 |
estine | -0.123 |
urers | -0.120 |
Token | seven |
Token ID | 3598 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
ochond | +0.012 |
Filip | +0.012 |
amily | +0.010 |
estine | +0.010 |
urers | +0.010 |
Neg logit contributions | |
═ | -0.015 |
DRAG | -0.013 |
Hour | -0.012 |
backdrop | -0.012 |
GEAR | -0.012 |
Token | days |
Token ID | 1528 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
═ | +0.053 |
DRAG | +0.044 |
Hour | +0.040 |
backdrop | +0.039 |
GEAR | +0.039 |
Neg logit contributions | |
ochond | -0.094 |
Filip | -0.091 |
amily | -0.084 |
estine | -0.083 |
urers | -0.082 |
Token | Y |
Token ID | 575 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ochond | +0.326 |
Filip | +0.312 |
estine | +0.275 |
amily | +0.274 |
urers | +0.266 |
Neg logit contributions | |
═ | -0.369 |
DRAG | -0.326 |
Hour | -0.304 |
backdrop | -0.303 |
GEAR | -0.301 |
Token | anda |
Token ID | 5282 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
═ | +0.155 |
DRAG | +0.141 |
Hour | +0.134 |
backdrop | +0.133 |
GEAR | +0.132 |
Neg logit contributions | |
ochond | -0.098 |
Filip | -0.092 |
amily | -0.081 |
estine | -0.078 |
urers | -0.077 |
Token | — |
Token ID | 851 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ochond | +0.365 |
Filip | +0.342 |
amily | +0.302 |
estine | +0.299 |
urers | +0.292 |
Neg logit contributions | |
═ | -0.478 |
DRAG | -0.426 |
Hour | -0.402 |
backdrop | -0.399 |
GEAR | -0.396 |
Token | per |
Token ID | 583 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
═ | +0.107 |
DRAG | +0.094 |
Hour | +0.087 |
backdrop | +0.087 |
GEAR | +0.086 |
Neg logit contributions | |
ochond | -0.112 |
Filip | -0.106 |
amily | -0.095 |
estine | -0.095 |
urers | -0.093 |
Token | Pro |
Token ID | 1041 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
ochond | +0.057 |
Filip | +0.054 |
amily | +0.049 |
estine | +0.049 |
urers | +0.048 |
Neg logit contributions | |
═ | -0.048 |
DRAG | -0.042 |
backdrop | -0.038 |
Hour | -0.038 |
GEAR | -0.038 |
Token | Football |
Token ID | 9957 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
ochond | +0.380 |
Filip | +0.368 |
amily | +0.335 |
estine | +0.334 |
urers | +0.327 |
Neg logit contributions | |
═ | -0.245 |
DRAG | -0.208 |
backdrop | -0.186 |
Hour | -0.185 |
GEAR | -0.184 |
Token | Focus |
Token ID | 17061 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
═ | +0.431 |
DRAG | +0.360 |
Hour | +0.321 |
backdrop | +0.320 |
GEAR | +0.315 |
Neg logit contributions | |
ochond | -0.745 |
Filip | -0.720 |
amily | -0.659 |
estine | -0.658 |
urers | -0.644 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ochond | +0.119 |
Filip | +0.112 |
amily | +0.099 |
estine | +0.098 |
urers | +0.096 |
Neg logit contributions | |
═ | -0.143 |
DRAG | -0.127 |
Hour | -0.120 |
backdrop | -0.119 |
GEAR | -0.118 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
═ | +0.129 |
DRAG | +0.114 |
Hour | +0.106 |
backdrop | +0.106 |
GEAR | +0.105 |
Neg logit contributions | |
ochond | -0.120 |
Filip | -0.113 |
amily | -0.101 |
estine | -0.101 |
urers | -0.099 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ochond | +0.076 |
Filip | +0.072 |
estine | +0.060 |
amily | +0.060 |
urers | +0.057 |
Neg logit contributions | |
═ | -0.143 |
DRAG | -0.130 |
Hour | -0.123 |
backdrop | -0.123 |
GEAR | -0.122 |
Token | A |
Token ID | 32 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ochond | +0.082 |
Filip | +0.077 |
amily | +0.067 |
estine | +0.067 |
urers | +0.065 |
Neg logit contributions | |
═ | -0.118 |
DRAG | -0.105 |
Hour | -0.099 |
backdrop | -0.099 |
GEAR | -0.099 |
Token | ured |
Token ID | 1522 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
ochond | +0.031 |
Filip | +0.029 |
amily | +0.025 |
estine | +0.024 |
urers | +0.024 |
Neg logit contributions | |
═ | -0.058 |
DRAG | -0.053 |
Hour | -0.050 |
backdrop | -0.050 |
GEAR | -0.050 |
Token | ) |
Token ID | 8 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
ochond | +0.357 |
Filip | +0.341 |
amily | +0.302 |
estine | +0.301 |
urers | +0.293 |
Neg logit contributions | |
═ | -0.392 |
DRAG | -0.348 |
Hour | -0.323 |
backdrop | -0.322 |
GEAR | -0.319 |
Token | would |
Token ID | 561 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
ochond | +0.253 |
Filip | +0.241 |
amily | +0.216 |
estine | +0.215 |
urers | +0.210 |
Neg logit contributions | |
═ | -0.242 |
DRAG | -0.213 |
Hour | -0.197 |
backdrop | -0.196 |
GEAR | -0.194 |
Token | be |
Token ID | 307 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
═ | +0.166 |
DRAG | +0.145 |
Hour | +0.134 |
backdrop | +0.133 |
GEAR | +0.132 |
Neg logit contributions | |
ochond | -0.182 |
Filip | -0.174 |
amily | -0.156 |
estine | -0.155 |
urers | -0.152 |
Token | an |
Token ID | 281 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
═ | +0.142 |
DRAG | +0.125 |
Hour | +0.115 |
backdrop | +0.115 |
GEAR | +0.114 |
Neg logit contributions | |
ochond | -0.149 |
Filip | -0.143 |
amily | -0.128 |
estine | -0.128 |
