Token | come |
Token ID | 1282 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
aches | +0.178 |
led | +0.175 |
stamps | +0.173 |
coins | +0.173 |
ers | +0.173 |
Neg logit contributions | |
Deal | -0.145 |
� | -0.144 |
She | -0.144 |
Don | -0.142 |
Why | -0.126 |
Token | back |
Token ID | 736 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
aches | +0.145 |
seeds | +0.133 |
coins | +0.131 |
cream | +0.131 |
stamps | +0.128 |
Neg logit contributions | |
Deal | -0.175 |
� | -0.173 |
She | -0.168 |
Don | -0.165 |
Why | -0.161 |
Token | with |
Token ID | 351 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
aches | +0.272 |
cream | +0.246 |
coins | +0.246 |
seeds | +0.245 |
ils | +0.242 |
Neg logit contributions | |
� | -0.218 |
She | -0.218 |
Don | -0.207 |
Deal | -0.206 |
Why | -0.196 |
Token | some |
Token ID | 617 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
aches | +0.050 |
ating | +0.046 |
cream | +0.046 |
asis | +0.046 |
led | +0.046 |
Neg logit contributions | |
� | -0.032 |
She | -0.032 |
Deal | -0.030 |
Don | -0.030 |
Daddy | -0.028 |
Token | friends |
Token ID | 2460 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
aches | +0.260 |
ating | +0.239 |
asis | +0.236 |
ep | +0.217 |
ves | +0.217 |
Neg logit contributions | |
� | -0.355 |
She | -0.333 |
Deal | -0.324 |
Don | -0.318 |
One | -0.318 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aches | +0.120 |
seeds | +0.111 |
cream | +0.109 |
coins | +0.109 |
stamps | +0.107 |
Neg logit contributions | |
� | -0.094 |
She | -0.089 |
Deal | -0.089 |
Don | -0.086 |
Why | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Deal | +0.455 |
Don | +0.307 |
Why | +0.297 |
� | +0.292 |
Okay | +0.280 |
Neg logit contributions | |
lands | -0.761 |
seeds | -0.739 |
aches | -0.738 |
n | -0.732 |
nests | -0.731 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Deal | +0.571 |
Don | +0.508 |
Why | +0.488 |
� | +0.481 |
She | +0.476 |
Neg logit contributions | |
aches | -0.633 |
ves | -0.582 |
ers | -0.573 |
cream | -0.556 |
seeds | -0.556 |
Token | The |
Token ID | 464 |
Feature activation | +9.90e-03 |
Pos logit contributions | |
Deal | +0.484 |
Don | +0.434 |
� | +0.434 |
She | +0.423 |
Why | +0.408 |
Neg logit contributions | |
aches | -0.703 |
ers | -0.634 |
seeds | -0.633 |
cream | -0.632 |
ils | -0.631 |
Token | vine |
Token ID | 17793 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
� | +0.017 |
Deal | +0.016 |
She | +0.016 |
Don | +0.015 |
Today | +0.014 |
Neg logit contributions | |
aches | -0.020 |
cream | -0.019 |
coins | -0.019 |
ers | -0.019 |
stamps | -0.019 |
Token | settled |
Token ID | 10282 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
aches | +0.280 |
cream | +0.275 |
ymes | +0.267 |
iest | +0.262 |
ts | +0.261 |
Neg logit contributions | |
� | -0.293 |
She | -0.286 |
One | -0.245 |
They | -0.232 |
� | -0.231 |
Token | he |
Token ID | 339 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
� | +0.023 |
She | +0.022 |
Don | +0.021 |
Daddy | +0.020 |
Why | +0.020 |
Neg logit contributions | |
aches | -0.034 |
ils | -0.032 |
ers | -0.032 |
seeds | -0.031 |
cream | -0.031 |
Token | had |
Token ID | 550 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
� | +0.024 |
Don | +0.024 |
She | +0.024 |
Why | +0.023 |
Deal | +0.022 |
Neg logit contributions | |
aches | -0.028 |
seeds | -0.026 |
cream | -0.026 |
coins | -0.025 |
bread | -0.025 |
Token | told |
Token ID | 1297 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
aches | +0.021 |
asis | +0.021 |
an | +0.020 |
ating | +0.020 |
seeds | +0.019 |
Neg logit contributions | |
� | -0.019 |
Don | -0.018 |
She | -0.018 |
Dad | -0.017 |
One | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
� | +0.095 |
She | +0.090 |
Deal | +0.090 |
Don | +0.088 |
Why | +0.082 |
Neg logit contributions | |
aches | -0.140 |
seeds | -0.134 |
cream | -0.131 |
stamps | -0.129 |
coins | -0.128 |
Token | truth |
Token ID | 3872 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
aches | +0.229 |
seeds | +0.199 |
ils | +0.197 |
ating | +0.196 |
cream | +0.196 |
Neg logit contributions | |
� | -0.300 |
Deal | -0.293 |
She | -0.289 |
Don | -0.283 |
Why | -0.278 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aches | +0.042 |
seeds | +0.039 |
cream | +0.038 |
stamps | +0.038 |
coins | +0.038 |
Neg logit contributions | |
� | -0.033 |
She | -0.031 |
Deal | -0.029 |
Don | -0.029 |
Why | -0.029 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Deal | +0.408 |
� | +0.296 |
Don | +0.279 |
Why | +0.275 |
Today | +0.270 |
Neg logit contributions | |
ers | -0.686 |
kingdom | -0.663 |
coins | -0.651 |
stamps | -0.649 |
aches | -0.646 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Deal | +0.231 |
� | +0.205 |
Don | +0.191 |
She | +0.179 |
Okay | +0.172 |
Neg logit contributions | |
ers | -0.308 |
aches | -0.289 |
seeds | -0.284 |
cream | -0.283 |
ating | -0.282 |
Token | upon |
Token ID | 2402 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
Deal | +0.255 |
� | +0.222 |
Don | +0.222 |
Why | +0.218 |
She | +0.208 |
Neg logit contributions | |
aches | -0.264 |
coins | -0.237 |
iest | -0.231 |
cream | -0.230 |
crown | -0.229 |
Token | a |
Token ID | 257 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
Deal | +0.092 |
� | +0.090 |
She | +0.086 |
Don | +0.086 |
Why | +0.083 |
Neg logit contributions | |
aches | -0.083 |
seeds | -0.076 |
cream | -0.076 |
coins | -0.075 |
ers | -0.074 |
Token | time |
Token ID | 640 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
aches | +0.075 |
cream | +0.066 |
coins | +0.057 |
food | +0.057 |
seeds | +0.056 |
Neg logit contributions | |
Don | -0.271 |
Deal | -0.271 |
� | -0.268 |
She | -0.268 |
Why | -0.266 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ils | +0.259 |
led | +0.236 |
aches | +0.235 |
ating | +0.229 |
ers | +0.214 |
Neg logit contributions | |
� | -0.278 |
She | -0.265 |
Don | -0.260 |
One | -0.250 |
| -0.246 |
Token | would |
Token ID | 561 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
aches | +0.247 |
cream | +0.241 |
seas | +0.239 |
ating | +0.227 |
stamps | +0.226 |
Neg logit contributions | |
� | -0.188 |
She | -0.185 |
Why | -0.167 |
� | -0.162 |
Don | -0.162 |
Token | soon |
Token ID | 2582 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Deal | +0.027 |
� | +0.026 |
She | +0.025 |
Don | +0.025 |
Why | +0.025 |
Neg logit contributions | |
aches | -0.026 |
seeds | -0.024 |
coins | -0.023 |
cream | -0.023 |
stamps | -0.023 |
Token | be |
Token ID | 307 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
� | +0.019 |
She | +0.018 |
Don | +0.018 |
They | +0.016 |
Deal | +0.016 |
Neg logit contributions | |
aches | -0.022 |
ers | -0.022 |
cream | -0.022 |
ils | -0.022 |
ating | -0.022 |
Token | better |
Token ID | 1365 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
ves | +0.162 |
aches | +0.161 |
ils | +0.157 |
ymes | +0.151 |
iest | +0.150 |
Neg logit contributions | |
� | -0.134 |
She | -0.128 |
Don | -0.122 |
Johnny | -0.122 |
Dad | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aches | +0.152 |
ers | +0.139 |
seeds | +0.138 |
ils | +0.138 |
stamps | +0.137 |
Neg logit contributions | |
� | -0.100 |
She | -0.099 |
Don | -0.097 |
Deal | -0.095 |
Why | -0.093 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Deal | +0.472 |
Don | +0.364 |
Why | +0.346 |
ula | +0.329 |
arl | +0.325 |
Neg logit contributions | |
cream | -0.675 |
way | -0.637 |
flavors | -0.636 |
ers | -0.635 |
food | -0.633 |
Token |
|
Token ID | 198 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Deal | +0.429 |
Don | +0.373 |
Why | +0.352 |
She | +0.318 |
� | +0.312 |
Neg logit contributions | |
aches | -0.712 |
ves | -0.699 |
ers | -0.667 |
cream | -0.658 |
ating | -0.628 |
Token | John |
Token ID | 7554 |
Feature activation | -9.29e-03 |
Pos logit contributions | |
Deal | +0.536 |
Don | +0.505 |
She | +0.485 |
� | +0.464 |
Why | +0.463 |
Neg logit contributions | |
aches | -0.628 |
cream | -0.597 |
ers | -0.572 |
ating | -0.565 |
ves | -0.550 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.25e-03 |
Pos logit contributions | |
aches | +0.019 |
cream | +0.017 |
iest | +0.017 |
stamps | +0.017 |
coins | +0.017 |
Neg logit contributions | |
� | -0.017 |
She | -0.016 |
They | -0.014 |
He | -0.014 |
Don | -0.014 |
Token | back |
Token ID | 736 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
aches | +0.004 |
seeds | +0.004 |
coins | +0.004 |
cream | +0.004 |
stamps | +0.003 |
Neg logit contributions | |
Deal | -0.005 |
Don | -0.004 |
� | -0.004 |
She | -0.004 |
Why | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
aches | +0.176 |
seeds | +0.164 |
cream | +0.162 |
stamps | +0.162 |
coins | +0.161 |
Neg logit contributions | |
� | -0.131 |
She | -0.123 |
Deal | -0.121 |
Don | -0.120 |
Why | -0.115 |
Token | echoed |
Token ID | 22211 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
� | +0.027 |
Don | +0.026 |
She | +0.025 |
Why | +0.025 |
He | +0.024 |
Neg logit contributions | |
aches | -0.028 |
stamps | -0.025 |
ils | -0.025 |
coins | -0.025 |
cream | -0.024 |
Token | throughout |
Token ID | 3690 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
aches | +0.065 |
cream | +0.058 |
stamps | +0.057 |
seeds | +0.057 |
coins | +0.056 |
Neg logit contributions | |
� | -0.060 |
She | -0.057 |
Don | -0.056 |
Why | -0.054 |
Deal | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
aches | +0.131 |
seeds | +0.120 |
cream | +0.119 |
coins | +0.118 |
stamps | +0.116 |
Neg logit contributions | |
Deal | -0.146 |
� | -0.145 |
She | -0.141 |
Don | -0.139 |
Why | -0.134 |
Token | forest |
Token ID | 8222 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
aches | +0.268 |
cream | +0.237 |
ils | +0.222 |
coins | +0.220 |
led | +0.219 |
Neg logit contributions | |
One | -0.270 |
Don | -0.261 |
She | -0.257 |
Today | -0.255 |
� | -0.248 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aches | +0.334 |
cream | +0.314 |
seeds | +0.307 |
stamps | +0.304 |
coins | +0.301 |
Neg logit contributions | |
� | -0.170 |
She | -0.158 |
Don | -0.151 |
They | -0.138 |
Why | -0.137 |
Token |
|
Token ID | 198 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Deal | +0.397 |
� | +0.324 |
Don | +0.291 |
She | +0.270 |
Why | +0.270 |
Neg logit contributions | |
seeds | -0.815 |
aches | -0.798 |
food | -0.797 |
ers | -0.794 |
coins | -0.789 |
Token |
|
Token ID | 198 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Deal | +0.390 |
Don | +0.322 |
� | +0.315 |
She | +0.307 |
Why | +0.294 |
Neg logit contributions | |
aches | -0.794 |
ves | -0.751 |
ers | -0.740 |
cream | -0.725 |
seeds | -0.718 |
Token | The |
Token ID | 464 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
Deal | +0.540 |
� | +0.491 |
She | +0.485 |
Don | +0.484 |
Today | +0.464 |
Neg logit contributions | |
aches | -0.639 |
ves | -0.580 |
ers | -0.577 |
cream | -0.566 |
seeds | -0.565 |
Token | lion |
Token ID | 18744 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Deal | +0.022 |
� | +0.022 |
Don | +0.021 |
Today | +0.020 |
One | +0.020 |
Neg logit contributions | |
aches | -0.022 |
cream | -0.018 |
ating | -0.018 |
seeds | -0.018 |
ils | -0.018 |
Token | cub |
Token ID | 13617 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
aches | +0.227 |
cream | +0.218 |
stamps | +0.205 |
coins | +0.204 |
iest | +0.204 |
Neg logit contributions | |
� | -0.159 |
She | -0.144 |
| -0.142 |
� | -0.134 |
He | -0.134 |
Token | it |
Token ID | 340 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
� | +0.132 |
Daddy | +0.122 |
She | +0.120 |
Dad | +0.118 |
Johnny | +0.116 |
Neg logit contributions | |
aches | -0.181 |
ers | -0.168 |
ils | -0.168 |
ating | -0.166 |
stamps | -0.164 |
Token | made |
Token ID | 925 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
aches | +0.245 |
stamps | +0.233 |
coins | +0.224 |
ymes | +0.219 |
ating | +0.211 |
Neg logit contributions | |
� | -0.203 |
She | -0.196 |
Daddy | -0.181 |
He | -0.179 |
Johnny | -0.177 |
Token | him |
Token ID | 683 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
aches | +0.146 |
seeds | +0.138 |
cream | +0.137 |
coins | +0.137 |
stamps | +0.135 |
Neg logit contributions | |
Deal | -0.074 |
� | -0.072 |
She | -0.069 |
Don | -0.067 |
Why | -0.064 |
Token | feel |
Token ID | 1254 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
aches | +0.166 |
ils | +0.158 |
ating | +0.157 |
ers | +0.157 |
seeds | +0.156 |
Neg logit contributions | |
� | -0.146 |
She | -0.142 |
Deal | -0.141 |
Don | -0.136 |
Why | -0.128 |
Token | amazing |
Token ID | 4998 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
aches | +0.107 |
stamps | +0.097 |
coins | +0.096 |
ils | +0.096 |
cream | +0.095 |
Neg logit contributions | |
� | -0.111 |
She | -0.107 |
Deal | -0.105 |
Don | -0.103 |
Why | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aches | +0.331 |
seeds | +0.300 |
stamps | +0.299 |
ils | +0.296 |
cream | +0.293 |
Neg logit contributions | |
� | -0.181 |
She | -0.169 |
Deal | -0.158 |
Don | -0.157 |
Why | -0.154 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Deal | +0.450 |
Don | +0.312 |
� | +0.307 |
Okay | +0.296 |
Why | +0.278 |
Neg logit contributions | |
seeds | -0.731 |
ers | -0.729 |
coins | -0.725 |
food | -0.723 |
cream | -0.717 |
Token |
|
Token ID | 198 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Deal | +0.397 |
Don | +0.314 |
� | +0.304 |
Why | +0.291 |
She | +0.270 |
Neg logit contributions | |
aches | -0.785 |
ves | -0.742 |
ers | -0.736 |
cream | -0.717 |
ating | -0.692 |
Token | He |
Token ID | 1544 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
Deal | +0.512 |
Don | +0.456 |
� | +0.451 |
Today | +0.437 |
She | +0.434 |
Neg logit contributions | |
aches | -0.670 |
cream | -0.618 |
ers | -0.613 |
seeds | -0.595 |
ves | -0.589 |
Token | drank |
Token ID | 24070 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
� | +0.167 |
She | +0.139 |
Daddy | +0.139 |
They | +0.137 |
Dad | +0.135 |
Neg logit contributions | |
aches | -0.206 |
iest | -0.195 |
ating | -0.188 |
ymes | -0.188 |
cream | -0.187 |
Token | it |
Token ID | 340 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
aches | +0.181 |
ils | +0.168 |
stamps | +0.165 |
ating | +0.164 |
asis | +0.160 |
Neg logit contributions | |
� | -0.151 |
She | -0.141 |
Deal | -0.130 |
Don | -0.128 |
Why | -0.124 |
Token | would |
Token ID | 561 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
� | +0.024 |
She | +0.024 |
Don | +0.022 |
Why | +0.022 |
Deal | +0.021 |
Neg logit contributions | |
aches | -0.028 |
cream | -0.026 |
seeds | -0.025 |
coins | -0.025 |
ating | -0.025 |
Token | never |
Token ID | 1239 |
Feature activation | -9.95e-03 |
Pos logit contributions | |
Deal | +0.025 |
� | +0.025 |
She | +0.024 |
Why | +0.024 |
Don | +0.023 |
Neg logit contributions | |
aches | -0.021 |
seeds | -0.018 |
cream | -0.018 |
coins | -0.018 |
crown | -0.017 |
Token | do |
Token ID | 466 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
aches | +0.021 |
seeds | +0.020 |
stamps | +0.020 |
coins | +0.020 |
ers | +0.019 |
Neg logit contributions | |
� | -0.016 |
Deal | -0.016 |
She | -0.016 |
Don | -0.016 |
Why | -0.015 |
Token | this |
Token ID | 428 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
aches | +0.116 |
seeds | +0.116 |
ils | +0.108 |
ers | +0.107 |
asis | +0.107 |
Neg logit contributions | |
� | -0.108 |
Don | -0.103 |
She | -0.102 |
Why | -0.100 |
Deal | -0.098 |
Token | again |
Token ID | 757 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
aches | +0.209 |
seeds | +0.199 |
stamps | +0.192 |
coins | +0.191 |
ils | +0.188 |
Neg logit contributions | |
� | -0.206 |
Deal | -0.196 |
She | -0.193 |
Don | -0.192 |
Why | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aches | +0.076 |
seeds | +0.071 |
coins | +0.070 |
cream | +0.070 |
stamps | +0.069 |
Neg logit contributions | |
� | -0.051 |
Deal | -0.050 |
She | -0.049 |
Don | -0.048 |
Why | -0.046 |
Token | His |
Token ID | 2399 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
Deal | +0.475 |
� | +0.352 |
oning | +0.347 |
Don | +0.345 |
Why | +0.325 |
Neg logit contributions | |
skills | -0.632 |
way | -0.618 |
ers | -0.608 |
coins | -0.604 |
kingdom | -0.604 |
Token | parents |
Token ID | 3397 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
Deal | +0.024 |
� | +0.023 |
She | +0.022 |
Don | +0.022 |
Daddy | +0.021 |
Neg logit contributions | |
aches | -0.028 |
ers | -0.026 |
seeds | -0.025 |
cream | -0.025 |
ating | -0.025 |
Token | were |
Token ID | 547 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
aches | +0.116 |
seeds | +0.108 |
cream | +0.106 |
coins | +0.106 |
stamps | +0.104 |
Neg logit contributions | |
� | -0.101 |
She | -0.099 |
Deal | -0.094 |
Don | -0.093 |
Why | -0.090 |
Token | very |
Token ID | 845 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
� | +0.030 |
Deal | +0.030 |
She | +0.029 |
Don | +0.027 |
Why | +0.027 |
Neg logit contributions | |
aches | -0.036 |
seeds | -0.034 |
coins | -0.033 |
ils | -0.033 |
cream | -0.033 |
Token | happy |
Token ID | 3772 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
aches | +0.066 |
seeds | +0.061 |
coins | +0.060 |
cream | +0.060 |
stamps | +0.059 |
Neg logit contributions | |
Deal | -0.067 |
� | -0.066 |
She | -0.064 |
Don | -0.063 |
Why | -0.061 |
Token | was |
Token ID | 373 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
� | +0.028 |
She | +0.026 |
Don | +0.026 |
Deal | +0.024 |
Why | +0.024 |
Neg logit contributions | |
aches | -0.028 |
cream | -0.026 |
seeds | -0.026 |
coins | -0.026 |
stamps | -0.025 |
Token | back |
Token ID | 736 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
aches | +0.020 |
seeds | +0.020 |
ils | +0.020 |
coins | +0.020 |
stamps | +0.020 |
Neg logit contributions | |
� | -0.017 |
Deal | -0.017 |
She | -0.016 |
Don | -0.016 |
Daddy | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
aches | +0.255 |
seeds | +0.234 |
ils | +0.230 |
coins | +0.228 |
stamps | +0.228 |
Neg logit contributions | |
� | -0.232 |
She | -0.228 |
Don | -0.219 |
Deal | -0.217 |
Why | -0.204 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
aches | +0.264 |
seeds | +0.238 |
ils | +0.235 |
cream | +0.233 |
coins | +0.233 |
Neg logit contributions | |
� | -0.237 |
She | -0.226 |
Deal | -0.226 |
Don | -0.220 |
Why | -0.206 |
Token | ground |
Token ID | 2323 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
aches | +0.218 |
ils | +0.196 |
led | +0.192 |
ating | +0.190 |
ers | +0.187 |
Neg logit contributions | |
� | -0.322 |
Deal | -0.292 |
She | -0.291 |
Don | -0.286 |
Today | -0.272 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aches | +0.342 |
seeds | +0.318 |
stamps | +0.316 |
coins | +0.314 |
cream | +0.314 |
Neg logit contributions | |
� | -0.218 |
She | -0.209 |
Don | -0.197 |
Deal | -0.196 |
Why | -0.185 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Deal | +0.489 |
oning | +0.382 |
Why | +0.367 |
Don | +0.366 |
symp | +0.360 |
Neg logit contributions | |
ers | -0.564 |
food | -0.536 |
nuts | -0.534 |
way | -0.534 |
coin | -0.533 |
Token | One |
Token ID | 3198 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Deal | +0.230 |
� | +0.197 |
Don | +0.185 |
Okay | +0.168 |
She | +0.167 |
Neg logit contributions | |
ers | -0.312 |
ating | -0.284 |
aches | -0.283 |
seeds | -0.283 |
food | -0.282 |
Token | day |
Token ID | 1110 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
� | +0.286 |
She | +0.279 |
Deal | +0.269 |
Don | +0.267 |
Today | +0.267 |
Neg logit contributions | |
aches | -0.234 |
stamps | -0.218 |
coins | -0.217 |
seeds | -0.216 |
ils | -0.215 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
aches | +0.096 |
coins | +0.090 |
cream | +0.089 |
seeds | +0.087 |
ers | +0.085 |
Neg logit contributions | |
Deal | -0.130 |
Don | -0.120 |
� | -0.119 |
She | -0.117 |
Why | -0.115 |
Token | a |
Token ID | 257 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
Deal | +0.355 |
Don | +0.306 |
� | +0.294 |
Why | +0.285 |
Okay | +0.284 |
Neg logit contributions | |
cream | -0.176 |
food | -0.175 |
coins | -0.174 |
ers | -0.168 |
aches | -0.168 |
Token | asked |
Token ID | 1965 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
� | +0.116 |
She | +0.110 |
Don | +0.107 |
Why | +0.099 |
They | +0.099 |
Neg logit contributions | |
aches | -0.131 |
seeds | -0.118 |
ers | -0.118 |
cream | -0.118 |
coins | -0.114 |
Token | for |
Token ID | 329 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
Deal | +0.123 |
� | +0.122 |
She | +0.118 |
Don | +0.115 |
Why | +0.111 |
Neg logit contributions | |
aches | -0.147 |
seeds | -0.136 |
cream | -0.135 |
coins | -0.135 |
stamps | -0.132 |
Token | his |
Token ID | 465 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
aches | +0.128 |
seeds | +0.116 |
asis | +0.115 |