urers | -0.125 |
Token | al |
Token ID | 435 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
═ | +0.111 |
DRAG | +0.094 |
Hour | +0.085 |
backdrop | +0.085 |
GEAR | +0.084 |
Neg logit contributions | |
ochond | -0.162 |
Filip | -0.156 |
amily | -0.142 |
estine | -0.142 |
urers | -0.139 |
Token | bat |
Token ID | 8664 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
═ | +0.534 |
DRAG | +0.483 |
Hour | +0.458 |
backdrop | +0.456 |
GEAR | +0.452 |
Neg logit contributions | |
ochond | -0.333 |
Filip | -0.313 |
amily | -0.271 |
estine | -0.267 |
urers | -0.263 |
Token | ross |
Token ID | 1214 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
ochond | +0.081 |
Filip | +0.076 |
estine | +0.065 |
amily | +0.065 |
urers | +0.063 |
Neg logit contributions | |
═ | -0.124 |
DRAG | -0.112 |
Hour | -0.105 |
backdrop | -0.105 |
GEAR | -0.104 |
Token | on |
Token ID | 319 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
═ | +0.447 |
DRAG | +0.397 |
Hour | +0.370 |
backdrop | +0.369 |
GEAR | +0.366 |
Neg logit contributions | |
ochond | -0.395 |
Filip | -0.375 |
amily | -0.332 |
estine | -0.331 |
urers | -0.322 |
Token | Miami |
Token ID | 8437 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
═ | +0.160 |
DRAG | +0.142 |
Hour | +0.132 |
backdrop | +0.132 |
GEAR | +0.131 |
Neg logit contributions | |
ochond | -0.153 |
Filip | -0.145 |
estine | -0.130 |
amily | -0.130 |
urers | -0.126 |
Token | � |
Token ID | 447 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ochond | +0.695 |
Filip | +0.662 |
amily | +0.591 |
estine | +0.589 |
urers | +0.576 |
Neg logit contributions | |
═ | -0.691 |
DRAG | -0.608 |
Hour | -0.565 |
backdrop | -0.563 |
GEAR | -0.558 |
Token | good |
Token ID | 922 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
═ | +0.247 |
DRAG | +0.215 |
Hour | +0.199 |
backdrop | +0.198 |
GEAR | +0.197 |
Neg logit contributions | |
ochond | -0.234 |
Filip | -0.225 |
amily | -0.199 |
estine | -0.198 |
urers | -0.194 |
Token | week |
Token ID | 1285 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
═ | +0.213 |
DRAG | +0.183 |
Hour | +0.167 |
GEAR | +0.165 |
backdrop | +0.165 |
Neg logit contributions | |
ochond | -0.263 |
Filip | -0.253 |
estine | -0.228 |
amily | -0.227 |
urers | -0.222 |
Token | to |
Token ID | 284 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
ochond | +0.138 |
Filip | +0.131 |
amily | +0.116 |
estine | +0.116 |
urers | +0.113 |
Neg logit contributions | |
═ | -0.155 |
DRAG | -0.137 |
Hour | -0.128 |
backdrop | -0.127 |
GEAR | -0.126 |
Token | trust |
Token ID | 3774 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
═ | +0.047 |
DRAG | +0.040 |
Hour | +0.037 |
backdrop | +0.037 |
GEAR | +0.037 |
Neg logit contributions | |
ochond | -0.053 |
Filip | -0.051 |
amily | -0.045 |
estine | -0.045 |
fooled | -0.044 |
Token | him |
Token ID | 683 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ochond | +0.143 |
Filip | +0.135 |
amily | +0.120 |
estine | +0.120 |
urers | +0.116 |
Neg logit contributions | |
═ | -0.167 |
DRAG | -0.149 |
Hour | -0.139 |
backdrop | -0.139 |
GEAR | -0.138 |
Token | given |
Token ID | 1813 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
ochond | +0.105 |
Filip | +0.099 |
amily | +0.088 |
estine | +0.087 |
urers | +0.085 |
Neg logit contributions | |
═ | -0.124 |
DRAG | -0.111 |
Hour | -0.104 |
backdrop | -0.103 |
GEAR | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
═ | +0.556 |
DRAG | +0.492 |
Hour | +0.458 |
backdrop | +0.456 |
GEAR | +0.450 |
Neg logit contributions | |
ochond | -0.562 |
Filip | -0.533 |
amily | -0.480 |
estine | -0.477 |
urers | -0.465 |
Token | matchup |
Token ID | 18406 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
═ | +0.128 |
DRAG | +0.109 |
Hour | +0.099 |
GEAR | +0.098 |
backdrop | +0.098 |
Neg logit contributions | |
ochond | -0.166 |
Filip | -0.160 |
estine | -0.143 |
amily | -0.143 |
urers | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
═ | +0.258 |
DRAG | +0.229 |
Hour | +0.214 |
backdrop | +0.212 |
GEAR | +0.211 |
Neg logit contributions | |
ochond | -0.219 |
Filip | -0.209 |
amily | -0.184 |
estine | -0.183 |
urers | -0.179 |
Token |
|
Token ID | 198 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
═ | +0.152 |
DRAG | +0.136 |
Hour | +0.128 |
backdrop | +0.128 |
GEAR | +0.127 |
Neg logit contributions | |
ochond | -0.110 |
Filip | -0.103 |
amily | -0.090 |
estine | -0.090 |
urers | -0.087 |
Token |
|
Token ID | 198 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
═ | +0.101 |
DRAG | +0.092 |
Hour | +0.086 |
backdrop | +0.086 |
GEAR | +0.086 |
Neg logit contributions | |
ochond | -0.054 |
Filip | -0.051 |
estine | -0.042 |
amily | -0.042 |
urers | -0.041 |
Token | ä |
Token ID | 11033 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ochond | +0.066 |
Filip | +0.062 |
amily | +0.055 |
estine | +0.055 |
urers | +0.054 |
Neg logit contributions | |
═ | -0.071 |
DRAG | -0.063 |
Hour | -0.058 |
backdrop | -0.058 |