ating | +0.112 |
ers | +0.112 |
Neg logit contributions | |
� | -0.113 |
Deal | -0.110 |
Don | -0.107 |
She | -0.105 |
Daddy | -0.100 |
Token | drum |
Token ID | 13026 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
aches | +0.236 |
seeds | +0.212 |
coins | +0.210 |
cream | +0.209 |
ers | +0.207 |
Neg logit contributions | |
Deal | -0.292 |
� | -0.291 |
She | -0.279 |
Don | -0.278 |
Why | -0.267 |
Token | back |
Token ID | 736 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
aches | +0.233 |
seeds | +0.214 |
coins | +0.211 |
cream | +0.210 |
stamps | +0.208 |
Neg logit contributions | |
� | -0.219 |
Deal | -0.211 |
She | -0.211 |
Don | -0.205 |
Why | -0.198 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aches | +0.286 |
seeds | +0.265 |
coins | +0.258 |
stamps | +0.258 |
cream | +0.258 |
Neg logit contributions | |
� | -0.208 |
She | -0.198 |
Don | -0.194 |
Deal | -0.191 |
Why | -0.182 |
Token | From |
Token ID | 3574 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Deal | +0.491 |
Why | +0.339 |
Daddy | +0.336 |
Okay | +0.327 |
� | +0.325 |
Neg logit contributions | |
skills | -0.694 |
seeds | -0.679 |
ers | -0.641 |
bread | -0.639 |
food | -0.634 |
Token | then |
Token ID | 788 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
� | +0.205 |
She | +0.192 |
Deal | +0.186 |
Don | +0.181 |
Why | +0.177 |
Neg logit contributions | |
aches | -0.330 |
seeds | -0.302 |
coins | -0.298 |
ils | -0.297 |
ers | -0.295 |
Token | on |
Token ID | 319 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Deal | +0.186 |
� | +0.179 |
Don | +0.175 |
She | +0.174 |
Why | +0.170 |
Neg logit contributions | |
aches | -0.058 |
ating | -0.049 |
coins | -0.048 |
cream | -0.048 |
seeds | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
aches | +0.221 |
coins | +0.206 |
seeds | +0.205 |
cream | +0.201 |
ers | +0.199 |
Neg logit contributions | |
Deal | -0.272 |
� | -0.255 |
She | -0.252 |
Don | -0.248 |
Why | -0.242 |
Token | Sam |
Token ID | 3409 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
Deal | +0.215 |
� | +0.204 |
She | +0.198 |
Don | +0.190 |
Why | +0.184 |
Neg logit contributions | |
aches | -0.372 |
seeds | -0.353 |
coins | -0.349 |
cream | -0.348 |
stamps | -0.342 |
Token | told |
Token ID | 1297 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
� | +0.013 |
She | +0.012 |
Deal | +0.012 |
Don | +0.012 |
Why | +0.011 |
Neg logit contributions | |
aches | -0.013 |
cream | -0.012 |
seeds | -0.012 |
coins | -0.012 |
ers | -0.012 |
Token | him |
Token ID | 683 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
Deal | +0.071 |
� | +0.068 |
She | +0.066 |
Don | +0.063 |
Why | +0.060 |
Neg logit contributions | |
aches | -0.154 |
seeds | -0.145 |
coins | -0.145 |
cream | -0.144 |
stamps | -0.142 |
Token | it |
Token ID | 340 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
aches | +0.177 |
seeds | +0.170 |
cream | +0.170 |
stamps | +0.164 |
ating | +0.164 |
Neg logit contributions | |
� | -0.141 |
She | -0.137 |
Don | -0.130 |
Why | -0.126 |
Deal | -0.122 |
Token | was |
Token ID | 373 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
aches | +0.231 |
cream | +0.214 |
seeds | +0.211 |
coins | +0.207 |
stamps | +0.204 |
Neg logit contributions | |
� | -0.245 |
She | -0.237 |
Don | -0.230 |
Why | -0.223 |
They | -0.214 |
Token | Spanish |
Token ID | 7897 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
aches | +0.022 |
seeds | +0.020 |
cream | +0.020 |
coins | +0.020 |
ils | +0.019 |
Neg logit contributions | |
� | -0.020 |
Don | -0.019 |
Deal | -0.019 |
She | -0.019 |
Why | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
aches | +0.181 |
seeds | +0.166 |
cream | +0.164 |
ils | +0.160 |
coins | +0.159 |
Neg logit contributions | |
� | -0.113 |
She | -0.107 |
Don | -0.101 |
Why | -0.099 |
Deal | -0.099 |
Token | J |
Token ID | 449 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
Deal | +0.581 |
Okay | +0.401 |
� | +0.346 |
Why | +0.343 |
Don | +0.330 |
Neg logit contributions | |
coins | -0.674 |
seas | -0.666 |
skills | -0.665 |
rings | -0.657 |
aches | -0.643 |
Token | ax |
Token ID | 897 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
Deal | +0.013 |
� | +0.012 |
She | +0.012 |
Don | +0.011 |
Why | +0.011 |
Neg logit contributions | |
aches | -0.021 |
cream | -0.019 |
coins | -0.019 |
seeds | -0.019 |
ers | -0.019 |
Token | asked |
Token ID | 1965 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
aches | +0.115 |
seeds | +0.111 |
cream | +0.108 |
food | +0.106 |
coins | +0.106 |
Neg logit contributions | |
� | -0.116 |
She | -0.111 |
Don | -0.103 |
Why | -0.101 |
One | -0.099 |
Token | them |
Token ID | 606 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
� | +0.125 |
She | +0.115 |
Don | +0.111 |
Deal | +0.108 |
Why | +0.108 |
Neg logit contributions | |
aches | -0.156 |
seeds | -0.149 |
cream | -0.146 |
asis | -0.143 |
ils | -0.141 |
Token | to |
Token ID | 284 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
aches | +0.229 |
coins | +0.212 |
seeds | +0.212 |
cream | +0.209 |
stamps | +0.208 |
Neg logit contributions | |
Deal | -0.187 |
� | -0.176 |
She | -0.172 |
Don | -0.169 |
Why | -0.163 |
Token | praised |
Token ID | 15342 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
aches | +0.127 |
seeds | +0.120 |
coins | +0.117 |
cream | +0.114 |
stamps | +0.114 |
Neg logit contributions | |
� | -0.113 |
She | -0.111 |
Why | -0.106 |
Don | -0.101 |
They | -0.099 |
Token | him |
Token ID | 683 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
Deal | +0.055 |
� | +0.050 |
She | +0.048 |
Don | +0.047 |
Why | +0.045 |
Neg logit contributions | |
aches | -0.099 |
coins | -0.097 |
seeds | -0.096 |
ers | -0.095 |
food | -0.095 |
Token | for |
Token ID | 329 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
aches | +0.175 |
seeds | +0.162 |
cream | +0.160 |
coins | +0.159 |
stamps | +0.157 |
Neg logit contributions | |
� | -0.143 |
Deal | -0.141 |
She | -0.137 |
Don | -0.134 |
Why | -0.128 |
Token | being |
Token ID | 852 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
aches | +0.129 |
seeds | +0.121 |
coins | +0.116 |
cream | +0.116 |
ers | +0.116 |
Neg logit contributions | |
� | -0.105 |
Deal | -0.102 |
Don | -0.099 |
She | -0.097 |
Why | -0.093 |
Token | brave |
Token ID | 14802 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
aches | +0.174 |
ves | +0.166 |
asis | +0.160 |
seeds | +0.158 |
coins | +0.156 |
Neg logit contributions | |
Why | -0.097 |
� | -0.094 |
She | -0.092 |
Don | -0.085 |
Deal | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aches | +0.183 |
seeds | +0.160 |
cream | +0.157 |
asis | +0.154 |
stamps | +0.153 |
Neg logit contributions | |
� | -0.102 |
She | -0.101 |
Don | -0.095 |
Why | -0.095 |
Deal | -0.094 |
Token | |
Token ID | 220 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Deal | +0.519 |
Okay | +0.372 |
� | +0.364 |
symp | +0.357 |
oning | +0.352 |
Neg logit contributions | |
kingdom | -0.641 |
seeds | -0.623 |
ating | -0.618 |
food | -0.613 |
ers | -0.612 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Deal | +0.267 |
� | +0.248 |
Don | +0.221 |
Today | +0.210 |
symp | +0.208 |
Neg logit contributions | |
ers | -0.522 |
aches | -0.505 |
ery | -0.487 |
ating | -0.483 |
ves | -0.470 |
Token | The |
Token ID | 464 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Deal | +0.473 |
Don | +0.402 |
� | +0.376 |
She | +0.365 |
Okay | +0.359 |
Neg logit contributions | |
aches | -0.695 |
ers | -0.690 |
ves | -0.687 |
ating | -0.669 |
ery | -0.661 |
Token | knight |
Token ID | 22062 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Deal | +0.022 |
� | +0.020 |
Don | +0.020 |
She | +0.019 |
Why | +0.019 |
Neg logit contributions | |
aches | -0.025 |
cream | -0.023 |
seeds | -0.022 |
ating | -0.022 |
ils | -0.022 |
Token | 's |
Token ID | 338 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
aches | +0.239 |
seeds | +0.226 |
cream | +0.224 |
nests | +0.215 |
ymes | +0.215 |
Neg logit contributions | |
� | -0.164 |
She | -0.152 |
| -0.141 |
� | -0.137 |
He | -0.136 |
Token | said |
Token ID | 531 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
� | +0.014 |
She | +0.014 |
Don | +0.013 |
Deal | +0.013 |
Why | +0.012 |
Neg logit contributions | |
aches | -0.016 |
cream | -0.016 |
ers | -0.015 |
ating | -0.015 |
coins | -0.015 |
Token | they |
Token ID | 484 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
� | +0.113 |
She | +0.106 |
Deal | +0.099 |
Don | +0.098 |
Why | +0.096 |
Neg logit contributions | |
aches | -0.178 |
seeds | -0.167 |
cream | -0.166 |
coins | -0.163 |
ers | -0.163 |
Token | could |
Token ID | 714 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
� | +0.015 |
Deal | +0.014 |
She | +0.014 |
Don | +0.014 |
Why | +0.013 |
Neg logit contributions | |
aches | -0.018 |
cream | -0.017 |
seeds | -0.017 |
coins | -0.017 |
ers | -0.016 |
Token | help |
Token ID | 1037 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
Deal | +0.076 |
� | +0.075 |
Why | +0.069 |
She | +0.068 |
Don | +0.067 |
Neg logit contributions | |
aches | -0.073 |
seeds | -0.065 |
cream | -0.064 |
coins | -0.063 |
food | -0.062 |
Token | her |
Token ID | 607 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
aches | +0.066 |
seeds | +0.062 |
coins | +0.061 |
cream | +0.061 |
stamps | +0.060 |
Neg logit contributions | |
Deal | -0.052 |
� | -0.051 |
She | -0.050 |
Don | -0.048 |
Why | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aches | +0.233 |
seeds | +0.228 |
ils | +0.228 |
coins | +0.224 |
ers | +0.224 |
Neg logit contributions | |
She | -0.173 |
� | -0.172 |
Don | -0.170 |
Deal | -0.163 |
Why | -0.155 |
Token | |
Token ID | 220 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Deal | +0.518 |
Don | +0.377 |
Okay | +0.363 |
Why | +0.346 |
� | +0.341 |
Neg logit contributions | |
ers | -0.689 |
seeds | -0.676 |
stamps | -0.665 |
food | -0.649 |
aches | -0.647 |
Token |
|
Token ID | 198 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Deal | +0.320 |
Don | +0.269 |
� | +0.261 |
Why | +0.246 |
symp | +0.231 |
Neg logit contributions | |
aches | -0.469 |
ers | -0.467 |
ves | -0.459 |
ating | -0.409 |
stamps | -0.406 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Deal | +0.479 |
Don | +0.394 |
� | +0.372 |
Why | +0.348 |
Okay | +0.337 |
Neg logit contributions | |
aches | -0.666 |
ers | -0.662 |
ves | -0.651 |
cream | -0.614 |
bread | -0.590 |
Token | The |
Token ID | 464 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
Deal | +0.554 |
Don | +0.507 |
� | +0.500 |
Today | +0.484 |
Why | +0.460 |
Neg logit contributions | |
aches | -0.615 |
cream | -0.577 |
ers | -0.568 |
seeds | -0.565 |
ils | -0.547 |
Token | police |
Token ID | 1644 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Deal | +0.028 |
� | +0.028 |
She | +0.027 |
Don | +0.027 |
Why | +0.026 |
Neg logit contributions | |
aches | -0.025 |
seeds | -0.023 |
cream | -0.023 |
coins | -0.022 |
ils | -0.022 |
Token | had |
Token ID | 550 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
She | +0.016 |
Why | +0.015 |
� | +0.015 |
Don | +0.015 |
One | +0.013 |
Neg logit contributions | |
aches | -0.028 |
cream | -0.028 |
bread | -0.026 |
ating | -0.026 |
seeds | -0.025 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
an | +0.030 |
aches | +0.030 |
asis | +0.030 |
iest | +0.030 |
ating | +0.029 |
Neg logit contributions | |
� | -0.023 |
Don | -0.021 |
She | -0.021 |
One | -0.020 |
Why | -0.019 |
Token | an |
Token ID | 281 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
aches | +0.023 |
seeds | +0.022 |
ils | +0.022 |
asis | +0.022 |
stamps | +0.021 |
Neg logit contributions | |
� | -0.019 |
She | -0.018 |
Don | -0.017 |
Why | -0.017 |
Deal | -0.016 |
Token | important |
Token ID | 1593 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aches | +0.104 |
cream | +0.095 |
stamps | +0.095 |
seeds | +0.094 |
coins | +0.092 |
Neg logit contributions | |
� | -0.257 |
Deal | -0.252 |
She | -0.246 |
Don | -0.241 |
Today | -0.241 |
Token | lesson |
Token ID | 11483 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
aches | +0.120 |
seeds | +0.105 |
ils | +0.101 |
ers | +0.101 |
stamps | +0.101 |
Neg logit contributions | |
� | -0.290 |
Deal | -0.282 |
She | -0.278 |
Don | -0.276 |
Today | -0.270 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aches | +0.181 |
seeds | +0.170 |
cream | +0.167 |
coins | +0.166 |
stamps | +0.165 |
Neg logit contributions | |
� | -0.129 |
Deal | -0.126 |
She | -0.124 |
Don | -0.120 |
Why | -0.116 |
Token | He |
Token ID | 679 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Deal | +0.441 |
� | +0.347 |
� | +0.323 |
Don | +0.301 |
oning | +0.298 |
Neg logit contributions | |
seeds | -0.718 |
food | -0.701 |
ers | -0.696 |
kingdom | -0.689 |
coins | -0.684 |
Token | would |
Token ID | 561 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
� | +0.168 |
She | +0.164 |
Don | +0.148 |
One | +0.146 |
� | +0.145 |
Neg logit contributions | |
aches | -0.222 |
cream | -0.217 |
iest | -0.213 |
ating | -0.207 |
food | -0.200 |
Token | never |
Token ID | 1239 |
Feature activation | -9.49e-03 |
Pos logit contributions | |
Deal | +0.024 |
� | +0.024 |
She | +0.023 |
Don | +0.023 |
Why | +0.022 |
Neg logit contributions | |
aches | -0.022 |
seeds | -0.020 |
coins | -0.020 |
cream | -0.019 |
stamps | -0.019 |
Token | try |
Token ID | 1949 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
aches | +0.020 |
ers | +0.019 |
cream | +0.019 |
seeds | +0.019 |
stamps | +0.019 |
Neg logit contributions | |
� | -0.015 |
She | -0.015 |
Deal | -0.015 |
Don | -0.015 |
Why | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
aches | +0.150 |
ers | +0.147 |
ils | +0.144 |
cream | +0.142 |
led | +0.141 |
Neg logit contributions | |
� | -0.120 |
She | -0.116 |
Don | -0.110 |
Why | -0.107 |
Deal | -0.101 |
Token | seen |
Token ID | 1775 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
aches | +0.020 |
stamps | +0.019 |
ves | +0.019 |
ils | +0.019 |
cream | +0.019 |
Neg logit contributions | |
Don | -0.016 |
� | -0.015 |
She | -0.015 |
Why | -0.015 |
What | -0.014 |
Token | anything |
Token ID | 1997 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
aches | +0.205 |
ils | +0.182 |
cream | +0.180 |
seeds | +0.177 |
asis | +0.175 |
Neg logit contributions | |
� | -0.151 |
Don | -0.139 |
She | -0.138 |
Daddy | -0.133 |
Why | -0.133 |
Token | so |
Token ID | 523 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
aches | +0.233 |
seeds | +0.223 |
stamps | +0.217 |
cream | +0.213 |
ils | +0.211 |
Neg logit contributions | |
� | -0.142 |
Don | -0.122 |
Why | -0.121 |
She | -0.120 |
Deal | -0.111 |
Token | impressive |
Token ID | 8036 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
� | +0.051 |
She | +0.047 |
Don | +0.047 |
Dad | +0.046 |
Daddy | +0.045 |
Neg logit contributions | |
aches | -0.036 |
ers | -0.032 |
seeds | -0.032 |
stamps | -0.032 |
ils | -0.031 |
Token | before |
Token ID | 878 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
aches | +0.349 |
seeds | +0.323 |
stamps | +0.316 |
cream | +0.314 |
coins | +0.308 |
Neg logit contributions | |
� | -0.252 |
She | -0.232 |
Don | -0.228 |
Why | -0.224 |
Deal | -0.221 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Deal | +0.099 |
� | +0.092 |
She | +0.088 |
Don | +0.087 |
Why | +0.086 |
Neg logit contributions | |
aches | -0.097 |
seeds | -0.092 |
coins | -0.092 |
cream | -0.090 |
ers | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Deal | +0.516 |
oning | +0.386 |
� | +0.376 |
istent | +0.374 |
please | +0.360 |
Neg logit contributions | |
kingdom | -0.586 |
ers | -0.585 |
food | -0.578 |
seeds | -0.552 |
way | -0.551 |
Token |
|
Token ID | 198 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Deal | +0.642 |
Don | +0.570 |
She | +0.560 |
Why | +0.551 |
� | +0.541 |
Neg logit contributions | |
aches | -0.533 |
ves | -0.507 |
ers | -0.491 |
seeds | -0.471 |
ery | -0.468 |
Token | The |
Token ID | 464 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
Deal | +0.558 |
She | +0.504 |
Don | +0.499 |
Today | +0.493 |
� | +0.487 |
Neg logit contributions | |
aches | -0.626 |
ves | -0.581 |
ers | -0.576 |
ating | -0.561 |
cream | -0.560 |
Token | dragon |
Token ID | 10441 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Deal | +0.023 |
� | +0.022 |
One | +0.021 |
Don | +0.021 |
She | +0.021 |
Neg logit contributions | |
aches | -0.020 |
ils | -0.017 |
cream | -0.017 |
ade | -0.017 |
ating | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
aches | +0.233 |
cream | +0.222 |
coins | +0.210 |
stamps | +0.209 |
seeds | +0.207 |
Neg logit contributions | |
� | -0.202 |
She | -0.183 |
Don | -0.171 |
| -0.164 |
� | -0.163 |
Token | mom |
Token ID | 1995 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
aches | +0.328 |
ers | +0.312 |
ils | +0.304 |
led | +0.302 |
ating | +0.299 |
Neg logit contributions | |
� | -0.205 |
Daddy | -0.204 |
Deal | -0.200 |
Dad | -0.199 |
Don | -0.192 |
Token | what |
Token ID | 644 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
aches | +0.104 |
seeds | +0.096 |
coins | +0.095 |
cream | +0.095 |
stamps | +0.093 |
Neg logit contributions | |
Deal | -0.099 |
� | -0.099 |
She | -0.096 |
Don | -0.094 |
Why | -0.090 |
Token | he |
Token ID | 339 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
� | +0.012 |
She | +0.011 |
Don | +0.010 |
Why | +0.010 |
Deal | +0.010 |
Neg logit contributions | |
aches | -0.026 |
seeds | -0.025 |
ers | -0.025 |
ils | -0.024 |
led | -0.024 |
Token | had |
Token ID | 550 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
� | +0.027 |
Deal | +0.027 |
She | +0.027 |
Don | +0.026 |
Why | +0.026 |
Neg logit contributions | |
aches | -0.025 |
seeds | -0.023 |
cream | -0.023 |
coins | -0.022 |
stamps | -0.022 |
Token | done |
Token ID | 1760 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
aches | +0.016 |
seeds | +0.015 |
coins | +0.014 |
stamps | +0.014 |
cream | +0.014 |
Neg logit contributions | |
She | -0.032 |
� | -0.032 |
Deal | -0.032 |
Don | -0.031 |
Why | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aches | +0.189 |
seeds | +0.176 |
cream | +0.175 |
coins | +0.175 |
stamps | +0.172 |
Neg logit contributions | |
Deal | -0.141 |
� | -0.140 |
She | -0.135 |
Don | -0.132 |
Why | -0.127 |
Token | She |
Token ID | 1375 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Deal | +0.582 |
istent | +0.414 |
Don | +0.405 |
symp | +0.404 |
arse | +0.398 |
Neg logit contributions | |
cream | -0.624 |
food | -0.618 |
seeds | -0.617 |
aches | -0.593 |
ers | -0.592 |
Token | was |
Token ID | 373 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
� | +0.227 |
She | +0.215 |
Deal | +0.202 |
Don | +0.198 |
Daddy | +0.193 |
Neg logit contributions | |
aches | -0.221 |
seeds | -0.201 |
coins | -0.199 |
cream | -0.198 |
ers | -0.195 |
Token | happy |
Token ID | 3772 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
aches | +0.021 |
seeds | +0.021 |
ils | +0.020 |
coins | +0.020 |
stamps | +0.020 |
Neg logit contributions | |
� | -0.016 |
She | -0.015 |
Deal | -0.015 |
Don | -0.015 |
Why | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
aches | +0.123 |
cream | +0.118 |
coins | +0.117 |
seeds | +0.117 |
stamps | +0.112 |
Neg logit contributions | |
Deal | -0.153 |
� | -0.142 |
Don | -0.136 |
She | -0.134 |
Today | -0.132 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
She | +0.144 |
� | +0.143 |
Don | +0.134 |
Deal | +0.134 |
Why | +0.129 |
Neg logit contributions | |
aches | -0.158 |
seeds | -0.144 |
coins | -0.144 |
ers | -0.143 |
stamps | -0.142 |
Token | learn |
Token ID | 2193 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
� | +0.125 |
She | +0.119 |
Don | +0.117 |
They | +0.105 |
Why | +0.105 |
Neg logit contributions | |
aches | -0.175 |
ers | -0.169 |
cream | -0.166 |
stamps | -0.165 |
seeds | -0.165 |
Token | in |
Token ID | 287 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
aches | +0.143 |
asis | +0.131 |
ils | +0.129 |
seeds | +0.127 |
led | +0.126 |
Neg logit contributions | |
� | -0.142 |
She | -0.128 |
Don | -0.119 |
They | -0.116 |
Why | -0.116 |
Token | so |
Token ID | 523 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
aches | +0.134 |
seeds | +0.123 |
cream | +0.123 |
coins | +0.120 |
ils | +0.119 |
Neg logit contributions | |
� | -0.130 |
Deal | -0.126 |
Don | -0.124 |
She | -0.124 |
Why | -0.116 |
Token | many |
Token ID | 867 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
� | +0.041 |
She | +0.039 |
Deal | +0.039 |
Don | +0.038 |
Why | +0.036 |
Neg logit contributions | |
aches | -0.047 |
seeds | -0.044 |
cream | -0.043 |
coins | -0.043 |
stamps | -0.042 |
Token | ways |
Token ID | 2842 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
aches | +0.204 |
cream | +0.180 |
asis | +0.176 |
an | +0.173 |