GEAR | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
═ | +0.242 |
DRAG | +0.214 |
Hour | +0.198 |
backdrop | +0.197 |
GEAR | +0.196 |
Neg logit contributions | |
ochond | -0.238 |
Filip | -0.227 |
amily | -0.203 |
estine | -0.202 |
urers | -0.197 |
Token | E |
Token ID | 412 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
═ | +0.058 |
DRAG | +0.051 |
Hour | +0.048 |
backdrop | +0.048 |
GEAR | +0.047 |
Neg logit contributions | |
ochond | -0.056 |
Filip | -0.053 |
amily | -0.048 |
estine | -0.047 |
urers | -0.046 |
Token | e |
Token ID | 68 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
═ | +0.327 |
DRAG | +0.292 |
Hour | +0.275 |
backdrop | +0.272 |
GEAR | +0.270 |
Neg logit contributions | |
ochond | -0.258 |
Filip | -0.243 |
amily | -0.214 |
estine | -0.212 |
urers | -0.206 |
Token | pp |
Token ID | 381 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ochond | +0.035 |
Filip | +0.033 |
amily | +0.029 |
estine | +0.029 |
urers | +0.028 |
Neg logit contributions | |
═ | -0.044 |
DRAG | -0.040 |
Hour | -0.037 |
backdrop | -0.037 |
GEAR | -0.037 |
Token | i |
Token ID | 72 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
ochond | +0.638 |
Filip | +0.608 |
amily | +0.534 |
estine | +0.531 |
urers | +0.516 |
Neg logit contributions | |
═ | -0.798 |
DRAG | -0.712 |
Hour | -0.665 |
backdrop | -0.664 |
GEAR | -0.659 |
Token | Urs |
Token ID | 37935 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ochond | +0.673 |
Filip | +0.644 |
amily | +0.575 |
estine | +0.572 |
urers | +0.559 |
Neg logit contributions | |
═ | -0.669 |
DRAG | -0.589 |
Hour | -0.545 |
backdrop | -0.544 |
GEAR | -0.539 |
Token | in |
Token ID | 259 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
═ | +0.241 |
DRAG | +0.216 |
Hour | +0.203 |
backdrop | +0.202 |
GEAR | +0.200 |
Neg logit contributions | |
ochond | -0.182 |
Filip | -0.172 |
amily | -0.151 |
estine | -0.150 |
urers | -0.146 |
Token | .[ |
Token ID | 3693 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ochond | +0.061 |
Filip | +0.058 |
amily | +0.051 |
estine | +0.051 |
urers | +0.049 |
Neg logit contributions | |
═ | -0.070 |
DRAG | -0.062 |
Hour | -0.058 |
backdrop | -0.058 |
GEAR | -0.057 |
Token | 25 |
Token ID | 1495 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
ochond | +0.168 |
Filip | +0.159 |
amily | +0.140 |
estine | +0.140 |
urers | +0.137 |
Neg logit contributions | |
═ | -0.196 |
DRAG | -0.174 |
Hour | -0.163 |
backdrop | -0.162 |
GEAR | -0.161 |
Token | ] |
Token ID | 60 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
═ | +0.686 |
DRAG | +0.620 |
Hour | +0.585 |
backdrop | +0.583 |
GEAR | +0.577 |
Neg logit contributions | |
ochond | -0.425 |
Filip | -0.398 |
amily | -0.342 |
estine | -0.341 |
urers | -0.333 |
Token | joint |
Token ID | 6466 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
═ | +0.036 |
DRAG | +0.032 |
Hour | +0.030 |
backdrop | +0.029 |
GEAR | +0.029 |
Neg logit contributions | |
ochond | -0.036 |
Filip | -0.035 |
amily | -0.031 |
estine | -0.031 |
urers | -0.030 |
Token | statement |
Token ID | 2643 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
═ | +0.565 |
DRAG | +0.481 |
Hour | +0.435 |
backdrop | +0.431 |
GEAR | +0.429 |
Neg logit contributions | |
ochond | -0.835 |
Filip | -0.806 |
amily | -0.731 |
estine | -0.730 |
urers | -0.715 |
Token | on |
Token ID | 319 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
═ | +0.287 |
DRAG | +0.252 |
Hour | +0.232 |
backdrop | +0.232 |
GEAR | +0.229 |
Neg logit contributions | |
ochond | -0.315 |
Filip | -0.301 |
amily | -0.271 |
estine | -0.270 |
urers | -0.264 |
Token | Wednesday |
Token ID | 3583 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
═ | +0.116 |
DRAG | +0.099 |
Hour | +0.090 |
backdrop | +0.090 |
GEAR | +0.089 |
Neg logit contributions | |
ochond | -0.166 |
Filip | -0.160 |
amily | -0.145 |
estine | -0.145 |
urers | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
═ | +0.227 |
DRAG | +0.201 |
Hour | +0.187 |
backdrop | +0.186 |
GEAR | +0.184 |
Neg logit contributions | |
ochond | -0.222 |
Filip | -0.210 |
amily | -0.188 |
estine | -0.187 |
urers | -0.183 |
Token |
|
Token ID | 198 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
ochond | +0.022 |
Filip | +0.020 |
amily | +0.018 |
estine | +0.018 |
urers | +0.017 |
Neg logit contributions | |
═ | -0.036 |
DRAG | -0.032 |
Hour | -0.031 |
backdrop | -0.030 |
GEAR | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
ochond | +0.043 |
Filip | +0.041 |
estine | +0.034 |
amily | +0.034 |
urers | +0.033 |
Neg logit contributions | |
═ | -0.081 |
DRAG | -0.074 |
Hour | -0.069 |
backdrop | -0.069 |
GEAR | -0.069 |
Token | " |
Token ID | 1 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ochond | +0.057 |
Filip | +0.053 |
amily | +0.047 |
estine | +0.047 |
urers | +0.046 |
Neg logit contributions | |
═ | -0.076 |
DRAG | -0.068 |
Hour | -0.064 |
backdrop | -0.064 |
GEAR | -0.063 |
Token | Japan |
Token ID | 16504 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
ochond | +0.106 |
Filip | +0.097 |
amily | +0.084 |
estine | +0.084 |
urers | +0.081 |
Neg logit contributions | |
═ | -0.177 |
DRAG | -0.160 |
Hour | -0.152 |
backdrop | -0.151 |
GEAR | -0.150 |
Token | 's |
Token ID | 338 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ochond | +0.672 |
Filip | +0.640 |
amily | +0.570 |
estine | +0.568 |
urers | +0.554 |
Neg logit contributions | |
═ | -0.711 |
DRAG | -0.629 |
Hour | -0.585 |
backdrop | -0.583 |
GEAR | -0.578 |
Token | official |
Token ID | 1743 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
ochond | +0.364 |
Filip | +0.351 |
amily | +0.315 |
estine | +0.314 |
urers | +0.307 |
Neg logit contributions | |
═ | -0.304 |
DRAG | -0.263 |
Hour | -0.241 |
backdrop | -0.240 |
GEAR | -0.238 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ochond | +0.060 |
Filip | +0.057 |
amily | +0.051 |
estine | +0.051 |
urers | +0.050 |
Neg logit contributions | |
═ | -0.056 |
DRAG | -0.049 |
Hour | -0.045 |
backdrop | -0.045 |
GEAR | -0.045 |
Token | car |
Token ID | 1097 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
═ | +0.098 |
DRAG | +0.084 |
Hour | +0.076 |
backdrop | +0.076 |
GEAR | +0.076 |
Neg logit contributions | |
ochond | -0.123 |
Filip | -0.119 |
amily | -0.107 |
estine | -0.106 |
urers | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
ochond | +0.361 |
Filip | +0.345 |
amily | +0.303 |
estine | +0.302 |
urers | +0.294 |
Neg logit contributions | |
═ | -0.439 |
DRAG | -0.392 |
Hour | -0.363 |
backdrop | -0.362 |
GEAR | -0.360 |
Token | Then |
Token ID | 3244 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
ochond | +0.025 |
Filip | +0.023 |
amily | +0.020 |
estine | +0.020 |
urers | +0.020 |
Neg logit contributions | |
═ | -0.035 |
DRAG | -0.031 |
Hour | -0.029 |
backdrop | -0.029 |
GEAR | -0.029 |
Token | we |
Token ID | 356 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
═ | +0.053 |
DRAG | +0.047 |
Hour | +0.044 |
backdrop | +0.044 |
GEAR | +0.044 |
Neg logit contributions | |
ochond | -0.048 |
Filip | -0.045 |
amily | -0.040 |
estine | -0.040 |
urers | -0.039 |
Token | had |
Token ID | 550 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
═ | +0.264 |
DRAG | +0.234 |
Hour | +0.218 |
backdrop | +0.217 |
GEAR | +0.216 |
Neg logit contributions | |
ochond | -0.226 |
Filip | -0.216 |
amily | -0.190 |
estine | -0.189 |
urers | -0.184 |
Token | a |
Token ID | 257 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ochond | +0.213 |
Filip | +0.201 |
amily | +0.181 |
estine | +0.180 |
urers | +0.175 |
Neg logit contributions | |
═ | -0.228 |
DRAG | -0.203 |
Hour | -0.190 |
backdrop | -0.188 |
GEAR | -0.186 |
Token | little |
Token ID | 1310 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
═ | +0.012 |
DRAG | +0.010 |
Hour | +0.009 |
backdrop | +0.009 |
GEAR | +0.009 |
Neg logit contributions | |
ochond | -0.013 |
Filip | -0.012 |
amily | -0.011 |
estine | -0.011 |
urers | -0.011 |
Token | issue |
Token ID | 2071 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
═ | +0.224 |
DRAG | +0.192 |
Hour | +0.175 |
backdrop | +0.175 |
GEAR | +0.173 |
Neg logit contributions | |
ochond | -0.299 |
Filip | -0.288 |
amily | -0.261 |
estine | -0.260 |
urers | -0.255 |
Token | between |
Token ID | 1022 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
═ | +0.657 |
DRAG | +0.584 |
Hour | +0.543 |
backdrop | +0.542 |
GEAR | +0.538 |
Neg logit contributions | |
ochond | -0.578 |
Filip | -0.550 |
amily | -0.486 |
estine | -0.484 |
urers | -0.472 |
Token | the |
Token ID | 262 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
═ | +0.053 |
DRAG | +0.047 |
Hour | +0.044 |
backdrop | +0.044 |
GEAR | +0.043 |
Neg logit contributions | |
ochond | -0.053 |
Filip | -0.050 |
amily | -0.045 |
estine | -0.045 |
urers | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
═ | +0.053 |
DRAG | +0.047 |
Hour | +0.043 |
backdrop | +0.043 |
GEAR | +0.043 |
Neg logit contributions | |
ochond | -0.053 |
Filip | -0.050 |
amily | -0.045 |
estine | -0.045 |
urers | -0.044 |
Token | petition |
Token ID | 8853 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
ochond | +0.007 |
Filip | +0.007 |
estine | +0.006 |
amily | +0.006 |
urers | +0.006 |
Neg logit contributions | |
═ | -0.007 |
DRAG | -0.006 |
Hour | -0.006 |
backdrop | -0.006 |
GEAR | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
═ | +0.081 |
DRAG | +0.072 |
Hour | +0.067 |
backdrop | +0.066 |
GEAR | +0.066 |
Neg logit contributions | |
ochond | -0.076 |
Filip | -0.072 |
estine | -0.064 |
amily | -0.064 |
urers | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
═ | +0.083 |
DRAG | +0.074 |
Hour | +0.069 |
backdrop | +0.069 |
GEAR | +0.068 |
Neg logit contributions | |
ochond | -0.063 |
Filip | -0.060 |
amily | -0.052 |
estine | -0.052 |
urers | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
═ | +0.111 |
DRAG | +0.100 |
Hour | +0.095 |
backdrop | +0.095 |
GEAR | +0.094 |