ery | +0.169 |
Neg logit contributions | |
� | -0.235 |
She | -0.221 |
One | -0.210 |
They | -0.209 |
Don | -0.206 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aches | +0.140 |
seeds | +0.131 |
cream | +0.130 |
coins | +0.129 |
stamps | +0.128 |
Neg logit contributions | |
� | -0.098 |
Deal | -0.094 |
She | -0.094 |
Don | -0.091 |
Why | -0.087 |
Token | The |
Token ID | 383 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
Deal | +0.478 |
Why | +0.345 |
� | +0.335 |
oning | +0.323 |
Don | +0.314 |
Neg logit contributions | |
aches | -0.687 |
lands | -0.663 |
seeds | -0.658 |
ers | -0.657 |
kingdom | -0.656 |
Token | bear |
Token ID | 6842 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
Deal | +0.050 |
� | +0.050 |
Don | +0.047 |
She | +0.047 |
Today | +0.045 |
Neg logit contributions | |
aches | -0.070 |
cream | -0.064 |
ils | -0.064 |
seeds | -0.062 |
ers | -0.062 |
Token | was |
Token ID | 373 |
Feature activation | -9.03e-03 |
Pos logit contributions | |
aches | +0.157 |
cream | +0.144 |
coins | +0.141 |
seeds | +0.140 |
stamps | +0.139 |
Neg logit contributions | |
� | -0.138 |
She | -0.131 |
Don | -0.115 |
They | -0.112 |
He | -0.111 |
Token | so |
Token ID | 523 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
aches | +0.020 |
seeds | +0.020 |
ils | +0.019 |
coins | +0.019 |
stamps | +0.019 |
Neg logit contributions | |
� | -0.015 |
She | -0.013 |
Don | -0.013 |
Deal | -0.012 |
Why | -0.012 |
Token | lucky |
Token ID | 9670 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
� | +0.043 |
She | +0.042 |
Deal | +0.041 |
Don | +0.039 |
Why | +0.038 |
Neg logit contributions | |
aches | -0.048 |
seeds | -0.046 |
ils | -0.045 |
coins | -0.044 |
stamps | -0.044 |
Token | had |
Token ID | 550 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
She | +0.020 |
� | +0.020 |
Don | +0.020 |
Why | +0.019 |
Deal | +0.017 |
Neg logit contributions | |
aches | -0.035 |
cream | -0.033 |
seeds | -0.031 |
coins | -0.031 |
bread | -0.031 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
aches | +0.023 |
an | +0.022 |
asis | +0.021 |
cream | +0.021 |
ating | +0.021 |
Neg logit contributions | |
� | -0.019 |
She | -0.018 |
Don | -0.018 |
| -0.017 |
Dad | -0.017 |
Token | an |
Token ID | 281 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
aches | +0.024 |
ils | +0.022 |
seeds | +0.022 |
asis | +0.022 |
led | +0.022 |
Neg logit contributions | |
� | -0.019 |
She | -0.017 |
Don | -0.016 |
Why | -0.016 |
What | -0.015 |
Token | important |
Token ID | 1593 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
aches | +0.111 |
cream | +0.103 |
seeds | +0.099 |
stamps | +0.099 |
ers | +0.097 |
Neg logit contributions | |
� | -0.254 |
Deal | -0.242 |
She | -0.239 |
Today | -0.238 |
One | -0.236 |
Token | lesson |
Token ID | 11483 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
aches | +0.119 |
seeds | +0.103 |
coins | +0.099 |
ers | +0.098 |
cream | +0.098 |
Neg logit contributions | |
� | -0.290 |
Deal | -0.282 |
She | -0.279 |
Don | -0.275 |
Today | -0.270 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aches | +0.177 |
seeds | +0.165 |
cream | +0.163 |
coins | +0.163 |
stamps | +0.160 |
Neg logit contributions | |
� | -0.133 |
Deal | -0.132 |
She | -0.128 |
Don | -0.125 |
Why | -0.120 |
Token | That |
Token ID | 1320 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
Deal | +0.399 |
� | +0.331 |
� | +0.296 |
oning | +0.294 |
symp | +0.286 |
Neg logit contributions | |
ers | -0.664 |
kingdom | -0.659 |
aches | -0.649 |
coins | -0.639 |
coin | -0.638 |
Token | day |
Token ID | 1110 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
� | +0.146 |
She | +0.146 |
Don | +0.139 |
Today | +0.136 |
One | +0.133 |
Neg logit contributions | |
aches | -0.169 |
ts | -0.158 |
cream | -0.155 |
ers | -0.153 |
coins | -0.150 |
Token | , |
Token ID | 11 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
aches | +0.127 |
seeds | +0.119 |
cream | +0.117 |
stamps | +0.114 |
coins | +0.113 |
Neg logit contributions | |
� | -0.098 |
She | -0.094 |
Deal | -0.092 |
Don | -0.091 |
Why | -0.087 |
Token | he |
Token ID | 339 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
� | +0.216 |
Don | +0.208 |
She | +0.202 |
Deal | +0.184 |
Why | +0.183 |
Neg logit contributions | |
aches | -0.367 |
ils | -0.353 |
seeds | -0.345 |
ers | -0.340 |
led | -0.340 |
Token | gained |
Token ID | 8618 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
She | +0.027 |
� | +0.027 |
Don | +0.026 |
Deal | +0.025 |
Why | +0.024 |
Neg logit contributions | |
aches | -0.030 |
cream | -0.029 |
coins | -0.028 |
seeds | -0.027 |
ers | -0.027 |
Token | found |
Token ID | 1043 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
aches | +0.024 |
an | +0.024 |
lers | +0.023 |
asis | +0.023 |
les | +0.022 |
Neg logit contributions | |
� | -0.022 |
She | -0.021 |
| -0.021 |
Don | -0.020 |
Dad | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
aches | +0.181 |
asis | +0.160 |
ils | +0.160 |
ves | +0.159 |
seeds | +0.157 |
Neg logit contributions | |
� | -0.132 |
She | -0.122 |
Don | -0.116 |
Why | -0.114 |
What | -0.113 |
Token | special |
Token ID | 2041 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
aches | +0.201 |
ils | +0.168 |
seeds | +0.165 |
ating | +0.164 |
led | +0.160 |
Neg logit contributions | |
� | -0.330 |
Deal | -0.328 |
She | -0.318 |
Don | -0.313 |
Why | -0.304 |
Token | present |
Token ID | 1944 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
aches | +0.234 |
ils | +0.198 |
led | +0.186 |
seeds | +0.185 |
ts | +0.182 |
Neg logit contributions | |
� | -0.338 |
She | -0.328 |
Today | -0.318 |
Deal | -0.313 |
What | -0.309 |
Token | inside |
Token ID | 2641 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
aches | +0.261 |
seeds | +0.243 |
coins | +0.241 |
cream | +0.241 |
stamps | +0.236 |
Neg logit contributions | |
Deal | -0.206 |
� | -0.204 |
She | -0.197 |
Don | -0.192 |
Why | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aches | +0.238 |
seeds | +0.221 |
coins | +0.218 |
cream | +0.217 |
stamps | +0.216 |
Neg logit contributions | |
� | -0.174 |
Deal | -0.169 |
She | -0.167 |
Don | -0.163 |
Why | -0.156 |
Token | He |
Token ID | 679 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Deal | +0.522 |
oning | +0.380 |
� | +0.361 |
Don | +0.354 |
Okay | +0.346 |
Neg logit contributions | |
seeds | -0.656 |
food | -0.654 |
cream | -0.637 |
ers | -0.636 |
coin | -0.633 |
Token | thanked |
Token ID | 26280 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
� | +0.191 |
She | +0.178 |
Don | +0.159 |
Daddy | +0.155 |
Deal | +0.154 |
Neg logit contributions | |
aches | -0.210 |
iest | -0.196 |
ating | -0.193 |
cream | -0.190 |
ers | -0.187 |
Token | the |
Token ID | 262 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Deal | +0.083 |
� | +0.081 |
She | +0.079 |
Don | +0.078 |
Why | +0.076 |
Neg logit contributions | |
aches | -0.067 |
seeds | -0.061 |
coins | -0.061 |
cream | -0.061 |
stamps | -0.059 |
Token | box |
Token ID | 3091 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
aches | +0.176 |
seeds | +0.158 |
coins | +0.157 |
cream | +0.156 |
stamps | +0.151 |
Neg logit contributions | |
Deal | -0.336 |
� | -0.332 |
She | -0.326 |
Don | -0.321 |
Why | -0.313 |
Token | for |
Token ID | 329 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
aches | +0.273 |
seeds | +0.249 |
cream | +0.248 |
coins | +0.246 |
stamps | +0.242 |
Neg logit contributions | |
� | -0.262 |
Deal | -0.258 |
She | -0.254 |
Don | -0.244 |
Why | -0.235 |
Token | they |
Token ID | 484 |
Feature activation | +9.28e-03 |
Pos logit contributions | |
� | +0.128 |
She | +0.127 |
Don | +0.116 |
Daddy | +0.116 |
They | +0.115 |
Neg logit contributions | |
aches | -0.168 |
ating | -0.159 |
ers | -0.157 |
asis | -0.155 |
ery | -0.153 |
Token | had |
Token ID | 550 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
� | +0.016 |
She | +0.016 |
Don | +0.015 |
Deal | +0.014 |
Daddy | +0.014 |
Neg logit contributions | |
aches | -0.018 |
cream | -0.018 |
coins | -0.017 |
ating | -0.017 |
ers | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
aches | +0.027 |
an | +0.025 |
ating | +0.025 |
asis | +0.025 |
iest | +0.025 |
Neg logit contributions | |
� | -0.018 |
She | -0.017 |
They | -0.016 |
Dad | -0.016 |
Daddy | -0.016 |
Token | great |
Token ID | 1049 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
aches | +0.122 |
seeds | +0.108 |
coins | +0.106 |
cream | +0.106 |
stamps | +0.103 |
Neg logit contributions | |
Deal | -0.223 |
� | -0.222 |
She | -0.217 |
Don | -0.213 |
Why | -0.208 |
Token | time |
Token ID | 640 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
aches | +0.205 |
seeds | +0.179 |
coins | +0.176 |
ers | +0.175 |
stamps | +0.175 |
Neg logit contributions | |
� | -0.315 |
Deal | -0.312 |
She | -0.304 |
Don | -0.296 |
Today | -0.295 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aches | +0.054 |
seeds | +0.049 |
cream | +0.049 |
coins | +0.048 |
ers | +0.048 |
Neg logit contributions | |
� | -0.041 |
Deal | -0.040 |
She | -0.039 |
Don | -0.038 |
Why | -0.037 |
Token | They |
Token ID | 1119 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Deal | +0.371 |
� | +0.327 |
Don | +0.308 |
Why | +0.278 |
She | +0.255 |
Neg logit contributions | |
aches | -0.822 |
ils | -0.810 |
lands | -0.804 |
seeds | -0.799 |
ers | -0.789 |
Token | both |
Token ID | 1111 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
� | +0.208 |
She | +0.199 |
Deal | +0.188 |
Don | +0.186 |
Daddy | +0.178 |
Neg logit contributions | |
aches | -0.217 |
cream | -0.206 |
coins | -0.203 |
powers | -0.202 |
ating | -0.202 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
aches | +0.057 |
ating | +0.053 |
seeds | +0.053 |
stamps | +0.053 |
coins | +0.053 |
Neg logit contributions | |
� | -0.068 |
She | -0.065 |
Don | -0.061 |
Deal | -0.061 |
They | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
aches | +0.132 |
seeds | +0.121 |
coins | +0.120 |
ers | +0.119 |
cream | +0.119 |
Neg logit contributions | |
� | -0.121 |
Deal | -0.118 |
She | -0.115 |
Don | -0.113 |
Why | -0.108 |
Token | creative |
Token ID | 7325 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
aches | +0.208 |
stamps | +0.174 |
ils | +0.174 |
seeds | +0.171 |
coins | +0.171 |
Neg logit contributions | |
Deal | -0.316 |
� | -0.311 |
She | -0.302 |
Today | -0.295 |