Neg logit contributions | |
ochond | -0.059 |
Filip | -0.056 |
estine | -0.047 |
amily | -0.047 |
urers | -0.045 |
Token | Jack |
Token ID | 14295 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
═ | +0.090 |
DRAG | +0.080 |
Hour | +0.076 |
backdrop | +0.076 |
GEAR | +0.075 |
Neg logit contributions | |
ochond | -0.064 |
Filip | -0.060 |
amily | -0.053 |
estine | -0.052 |
urers | -0.051 |
Token | now |
Token ID | 2197 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ochond | +0.513 |
Filip | +0.486 |
estine | +0.426 |
amily | +0.419 |
apeake | +0.408 |
Neg logit contributions | |
═ | -0.739 |
DRAG | -0.671 |
backdrop | -0.617 |
GEAR | -0.616 |
Hour | -0.614 |
Token | , |
Token ID | 11 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
ochond | +0.253 |
Filip | +0.242 |
amily | +0.215 |
estine | +0.214 |
urers | +0.209 |
Neg logit contributions | |
═ | -0.255 |
DRAG | -0.225 |
Hour | -0.208 |
backdrop | -0.208 |
GEAR | -0.206 |
Token | who |
Token ID | 508 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
═ | +0.053 |
DRAG | +0.048 |
Hour | +0.045 |
backdrop | +0.045 |
GEAR | +0.044 |
Neg logit contributions | |
ochond | -0.039 |
Filip | -0.037 |
amily | -0.032 |
estine | -0.032 |
urers | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
ochond | +0.410 |
Filip | +0.391 |
amily | +0.347 |
estine | +0.347 |
urers | +0.338 |
Neg logit contributions | |
═ | -0.435 |
DRAG | -0.385 |
Hour | -0.357 |
backdrop | -0.357 |
GEAR | -0.354 |
Token | at |
Token ID | 379 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ochond | +0.083 |
Filip | +0.078 |
amily | +0.070 |
estine | +0.070 |
urers | +0.068 |
Neg logit contributions | |
═ | -0.088 |
DRAG | -0.078 |
Hour | -0.073 |
backdrop | -0.073 |
GEAR | -0.072 |
Token | refused |
Token ID | 6520 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
═ | +0.035 |
DRAG | +0.031 |
Hour | +0.028 |
backdrop | +0.028 |
GEAR | +0.028 |
Neg logit contributions | |
ochond | -0.034 |
Filip | -0.033 |
amily | -0.029 |
estine | -0.029 |
urers | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
═ | +0.137 |
DRAG | +0.121 |
Hour | +0.113 |
backdrop | +0.112 |
GEAR | +0.111 |
Neg logit contributions | |
ochond | -0.132 |
Filip | -0.125 |
amily | -0.112 |
estine | -0.112 |
urers | -0.109 |
Token | let |
Token ID | 1309 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
═ | +0.062 |
DRAG | +0.054 |
Hour | +0.050 |
backdrop | +0.050 |
GEAR | +0.049 |
Neg logit contributions | |
ochond | -0.070 |
Filip | -0.067 |
amily | -0.060 |
estine | -0.060 |
urers | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
ochond | +0.097 |
Filip | +0.093 |
amily | +0.083 |
estine | +0.083 |
urers | +0.081 |
Neg logit contributions | |
═ | -0.095 |
DRAG | -0.084 |
Hour | -0.078 |
backdrop | -0.078 |
GEAR | -0.077 |
Token | detention |
Token ID | 13280 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
═ | +0.064 |
DRAG | +0.055 |
Hour | +0.051 |
backdrop | +0.051 |
GEAR | +0.050 |
Neg logit contributions | |
ochond | -0.080 |
Filip | -0.077 |
amily | -0.069 |
estine | -0.069 |
urers | -0.068 |
Token | of |
Token ID | 286 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ochond | +0.054 |
Filip | +0.051 |
amily | +0.046 |
estine | +0.046 |
urers | +0.045 |
Neg logit contributions | |
═ | -0.045 |
DRAG | -0.039 |
Hour | -0.036 |
backdrop | -0.036 |
GEAR | -0.036 |
Token | Kob |
Token ID | 23403 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
═ | +0.135 |
DRAG | +0.118 |
Hour | +0.109 |
backdrop | +0.109 |
GEAR | +0.108 |
Neg logit contributions | |
ochond | -0.145 |
Filip | -0.139 |
amily | -0.125 |
estine | -0.124 |
urers | -0.121 |
Token | ay |
Token ID | 323 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
═ | +0.564 |
DRAG | +0.504 |
Hour | +0.471 |
backdrop | +0.470 |
GEAR | +0.466 |
Neg logit contributions | |
ochond | -0.444 |
Filip | -0.421 |
amily | -0.370 |
estine | -0.368 |
urers | -0.358 |
Token | ashi |
Token ID | 12144 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
═ | +0.467 |
DRAG | +0.410 |
Hour | +0.377 |
backdrop | +0.377 |
GEAR | +0.373 |
Neg logit contributions | |
ochond | -0.501 |
Filip | -0.480 |
amily | -0.430 |
estine | -0.430 |
urers | -0.418 |
Token | ruin |
Token ID | 16866 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ochond | +0.343 |
Filip | +0.327 |
amily | +0.292 |
estine | +0.291 |
urers | +0.284 |
Neg logit contributions | |
═ | -0.348 |
DRAG | -0.307 |
Hour | -0.285 |
backdrop | -0.284 |
GEAR | -0.282 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
ochond | +0.475 |
Filip | +0.454 |
amily | +0.408 |
estine | +0.407 |
urers | +0.398 |
Neg logit contributions | |
═ | -0.425 |
DRAG | -0.372 |
Hour | -0.344 |
backdrop | -0.342 |
GEAR | -0.339 |
Token | on |
Token ID | 319 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
═ | +0.157 |
DRAG | +0.140 |
Hour | +0.131 |
backdrop | +0.131 |
GEAR | +0.129 |
Neg logit contributions | |
ochond | -0.139 |
Filip | -0.131 |
amily | -0.117 |
estine | -0.116 |
urers | -0.113 |
Token | Thursday |
Token ID | 3635 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
═ | +0.140 |
DRAG | +0.120 |
Hour | +0.108 |
backdrop | +0.108 |
GEAR | +0.107 |
Neg logit contributions | |
ochond | -0.200 |
Filip | -0.192 |
amily | -0.174 |
estine | -0.174 |
urers | -0.170 |
Token | . |
Token ID | 13 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
═ | +0.410 |
DRAG | +0.365 |
Hour | +0.343 |
backdrop | +0.342 |
GEAR | +0.337 |
Neg logit contributions | |
ochond | -0.357 |
Filip | -0.337 |
amily | -0.301 |
estine | -0.299 |
urers | -0.291 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
═ | +0.105 |
DRAG | +0.095 |
Hour | +0.091 |
backdrop | +0.090 |
GEAR | +0.089 |
Neg logit contributions | |
ochond | -0.068 |
Filip | -0.063 |
amily | -0.055 |
estine | -0.055 |
urers | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ochond | +0.099 |
Filip | +0.093 |
amily | +0.078 |
estine | +0.078 |
urers | +0.075 |
Neg logit contributions | |
═ | -0.181 |
DRAG | -0.164 |
Hour | -0.155 |
backdrop | -0.155 |
GEAR | -0.154 |
Token | Mill |
Token ID | 22603 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ochond | +0.085 |
Filip | +0.080 |
amily | +0.071 |
estine | +0.069 |
urers | +0.068 |
Neg logit contributions | |
═ | -0.110 |
DRAG | -0.098 |
Hour | -0.093 |
backdrop | -0.092 |
GEAR | -0.091 |
Token | ions |
Token ID | 507 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ochond | +1.646 |
Filip | +1.583 |
amily | +1.442 |
estine | +1.442 |
urers | +1.417 |
Neg logit contributions | |
═ | -1.085 |
DRAG | -0.923 |
backdrop | -0.830 |
Hour | -0.824 |
GEAR | -0.821 |
Token | of |
Token ID | 286 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
═ | +0.257 |
DRAG | +0.222 |
Hour | +0.206 |
backdrop | +0.205 |
GEAR | +0.201 |
Neg logit contributions | |
ochond | -0.321 |
Filip | -0.306 |
amily | -0.278 |
estine | -0.278 |
urers | -0.270 |
Token | Afghans |
Token ID | 48336 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
═ | +0.120 |
DRAG | +0.105 |
Hour | +0.099 |
backdrop | +0.098 |
GEAR | +0.097 |
Neg logit contributions | |
ochond | -0.120 |
Filip | -0.113 |
amily | -0.102 |
estine | -0.102 |
urers | -0.099 |
Token | defied |
Token ID | 47437 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ochond | +0.624 |
Filip | +0.593 |
amily | +0.532 |
estine | +0.529 |
urers | +0.517 |
Neg logit contributions | |
═ | -0.610 |
DRAG | -0.537 |
Hour | -0.499 |
backdrop | -0.499 |
GEAR | -0.492 |
Token | Taliban |
Token ID | 15471 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
═ | +0.111 |
DRAG | +0.098 |
backdrop | +0.092 |
Hour | +0.092 |
GEAR | +0.090 |
Neg logit contributions | |
ochond | -0.111 |
Filip | -0.105 |
amily | -0.095 |
estine | -0.094 |
urers | -0.092 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ochond | +0.176 |
Filip | +0.167 |
amily | +0.150 |
estine | +0.150 |
urers | +0.145 |
Neg logit contributions | |
═ | -0.180 |
DRAG | -0.158 |
Hour | -0.148 |
backdrop | -0.148 |
GEAR | -0.145 |
Token | time |
Token ID | 640 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
ochond | +0.110 |
Filip | +0.105 |
amily | +0.096 |
estine | +0.096 |
urers | +0.094 |
Neg logit contributions | |
═ | -0.082 |
DRAG | -0.070 |
backdrop | -0.065 |
Hour | -0.064 |
GEAR | -0.063 |
Token | where |
Token ID | 810 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
ochond | +0.227 |
Filip | +0.216 |
amily | +0.194 |
estine | +0.193 |
urers | +0.188 |
Neg logit contributions | |
═ | -0.237 |
DRAG | -0.208 |
Hour | -0.195 |
backdrop | -0.194 |
GEAR | -0.191 |
Token | those |
Token ID | 883 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ochond | +0.671 |
Filip | +0.637 |
amily | +0.568 |
estine | +0.566 |
urers | +0.551 |
Neg logit contributions | |
═ | -0.717 |
DRAG | -0.635 |
Hour | -0.591 |
backdrop | -0.589 |
GEAR | -0.583 |
Token | interested |
Token ID | 4609 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ochond | +0.342 |
Filip | +0.322 |
amily | +0.284 |
estine | +0.283 |
urers | +0.274 |
Neg logit contributions | |
═ | -0.433 |
DRAG | -0.388 |
Hour | -0.363 |
backdrop | -0.363 |
GEAR | -0.359 |
Token | in |
Token ID | 287 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
ochond | +1.172 |
Filip | +1.112 |
amily | +0.985 |
estine | +0.983 |
urers | +0.956 |
Neg logit contributions | |
═ | -1.349 |
DRAG | -1.198 |
Hour | -1.120 |
backdrop | -1.117 |
GEAR | -1.106 |
Token | Lac |
Token ID | 23115 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ochond | +0.937 |
Filip | +0.896 |
amily | +0.798 |
estine | +0.794 |
urers | +0.775 |
Neg logit contributions | |
═ | -0.943 |
DRAG | -0.831 |
Hour | -0.769 |
backdrop | -0.767 |
GEAR | -0.761 |
Token | an |
Token ID | 272 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ochond | +1.088 |
Filip | +1.044 |
amily | +0.945 |
estine | +0.943 |
urers | +0.922 |
Neg logit contributions | |
═ | -0.860 |
DRAG | -0.745 |