Don | -0.295 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
aches | +0.147 |
seeds | +0.138 |
ils | +0.137 |
ery | +0.136 |
ers | +0.135 |
Neg logit contributions | |
� | -0.121 |
She | -0.113 |
Don | -0.108 |
Deal | -0.104 |
They | -0.103 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
aches | +0.256 |
ils | +0.248 |
ating | +0.216 |
stamps | +0.216 |
seeds | +0.216 |
Neg logit contributions | |
� | -0.279 |
Today | -0.269 |
She | -0.267 |
They | -0.266 |
One | -0.264 |
Token | sights |
Token ID | 21343 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ils | +0.288 |
aches | +0.278 |
ymes | +0.270 |
ery | +0.259 |
iflower | +0.243 |
Neg logit contributions | |
Today | -0.304 |
They | -0.295 |
� | -0.293 |
She | -0.289 |
One | -0.288 |
Token | they |
Token ID | 484 |
Feature activation | +9.06e-03 |
Pos logit contributions | |
aches | +0.383 |
seeds | +0.341 |
ils | +0.337 |
cream | +0.336 |
stamps | +0.335 |
Neg logit contributions | |
� | -0.222 |
She | -0.213 |
They | -0.181 |
Why | -0.172 |
Don | -0.170 |
Token | found |
Token ID | 1043 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
Deal | +0.020 |
� | +0.019 |
She | +0.019 |
Don | +0.018 |
Why | +0.018 |
Neg logit contributions | |
aches | -0.014 |
seeds | -0.013 |
coins | -0.013 |
stamps | -0.013 |
cream | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aches | +0.207 |
seeds | +0.189 |
cream | +0.182 |
stamps | +0.182 |
crown | +0.181 |
Neg logit contributions | |
� | -0.112 |
She | -0.105 |
Don | -0.094 |
Why | -0.094 |
They | -0.085 |
Token | At |
Token ID | 1629 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
Deal | +0.446 |
� | +0.318 |
Don | +0.299 |
Okay | +0.283 |
Why | +0.282 |
Neg logit contributions | |
food | -0.772 |
seeds | -0.746 |
aches | -0.735 |
ers | -0.730 |
bread | -0.730 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
� | +0.117 |
Deal | +0.116 |
She | +0.113 |
Don | +0.111 |
Why | +0.106 |
Neg logit contributions | |
aches | -0.110 |
seeds | -0.102 |
coins | -0.100 |
cream | -0.100 |
ils | -0.099 |
Token | end |
Token ID | 886 |
Feature activation | +5.91e-03 |
Pos logit contributions | |
aches | +0.285 |
coins | +0.268 |
seeds | +0.267 |
cream | +0.267 |
stamps | +0.260 |
Neg logit contributions | |
Deal | -0.231 |
� | -0.226 |
She | -0.221 |
Don | -0.215 |
Why | -0.211 |
Token | of |
Token ID | 286 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
� | +0.011 |
Deal | +0.011 |
She | +0.011 |
Don | +0.011 |
Why | +0.010 |
Neg logit contributions | |
aches | -0.011 |
seeds | -0.010 |
cream | -0.010 |
coins | -0.010 |
ils | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
aches | +0.218 |
seeds | +0.200 |
cream | +0.198 |
coins | +0.198 |
stamps | +0.193 |
Neg logit contributions | |
Deal | -0.256 |
� | -0.253 |
She | -0.246 |
Don | -0.242 |
Why | -0.235 |
Token | to |
Token ID | 284 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
aches | +0.039 |
asis | +0.037 |
seeds | +0.037 |
ils | +0.036 |
crown | +0.036 |
Neg logit contributions | |
� | -0.040 |
Don | -0.036 |
She | -0.035 |
Why | -0.034 |
Deal | -0.034 |
Token | get |
Token ID | 651 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
aches | +0.169 |
seeds | +0.162 |
coins | +0.160 |
cream | +0.159 |
ers | +0.158 |
Neg logit contributions | |
Deal | -0.159 |
� | -0.156 |
She | -0.156 |
Don | -0.153 |
Why | -0.143 |
Token | what |
Token ID | 644 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
aches | +0.121 |
asis | +0.117 |
ating | +0.112 |
ils | +0.110 |
ves | +0.110 |
Neg logit contributions | |
� | -0.138 |
She | -0.136 |
Don | -0.135 |
Why | -0.132 |
Deal | -0.127 |
Token | he |
Token ID | 339 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
� | +0.016 |
She | +0.016 |
Don | +0.015 |
Why | +0.015 |
Daddy | +0.014 |
Neg logit contributions | |
aches | -0.023 |
asis | -0.022 |
crown | -0.022 |
ers | -0.021 |
an | -0.021 |
Token | wanted |
Token ID | 2227 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
Don | +0.025 |
Why | +0.024 |
She | +0.024 |
Deal | +0.023 |
� | +0.023 |
Neg logit contributions | |
aches | -0.029 |
seeds | -0.027 |
crown | -0.027 |
nests | -0.027 |
cream | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
� | +0.067 |
She | +0.065 |
Don | +0.063 |
Why | +0.061 |
Deal | +0.060 |
Neg logit contributions | |
aches | -0.098 |
seeds | -0.091 |
cream | -0.089 |
stamps | -0.089 |
coins | -0.088 |
Token | She |
Token ID | 1375 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Deal | +0.460 |
Okay | +0.292 |
Today | +0.290 |
Don | +0.286 |
� | +0.279 |
Neg logit contributions | |
seeds | -0.704 |
coins | -0.696 |
stamps | -0.685 |
cream | -0.680 |
ers | -0.675 |
Token | said |
Token ID | 531 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
� | +0.208 |
She | +0.191 |
Deal | +0.173 |
Don | +0.172 |
Why | +0.169 |
Neg logit contributions | |
aches | -0.240 |
iest | -0.220 |
asis | -0.218 |
ating | -0.218 |
cream | -0.218 |
Token | that |
Token ID | 326 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
� | +0.138 |
Deal | +0.133 |
She | +0.132 |
Don | +0.127 |
Why | +0.124 |
Neg logit contributions | |
aches | -0.159 |
seeds | -0.148 |
cream | -0.146 |
coins | -0.145 |
ers | -0.143 |
Token | it |
Token ID | 340 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
� | +0.022 |
Don | +0.021 |
She | +0.021 |
Why | +0.020 |
Daddy | +0.019 |
Neg logit contributions | |
aches | -0.034 |
ers | -0.032 |
ils | -0.032 |
cream | -0.031 |
led | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | -8.70e-03 |
Pos logit contributions | |
aches | +0.259 |
cream | +0.238 |
crown | +0.230 |
asis | +0.230 |
coins | +0.225 |
Neg logit contributions | |
� | -0.214 |
She | -0.213 |
Why | -0.207 |
Don | -0.204 |
That | -0.189 |
Token | who |
Token ID | 508 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
aches | +0.362 |
seeds | +0.330 |
cream | +0.323 |
coins | +0.322 |
ils | +0.320 |
Neg logit contributions | |
� | -0.240 |
She | -0.234 |
Don | -0.229 |
Why | -0.219 |
Deal | -0.213 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
She | +0.126 |
� | +0.124 |
Don | +0.122 |
Why | +0.119 |
They | +0.119 |
Neg logit contributions | |
aches | -0.117 |
seeds | -0.105 |
cream | -0.105 |
coins | -0.101 |
stamps | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
aches | +0.025 |
ating | +0.022 |
ery | +0.022 |
ers | +0.022 |
led | +0.022 |
Neg logit contributions | |
� | -0.019 |
Don | -0.018 |
She | -0.018 |
Why | -0.017 |
Daddy | -0.017 |
Token | sail |
Token ID | 14936 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
aches | +0.226 |
cream | +0.217 |
seeds | +0.216 |
ers | +0.213 |
led | +0.213 |
Neg logit contributions | |
� | -0.180 |
Don | -0.175 |
She | -0.174 |
Deal | -0.170 |
One | -0.167 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
aches | +0.306 |
ils | +0.265 |
seeds | +0.261 |
ating | +0.258 |
stamps | +0.257 |
Neg logit contributions | |
� | -0.226 |
She | -0.224 |
They | -0.204 |
He | -0.203 |
Why | -0.199 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
aches | +0.220 |
ils | +0.183 |
ating | +0.177 |
ves | +0.166 |
led | +0.155 |
Neg logit contributions | |
� | -0.335 |
Don | -0.322 |
Daddy | -0.320 |
Deal | -0.317 |
Dad | -0.316 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
stamps | +0.439 |
aches | +0.434 |
seeds | +0.430 |
coins | +0.417 |
ating | +0.414 |
Neg logit contributions | |
She | -0.507 |
� | -0.503 |
One | -0.476 |
Today | -0.461 |
| -0.461 |
Token | He |
Token ID | 679 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
Deal | +0.398 |
Okay | +0.277 |
� | +0.262 |
Why | +0.250 |
Don | +0.241 |
Neg logit contributions | |
coins | -0.690 |
bread | -0.685 |
seeds | -0.684 |
ers | -0.680 |
stamps | -0.678 |
Token | had |
Token ID | 550 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
� | +0.130 |
One | +0.123 |
They | +0.116 |
Don | +0.114 |
She | +0.113 |
Neg logit contributions | |
aches | -0.139 |
cream | -0.131 |
seeds | -0.129 |
ating | -0.122 |
food | -0.121 |
Token | a |
Token ID | 257 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
aches | +0.088 |
ating | +0.084 |
led | +0.081 |
ils | +0.081 |
cream | +0.080 |
Neg logit contributions | |
She | -0.056 |
� | -0.056 |
One | -0.051 |
They | -0.050 |
He | -0.050 |
Token | big |
Token ID | 1263 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
aches | +0.182 |
ating | +0.166 |
ers | +0.164 |
ils | +0.164 |
led | +0.162 |
Neg logit contributions | |
� | -0.246 |
Deal | -0.233 |
Don | -0.225 |
She | -0.223 |
One | -0.218 |
Token | . |
Token ID | 13 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
aches | +0.431 |
cream | +0.389 |
ating | +0.389 |
seeds | +0.387 |
stamps | +0.387 |
Neg logit contributions | |
� | -0.237 |
She | -0.234 |
Don | -0.212 |
Deal | -0.207 |
Why | -0.207 |
Token | He |
Token ID | 679 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
Deal | +0.363 |
istent | +0.240 |
Okay | +0.228 |
arse | +0.220 |
arl | +0.218 |
Neg logit contributions | |
ers | -0.605 |
coins | -0.586 |
seeds | -0.574 |
kingdom | -0.565 |
food | -0.564 |
Token | was |
Token ID | 373 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
� | +0.140 |
She | +0.130 |
Don | +0.122 |
One | +0.120 |
Why | +0.117 |
Neg logit contributions | |
aches | -0.140 |
cream | -0.132 |
ating | -0.131 |
iest | -0.129 |
seeds | -0.125 |
Token | sailing |
Token ID | 28499 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
aches | +0.073 |
seeds | +0.069 |
ating | +0.069 |
cream | +0.068 |
ils | +0.068 |
Neg logit contributions | |
� | -0.050 |
She | -0.046 |
Deal | -0.046 |
Don | -0.044 |
Why | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
aches | +0.208 |
stamps | +0.188 |
seeds | +0.183 |
ils | +0.182 |
coins | +0.176 |
Neg logit contributions | |
� | -0.209 |
She | -0.192 |
Why | -0.180 |
Don | -0.178 |
He | -0.173 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
aches | +0.238 |
ils | +0.209 |
ating | +0.201 |
ves | +0.190 |
led | +0.186 |
Neg logit contributions | |
� | -0.354 |
Deal | -0.334 |
Don | -0.330 |
She | -0.320 |
Daddy | -0.317 |
Token | in |
Token ID | 287 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
stamps | +0.434 |
aches | +0.418 |
seeds | +0.414 |
coins | +0.405 |
lands | +0.390 |
Neg logit contributions | |
� | -0.570 |
She | -0.554 |
One | -0.509 |
Today | -0.507 |
Deal | -0.504 |
Token | his |
Token ID | 465 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
aches | +0.154 |
seeds | +0.142 |
coins | +0.141 |
cream | +0.140 |
stamps | +0.137 |
Neg logit contributions | |
Deal | -0.190 |
� | -0.187 |
She | -0.181 |
Don | -0.179 |
Why | -0.174 |
Token | boat |
Token ID | 8848 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
aches | +0.271 |
ils | +0.241 |
iest | +0.234 |
led | +0.232 |
ers | +0.229 |
Neg logit contributions | |
Dad | -0.334 |
� | -0.330 |
Daddy | -0.328 |
She | -0.324 |
Don | -0.321 |
Token | and |
Token ID | 290 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
aches | +0.378 |
ils | +0.346 |
stamps | +0.344 |
coins | +0.339 |
seeds | +0.339 |
Neg logit contributions | |
� | -0.254 |
She | -0.248 |
Don | -0.231 |
One | -0.220 |
Today | -0.218 |
Token | looking |
Token ID | 2045 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
� | +0.075 |
She | +0.073 |
Don | +0.071 |
Why | +0.067 |
Daddy | +0.066 |
Neg logit contributions | |
aches | -0.110 |
ymes | -0.103 |
ating | -0.102 |
ery | -0.102 |
ilt | -0.100 |
Token | castle |
Token ID | 18676 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
aches | +0.335 |
ils | +0.303 |
stamps | +0.291 |
powers | +0.289 |
seeds | +0.287 |
Neg logit contributions | |
She | -0.483 |
� | -0.479 |
They | -0.437 |
Dad | -0.436 |
Deal | -0.435 |
Token | and |
Token ID | 290 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
aches | +0.378 |
seeds | +0.351 |
stamps | +0.345 |
ils | +0.343 |
coins | +0.341 |
Neg logit contributions | |
She | -0.297 |
� | -0.294 |
Deal | -0.256 |
Don | -0.253 |
Why | -0.251 |
Token | decorated |
Token ID | 24789 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
� | +0.092 |
She | +0.091 |
Daddy | +0.087 |
Dad | +0.087 |
They | +0.084 |
Neg logit contributions | |
aches | -0.102 |
ating | -0.102 |
an | -0.100 |
asis | -0.100 |
ymes | -0.097 |
Token | it |
Token ID | 340 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
aches | +0.360 |
ery | +0.330 |
asis | +0.328 |
ils | +0.327 |
seeds | +0.324 |
Neg logit contributions | |
She | -0.239 |
� | -0.238 |
Dad | -0.207 |
They | -0.205 |
Daddy | -0.203 |
Token | with |
Token ID | 351 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
aches | +0.282 |
seeds | +0.259 |
stamps | +0.256 |
coins | +0.256 |
cream | +0.254 |
Neg logit contributions | |
� | -0.272 |
She | -0.268 |
Deal | -0.250 |
Don | -0.242 |
Today | -0.239 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
aches | +0.062 |
ating | +0.057 |
asis | +0.055 |
ils | +0.054 |
an | +0.053 |
Neg logit contributions | |
� | -0.094 |
She | -0.092 |
Daddy | -0.088 |
Dad | -0.088 |
Deal | -0.085 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
aches | +0.396 |
seeds | +0.380 |
stamps | +0.374 |
ating | +0.373 |
ils | +0.362 |
Neg logit contributions | |
� | -0.598 |
She | -0.588 |
Deal | -0.551 |
One | -0.538 |
Today | -0.537 |
Token | s |
Token ID | 82 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
aches | +0.217 |
ating | +0.197 |
powers | +0.196 |
ers | +0.195 |
ts | +0.194 |
Neg logit contributions | |
She | -0.122 |
� | -0.118 |
They | -0.104 |
One | -0.094 |
Today | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
aches | +0.169 |
ils | +0.153 |
stamps | +0.153 |
ating | +0.151 |
cream | +0.148 |
Neg logit contributions | |
� | -0.093 |
She | -0.085 |
Deal | -0.076 |
Don | -0.075 |
Dad | -0.074 |
Token | Her |
Token ID | 2332 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
Deal | +0.410 |
Don | +0.292 |
istent | +0.291 |
symp | +0.267 |
Okay | +0.263 |
Neg logit contributions | |
cream | -0.598 |
food | -0.594 |
seeds | -0.589 |
stamps | -0.586 |
coins | -0.570 |
Token | dad |
Token ID | 9955 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
� | +0.034 |
Dad | +0.032 |
Deal | +0.032 |
She | +0.032 |
Daddy | +0.031 |
Neg logit contributions | |
aches | -0.109 |
ers | -0.104 |
ils | -0.102 |
seeds | -0.101 |
ating | -0.100 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
aches | +0.250 |
iest | +0.248 |
an | +0.238 |
ade | +0.234 |
ers | +0.234 |
Neg logit contributions | |
� | -0.150 |
She | -0.128 |
Dad | -0.127 |
Daddy | -0.126 |
They | -0.124 |
Token | shore |
Token ID | 15191 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
aches | +0.256 |
ils | +0.226 |
ers | +0.215 |
ating | +0.212 |
stamps | +0.212 |
Neg logit contributions | |
� | -0.342 |
Deal | -0.327 |
She | -0.318 |
Today | -0.308 |
Daddy | -0.306 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
aches | +0.313 |
stamps | +0.291 |
ils | +0.289 |
coins | +0.289 |
cream | +0.283 |
Neg logit contributions | |
� | -0.223 |
She | -0.217 |
Don | -0.192 |
Deal | -0.189 |
They | -0.186 |
Token | They |
Token ID | 1119 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
Deal | +0.356 |
Why | +0.244 |
� | +0.244 |
Don | +0.241 |
symp | +0.228 |
Neg logit contributions | |
ers | -0.645 |
food | -0.615 |
seeds | -0.607 |
bread | -0.603 |
way | -0.601 |
Token | collected |
Token ID | 7723 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
� | +0.155 |
She | +0.147 |
Don | +0.139 |
Deal | +0.138 |
Daddy | +0.129 |
Neg logit contributions | |
aches | -0.175 |
seeds | -0.170 |
cream | -0.170 |
coins | -0.167 |
ating | -0.166 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
asis | +0.254 |
aches | +0.247 |
ating | +0.236 |
ves | +0.226 |
kingdom | +0.224 |
Neg logit contributions | |
� | -0.274 |
Dad | -0.253 |
She | -0.249 |
Daddy | -0.245 |
They | -0.231 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
aches | +0.396 |
stamps | +0.388 |
seeds | +0.379 |
ating | +0.366 |
cream | +0.365 |
Neg logit contributions | |
� | -0.582 |
She | -0.565 |
Deal | -0.512 |
They | -0.508 |
| -0.497 |
Token | s |
Token ID | 82 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
aches | +0.232 |
powers | +0.212 |
ils | +0.210 |
stamps | +0.209 |
cream | +0.209 |
Neg logit contributions | |
She | -0.111 |
� | -0.109 |
They | -0.090 |
Daddy | -0.077 |
Dad | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
aches | +0.147 |
ils | +0.133 |
stamps | +0.133 |
ating | +0.133 |
cream | +0.131 |
Neg logit contributions | |
� | -0.117 |
She | -0.107 |
Don | -0.099 |
They | -0.094 |
Daddy | -0.094 |
Token | built |
Token ID | 3170 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
� | +0.095 |
Daddy | +0.092 |
Johnny | +0.091 |
Dad | +0.091 |
She | +0.089 |
Neg logit contributions | |
ating | -0.097 |
aches | -0.096 |
ymes | -0.092 |
asis | -0.092 |
ery | -0.091 |
Token | sand |
Token ID | 6450 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
aches | +0.212 |
ating | +0.199 |
ils | +0.197 |
asis | +0.196 |
iest | +0.193 |
Neg logit contributions | |
� | -0.235 |
She | -0.212 |
They | -0.201 |
Dad | -0.189 |
| -0.187 |
Token | sand |
Token ID | 6450 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
aches | +0.269 |
ils | +0.240 |
ating | +0.232 |
coins | +0.225 |
stamps | +0.224 |
Neg logit contributions | |
� | -0.350 |
She | -0.342 |
Deal | -0.324 |
Don | -0.322 |
Today | -0.318 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
aches | +0.479 |
ils | +0.459 |
ymes | +0.452 |
stamps | +0.452 |
ating | +0.434 |
Neg logit contributions | |
She | -0.336 |
� | -0.331 |
They | -0.302 |
Dad | -0.282 |
Today | -0.279 |
Token | and |
Token ID | 290 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
� | +0.218 |
She | +0.210 |
Deal | +0.199 |
Don | +0.198 |
Why | +0.191 |
Neg logit contributions | |
aches | -0.223 |
ils | -0.206 |
ating | -0.202 |
ers | -0.201 |
seeds | -0.200 |
Token | deep |
Token ID | 2769 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
� | +0.079 |
She | +0.077 |
Don | +0.070 |
Deal | +0.068 |
Dad | +0.068 |
Neg logit contributions | |
aches | -0.090 |
ating | -0.087 |
ers | -0.084 |
asis | -0.083 |
ils | -0.083 |
Token | blue |
Token ID | 4171 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
aches | +0.314 |
ves | +0.285 |
ils | +0.277 |
stamps | +0.269 |
ery | +0.267 |
Neg logit contributions | |
She | -0.277 |
� | -0.262 |
They | -0.247 |
Today | -0.244 |
Don | -0.244 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
aches | +0.244 |
ils | +0.218 |
stamps | +0.211 |
ating | +0.210 |
seeds | +0.205 |
Neg logit contributions | |
She | -0.285 |
� | -0.282 |
Deal | -0.270 |
Don | -0.267 |
Today | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
stamps | +0.427 |
seeds | +0.408 |
aches | +0.402 |
ils | +0.393 |
cream | +0.392 |
Neg logit contributions | |
She | -0.563 |
� | -0.560 |
Today | -0.503 |
One | -0.502 |
Deal | -0.495 |
Token | |
Token ID | 220 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Deal | +0.317 |
istent | +0.214 |
� | +0.206 |
symp | +0.206 |
Don | +0.191 |
Neg logit contributions | |
seeds | -0.656 |
ers | -0.641 |
food | -0.633 |
bread | -0.633 |
coins | -0.632 |
Token |
|
Token ID | 198 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Deal | +0.240 |
Don | +0.185 |
� | +0.180 |
Why | +0.170 |
Okay | +0.153 |
Neg logit contributions | |
aches | -0.481 |
ers | -0.457 |
ves | -0.443 |
ery | -0.432 |
seeds | -0.428 |
Token |
|
Token ID | 198 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Deal | +0.351 |
Don | +0.291 |
Why | +0.269 |
� | +0.259 |
� | +0.244 |
Neg logit contributions | |
aches | -0.637 |
ers | -0.621 |
ves | -0.595 |
cream | -0.577 |
seeds | -0.566 |
Token | One |
Token ID | 3198 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Deal | +0.448 |
Don | +0.407 |
Why | +0.384 |
� | +0.382 |
Daddy | +0.362 |
Neg logit contributions | |
aches | -0.541 |
ers | -0.493 |
cream | -0.493 |
ves | -0.480 |
seeds | -0.467 |
Token | found |
Token ID | 1043 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
� | +0.173 |
She | +0.170 |
Daddy | +0.162 |
Johnny | +0.156 |
Dad | +0.155 |
Neg logit contributions | |
aches | -0.185 |
seeds | -0.177 |
asis | -0.165 |
ating | -0.164 |
bread | -0.162 |
Token | a |
Token ID | 257 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
aches | +0.245 |
asis | +0.231 |
ating | +0.222 |
ils | +0.217 |
an | +0.214 |
Neg logit contributions | |
She | -0.181 |
� | -0.181 |
Daddy | -0.157 |
Why | -0.156 |
Deal | -0.153 |
Token | charming |
Token ID | 23332 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
aches | +0.187 |
led | +0.180 |
ils | +0.179 |
ating | +0.175 |
ers | +0.166 |
Neg logit contributions | |
� | -0.259 |
Deal | -0.225 |
Daddy | -0.224 |
She | -0.223 |
Don | -0.221 |