Hour | -0.681 |
backdrop | -0.679 |
GEAR | -0.672 |
Token | feel |
Token ID | 1254 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ochond | +0.423 |
Filip | +0.403 |
amily | +0.359 |
estine | +0.358 |
urers | +0.349 |
Neg logit contributions | |
═ | -0.445 |
DRAG | -0.393 |
Hour | -0.366 |
backdrop | -0.364 |
GEAR | -0.361 |
Token | that |
Token ID | 326 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ochond | +0.195 |
Filip | +0.185 |
amily | +0.166 |
estine | +0.165 |
urers | +0.160 |
Neg logit contributions | |
═ | -0.216 |
DRAG | -0.191 |
Hour | -0.179 |
backdrop | -0.178 |
GEAR | -0.176 |
Token | they |
Token ID | 484 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
ochond | +0.370 |
Filip | +0.352 |
amily | +0.311 |
estine | +0.310 |
urers | +0.302 |
Neg logit contributions | |
═ | -0.425 |
DRAG | -0.378 |
Hour | -0.352 |
backdrop | -0.351 |
GEAR | -0.348 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
═ | +0.157 |
DRAG | +0.141 |
Hour | +0.133 |
backdrop | +0.132 |
GEAR | +0.131 |
Neg logit contributions | |
ochond | -0.118 |
Filip | -0.111 |
amily | -0.098 |
estine | -0.097 |
urers | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
═ | +0.392 |
DRAG | +0.356 |
Hour | +0.336 |
backdrop | +0.335 |
GEAR | +0.333 |
Neg logit contributions | |
ochond | -0.216 |
Filip | -0.202 |
amily | -0.171 |
estine | -0.170 |
urers | -0.164 |
Token | Dean |
Token ID | 36372 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
═ | +0.377 |
DRAG | +0.342 |
Hour | +0.326 |
backdrop | +0.323 |
GEAR | +0.321 |
Neg logit contributions | |
ochond | -0.192 |
Filip | -0.178 |
amily | -0.150 |
estine | -0.150 |
urers | -0.143 |
Token | looks |
Token ID | 3073 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ochond | +0.018 |
Filip | +0.017 |
amily | +0.015 |
estine | +0.015 |
urers | +0.015 |
Neg logit contributions | |
═ | -0.021 |
DRAG | -0.019 |
Hour | -0.017 |
backdrop | -0.017 |
GEAR | -0.017 |
Token | on |
Token ID | 319 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
═ | +0.205 |
DRAG | +0.183 |
Hour | +0.172 |
backdrop | +0.172 |
GEAR | +0.170 |
Neg logit contributions | |
ochond | -0.167 |
Filip | -0.158 |
amily | -0.140 |
estine | -0.139 |
urers | -0.135 |
Token | concerned |
Token ID | 5213 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
═ | +0.426 |
DRAG | +0.376 |
Hour | +0.350 |
backdrop | +0.349 |
GEAR | +0.344 |
Neg logit contributions | |
ochond | -0.430 |
Filip | -0.409 |
amily | -0.366 |
estine | -0.365 |
urers | -0.356 |
Token | as |
Token ID | 355 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ochond | +0.956 |
Filip | +0.913 |
amily | +0.812 |
estine | +0.807 |
urers | +0.787 |
Neg logit contributions | |
═ | -1.013 |
DRAG | -0.896 |
Hour | -0.830 |
backdrop | -0.829 |
GEAR | -0.823 |
Token | Tor |
Token ID | 4022 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
═ | +0.117 |
DRAG | +0.104 |
Hour | +0.097 |
backdrop | +0.097 |
GEAR | +0.096 |
Neg logit contributions | |
ochond | -0.109 |
Filip | -0.103 |
amily | -0.092 |
estine | -0.092 |
urers | -0.089 |
Token | i |
Token ID | 72 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
═ | +0.079 |
DRAG | +0.071 |
Hour | +0.067 |
backdrop | +0.067 |
GEAR | +0.067 |
Neg logit contributions | |
ochond | -0.048 |
Filip | -0.046 |
amily | -0.039 |
estine | -0.039 |
urers | -0.038 |
Token | inspect |
Token ID | 10104 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
ochond | +0.166 |
Filip | +0.158 |
amily | +0.141 |
estine | +0.140 |
urers | +0.137 |
Neg logit contributions | |
═ | -0.174 |
DRAG | -0.154 |
Hour | -0.143 |
backdrop | -0.143 |
GEAR | -0.141 |
Token | s |
Token ID | 82 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
═ | +0.089 |
DRAG | +0.079 |
Hour | +0.072 |
backdrop | +0.072 |
GEAR | +0.071 |
Neg logit contributions | |
ochond | -0.095 |
Filip | -0.091 |
amily | -0.081 |
estine | -0.081 |
urers | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ochond | +0.265 |
Filip | +0.252 |
amily | +0.225 |
estine | +0.225 |
urers | +0.220 |
Neg logit contributions | |
═ | -0.263 |
DRAG | -0.231 |
Hour | -0.216 |
backdrop | -0.215 |
GEAR | -0.212 |
Token | smoker |
Token ID | 41644 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ochond | +0.208 |
Filip | +0.200 |
amily | +0.179 |
estine | +0.179 |
urers | +0.175 |
Neg logit contributions | |
═ | -0.183 |
DRAG | -0.160 |
Hour | -0.146 |
backdrop | -0.146 |
GEAR | -0.145 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
═ | +0.454 |
DRAG | +0.402 |
Hour | +0.376 |
backdrop | +0.376 |
GEAR | +0.371 |
Neg logit contributions | |
ochond | -0.403 |
Filip | -0.384 |
amily | -0.340 |
estine | -0.339 |
urers | -0.331 |
Token | like |
Token ID | 588 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
ochond | +0.224 |
Filip | +0.214 |
amily | +0.191 |
estine | +0.190 |
urers | +0.186 |
Neg logit contributions | |
═ | -0.221 |
DRAG | -0.194 |
Hour | -0.180 |
backdrop | -0.179 |
GEAR | -0.178 |
Token | k |
Token ID | 479 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
ochond | +0.567 |
Filip | +0.538 |
amily | +0.480 |
estine | +0.478 |
urers | +0.466 |
Neg logit contributions | |
═ | -0.605 |
DRAG | -0.536 |
Hour | -0.499 |
backdrop | -0.498 |
GEAR | -0.492 |
Token | ung |
Token ID | 2150 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ochond | +0.213 |
Filip | +0.203 |
amily | +0.178 |
estine | +0.177 |
urers | +0.173 |
Neg logit contributions | |
═ | -0.258 |
DRAG | -0.230 |
Hour | -0.217 |
backdrop | -0.215 |
GEAR | -0.212 |
Token | p |
Token ID | 279 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ochond | +0.953 |
Filip | +0.906 |
amily | +0.802 |
estine | +0.799 |
urers | +0.778 |
Neg logit contributions | |
═ | -1.079 |
DRAG | -0.958 |
Hour | -0.893 |
backdrop | -0.890 |
GEAR | -0.883 |
Token | ao |
Token ID | 5488 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
ochond | +0.810 |
Filip | +0.773 |
estine | +0.655 |
amily | +0.645 |
urers | +0.638 |
Neg logit contributions | |
═ | -1.228 |
DRAG | -1.116 |
Hour | -1.059 |
backdrop | -1.044 |
GEAR | -1.032 |
Token | cor |
Token ID | 1162 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
ochond | +0.538 |
Filip | +0.511 |
amily | +0.455 |
estine | +0.454 |
urers | +0.443 |
Neg logit contributions | |
═ | -0.580 |
DRAG | -0.515 |
Hour | -0.480 |
backdrop | -0.478 |
GEAR | -0.471 |
Token | ned |
Token ID | 2817 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
ochond | +0.645 |
Filip | +0.607 |
amily | +0.522 |
estine | +0.519 |
urers | +0.502 |
Neg logit contributions | |
═ | -1.027 |
DRAG | -0.928 |
Hour | -0.873 |
backdrop | -0.872 |
GEAR | -0.866 |
Token | beef |
Token ID | 12023 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ochond | +0.966 |
Filip | +0.926 |
amily | +0.843 |
estine | +0.839 |
urers | +0.823 |
Neg logit contributions | |
═ | -0.691 |
DRAG | -0.593 |
Hour | -0.540 |
backdrop | -0.538 |
GEAR | -0.532 |
Token | others |
Token ID | 1854 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
ochond | +0.138 |
Filip | +0.132 |
amily | +0.118 |
estine | +0.117 |
urers | +0.114 |
Neg logit contributions | |
═ | -0.143 |
DRAG | -0.126 |
Hour | -0.117 |
backdrop | -0.117 |
GEAR | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
ochond | +0.271 |
Filip | +0.256 |
amily | +0.224 |
estine | +0.223 |
urers | +0.217 |
Neg logit contributions | |
═ | -0.368 |
DRAG | -0.330 |
Hour | -0.310 |
backdrop | -0.310 |
GEAR | -0.307 |
Token | Most |
Token ID | 4042 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ochond | +0.084 |
Filip | +0.080 |
amily | +0.071 |
estine | +0.070 |
urers | +0.069 |
Neg logit contributions | |
═ | -0.094 |
DRAG | -0.084 |
Hour | -0.078 |
backdrop | -0.078 |
GEAR | -0.077 |
Token | tweets |
Token ID | 12665 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ochond | +0.271 |
Filip | +0.259 |
amily | +0.232 |
estine | +0.231 |
urers | +0.226 |
Neg logit contributions | |
═ | -0.254 |
DRAG | -0.223 |
Hour | -0.207 |
backdrop | -0.206 |
GEAR | -0.204 |
Token | about |
Token ID | 546 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
═ | +0.276 |
DRAG | +0.245 |
Hour | +0.228 |
backdrop | +0.228 |
GEAR | +0.225 |
Neg logit contributions | |
ochond | -0.260 |
Filip | -0.246 |
amily | -0.221 |
estine | -0.219 |
urers | -0.213 |
Token | Pur |
Token ID | 9330 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ochond | +0.097 |
Filip | +0.091 |
amily | +0.081 |
estine | +0.081 |
urers | +0.079 |
Neg logit contributions | |
═ | -0.108 |
DRAG | -0.096 |
Hour | -0.090 |
backdrop | -0.089 |
GEAR | -0.088 |
Token | ges |
Token ID | 3212 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
ochond | +1.033 |
Filip | +0.989 |
estine | +0.882 |
amily | +0.881 |
urers | +0.858 |
Neg logit contributions | |
═ | -1.017 |
DRAG | -0.896 |
Hour | -0.828 |
backdrop | -0.828 |
GEAR | -0.820 |
Token | have |
Token ID | 423 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ochond | +0.018 |
Filip | +0.017 |
amily | +0.015 |
estine | +0.015 |
urers | +0.015 |
Neg logit contributions | |
═ | -0.019 |
DRAG | -0.017 |
Hour | -0.016 |
backdrop | -0.016 |
GEAR | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
ochond | +0.195 |
Filip | +0.185 |
amily | +0.166 |
estine | +0.165 |
urers | +0.160 |
Neg logit contributions | |
═ | -0.213 |
DRAG | -0.190 |
Hour | -0.177 |
backdrop | -0.177 |
GEAR | -0.174 |
Token | refrain |
Token ID | 25133 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
═ | +0.026 |
DRAG | +0.023 |
backdrop | +0.021 |
Hour | +0.021 |
GEAR | +0.021 |
Neg logit contributions | |
ochond | -0.030 |
Filip | -0.029 |
amily | -0.026 |
estine | -0.026 |
urers | -0.026 |
Token | � |
Token ID | 564 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
═ | +0.243 |
DRAG | +0.214 |
Hour | +0.200 |
backdrop | +0.200 |
GEAR | +0.197 |
Neg logit contributions | |
ochond | -0.236 |
Filip | -0.225 |
amily | -0.201 |
estine | -0.200 |
urers | -0.196 |