Token | piece |
Token ID | 3704 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
aches | +0.270 |
ils | +0.247 |
led | +0.243 |
ating | +0.231 |
ers | +0.218 |
Neg logit contributions | |
� | -0.345 |
Daddy | -0.308 |
Today | -0.296 |
She | -0.295 |
Johnny | -0.294 |
Token | of |
Token ID | 286 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
aches | +0.435 |
ils | +0.387 |
stamps | +0.386 |
seeds | +0.386 |
ating | +0.381 |
Neg logit contributions | |
� | -0.365 |
She | -0.363 |
Why | -0.315 |
Don | -0.311 |
Deal | -0.300 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
aches | +0.209 |
ating | +0.207 |
led | +0.205 |
ils | +0.200 |
asis | +0.186 |
Neg logit contributions | |
� | -0.334 |
She | -0.314 |
Daddy | -0.310 |
Don | -0.303 |
Dad | -0.302 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
aches | +0.436 |
seeds | +0.426 |
stamps | +0.413 |
ating | +0.401 |
ils | +0.399 |
Neg logit contributions | |
� | -0.572 |
She | -0.564 |
Today | -0.505 |
Deal | -0.493 |
One | -0.493 |
Token | in |
Token ID | 287 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
aches | +0.206 |
seeds | +0.181 |
cream | +0.178 |
powers | +0.178 |
ating | +0.177 |
Neg logit contributions | |
She | -0.148 |
� | -0.144 |
They | -0.121 |
That | -0.117 |
Today | -0.117 |
Token | her |
Token ID | 607 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
aches | +0.171 |
seeds | +0.157 |
cream | +0.156 |
coins | +0.156 |
stamps | +0.152 |
Neg logit contributions | |
Deal | -0.176 |
� | -0.175 |
She | -0.170 |
Don | -0.166 |
Why | -0.161 |
Token | bag |
Token ID | 6131 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
aches | +0.233 |
ils | +0.200 |
ating | +0.193 |
led | +0.192 |
ers | +0.189 |
Neg logit contributions | |
She | -0.277 |
� | -0.269 |
Daddy | -0.269 |
Deal | -0.268 |
Dad | -0.267 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
aches | +0.461 |
seeds | +0.426 |
coins | +0.421 |
stamps | +0.419 |
cream | +0.417 |
Neg logit contributions | |
She | -0.316 |
� | -0.315 |
Deal | -0.296 |
Don | -0.288 |
Why | -0.277 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
aches | +0.244 |
stamps | +0.229 |
seeds | +0.227 |
ils | +0.226 |
coins | +0.219 |
Neg logit contributions | |
� | -0.172 |
She | -0.160 |
Why | -0.141 |
Don | -0.141 |
Today | -0.138 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
� | +0.166 |
Deal | +0.163 |
She | +0.159 |
Don | +0.154 |
Why | +0.146 |
Neg logit contributions | |
aches | -0.318 |
seeds | -0.297 |
cream | -0.294 |
coins | -0.293 |
stamps | -0.290 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
aches | +0.098 |
cream | +0.088 |
seeds | +0.086 |
coins | +0.086 |
iest | +0.085 |
Neg logit contributions | |
� | -0.081 |
She | -0.079 |
Don | -0.074 |
Johnny | -0.073 |
Daddy | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
aches | +0.097 |
coins | +0.087 |
ils | +0.087 |
seeds | +0.087 |
ating | +0.086 |
Neg logit contributions | |
� | -0.080 |
She | -0.078 |
Deal | -0.074 |
Don | -0.073 |
Why | -0.072 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
aches | +0.187 |
ils | +0.177 |
ers | +0.169 |
led | +0.167 |
ating | +0.166 |
Neg logit contributions | |
� | -0.254 |
She | -0.229 |
Don | -0.227 |
Deal | -0.225 |
Daddy | -0.217 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
aches | +0.299 |
ils | +0.288 |
led | +0.263 |
ers | +0.262 |
ts | +0.246 |
Neg logit contributions | |
� | -0.383 |
She | -0.349 |
Daddy | -0.338 |
Today | -0.328 |
Don | -0.327 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
aches | +0.374 |
seeds | +0.350 |
coins | +0.339 |
stamps | +0.339 |
cream | +0.332 |
Neg logit contributions | |
� | -0.648 |
She | -0.636 |
Deal | -0.624 |
Don | -0.602 |
Today | -0.592 |
Token | in |
Token ID | 287 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
aches | +0.169 |
seeds | +0.151 |
cream | +0.151 |
coins | +0.150 |
ers | +0.148 |
Neg logit contributions | |
� | -0.182 |
She | -0.179 |
Deal | -0.174 |
Don | -0.169 |
Why | -0.164 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
aches | +0.142 |
cream | +0.134 |
seeds | +0.133 |
coins | +0.131 |
stamps | +0.128 |
Neg logit contributions | |
Deal | -0.205 |
� | -0.198 |
Don | -0.192 |
Why | -0.188 |
She | -0.187 |
Token | water |
Token ID | 1660 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
aches | +0.334 |
ils | +0.318 |
led | +0.301 |
ves | +0.299 |
ating | +0.295 |
Neg logit contributions | |
� | -0.266 |
She | -0.261 |
Don | -0.253 |
Dad | -0.241 |
One | -0.240 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
aches | +0.378 |
coins | +0.349 |
seeds | +0.348 |
stamps | +0.346 |
cream | +0.344 |
Neg logit contributions | |
� | -0.254 |
She | -0.250 |
Deal | -0.239 |
Don | -0.236 |
Why | -0.227 |
Token | place |
Token ID | 1295 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
aches | +0.174 |
led | +0.162 |
ating | +0.159 |
ers | +0.158 |
ils | +0.158 |
Neg logit contributions | |
� | -0.253 |
Don | -0.236 |
Deal | -0.235 |
She | -0.226 |
Daddy | -0.220 |
Token | that |
Token ID | 326 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
aches | +0.405 |
seeds | +0.373 |
stamps | +0.368 |
coins | +0.364 |
ils | +0.359 |
Neg logit contributions | |
� | -0.316 |
She | -0.305 |
Don | -0.295 |
Deal | -0.293 |
Why | -0.287 |
Token | has |
Token ID | 468 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
aches | +0.024 |
cream | +0.022 |
stamps | +0.022 |
ils | +0.021 |
coins | +0.021 |
Neg logit contributions | |
She | -0.014 |
Don | -0.014 |
� | -0.014 |
Why | -0.013 |
Daddy | -0.012 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
aches | +0.116 |
ating | +0.108 |
an | +0.105 |
led | +0.103 |
asis | +0.101 |
Neg logit contributions | |
She | -0.080 |
Don | -0.075 |
� | -0.074 |
They | -0.070 |
One | -0.070 |
Token | of |
Token ID | 286 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
aches | +0.282 |
stamps | +0.251 |
ating | +0.250 |
ts | +0.246 |
ery | +0.246 |
Neg logit contributions | |
She | -0.181 |
� | -0.170 |
Why | -0.150 |
Don | -0.149 |
Today | -0.149 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ating | +0.183 |
aches | +0.183 |
led | +0.171 |
an | +0.167 |
asis | +0.163 |
Neg logit contributions | |
She | -0.331 |
� | -0.320 |
Don | -0.310 |
One | -0.307 |
They | -0.304 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
aches | +0.415 |
seeds | +0.406 |
ating | +0.402 |
stamps | +0.401 |
cream | +0.394 |
Neg logit contributions | |
She | -0.543 |
� | -0.520 |
Today | -0.488 |
One | -0.479 |
They | -0.477 |
Token | s |
Token ID | 82 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
aches | +0.180 |
cream | +0.162 |
seeds | +0.162 |
coins | +0.161 |
stamps | +0.160 |
Neg logit contributions | |
She | -0.161 |
� | -0.153 |
Deal | -0.142 |
Don | -0.142 |
Why | -0.141 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
aches | +0.140 |
stamps | +0.130 |
cream | +0.127 |
seeds | +0.127 |
coins | +0.126 |
Neg logit contributions | |
She | -0.123 |
� | -0.123 |
Don | -0.117 |
Deal | -0.114 |
Today | -0.112 |
Token | right |
Token ID | 826 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
� | +0.209 |
She | +0.201 |
Deal | +0.199 |
Don | +0.198 |
Why | +0.185 |
Neg logit contributions | |
aches | -0.266 |
ating | -0.245 |
ils | -0.245 |
cream | -0.244 |
seeds | -0.241 |
Token | near |
Token ID | 1474 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
aches | +0.207 |
seeds | +0.196 |
stamps | +0.192 |
coins | +0.189 |
ils | +0.187 |
Neg logit contributions | |
� | -0.190 |
She | -0.182 |
Why | -0.179 |
Deal | -0.178 |
Don | -0.177 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
aches | +0.411 |
seeds | +0.391 |
ils | +0.387 |
stamps | +0.379 |
coins | +0.377 |
Neg logit contributions | |
She | -0.253 |
� | -0.246 |
Deal | -0.232 |
Don | -0.227 |
Today | -0.212 |
Token | Tim |
Token ID | 5045 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
Deal | +0.178 |
� | +0.177 |
She | +0.170 |
Don | +0.165 |
Why | +0.157 |
Neg logit contributions | |
aches | -0.298 |
seeds | -0.280 |
coins | -0.277 |
cream | -0.277 |
stamps | -0.273 |
Token | my |
Token ID | 1820 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
aches | +0.099 |
seeds | +0.095 |
coins | +0.093 |
stamps | +0.092 |
cream | +0.092 |
Neg logit contributions | |
She | -0.049 |
� | -0.048 |
Deal | -0.047 |
Don | -0.046 |
Why | -0.044 |
Token | put |
Token ID | 1234 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
aches | +0.078 |
seeds | +0.077 |
ating | +0.073 |
coins | +0.073 |
ils | +0.073 |
Neg logit contributions | |
She | -0.078 |
� | -0.077 |
Don | -0.072 |
One | -0.069 |
They | -0.068 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
aches | +0.204 |
ils | +0.187 |
asis | +0.183 |
ating | +0.181 |
ves | +0.181 |
Neg logit contributions | |
She | -0.187 |
� | -0.182 |
Deal | -0.174 |
Johnny | -0.169 |
Daddy | -0.167 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
aches | +0.225 |
ating | +0.220 |
ils | +0.216 |
ves | +0.193 |
led | +0.192 |
Neg logit contributions | |
� | -0.351 |
Deal | -0.339 |
Don | -0.330 |
Daddy | -0.326 |
She | -0.320 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
ating | +0.405 |
stamps | +0.405 |
lands | +0.398 |
seeds | +0.385 |
aches | +0.384 |
Neg logit contributions | |
� | -0.525 |
She | -0.523 |
One | -0.466 |
| -0.462 |
Deal | -0.458 |
Token | in |
Token ID | 287 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
aches | +0.180 |
powers | +0.168 |
ils | +0.167 |
ating | +0.166 |
stamps | +0.163 |
Neg logit contributions | |
She | -0.163 |
� | -0.152 |
They | -0.134 |
He | -0.134 |
One | -0.129 |
Token | his |
Token ID | 465 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
aches | +0.150 |
cream | +0.143 |
coins | +0.141 |
seeds | +0.139 |
ers | +0.136 |
Neg logit contributions | |
Deal | -0.203 |
� | -0.196 |
Why | -0.188 |
Don | -0.188 |
She | -0.188 |
Token | pocket |
Token ID | 10000 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
aches | +0.286 |
ating | +0.274 |
ils | +0.274 |
iest | +0.270 |
ers | +0.256 |
Neg logit contributions | |
� | -0.301 |
Deal | -0.301 |
She | -0.296 |
Dad | -0.296 |
Daddy | -0.292 |
Token | and |
Token ID | 290 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
aches | +0.483 |
ils | +0.456 |
seeds | +0.444 |
ating | +0.444 |
stamps | +0.441 |
Neg logit contributions | |
She | -0.268 |
� | -0.267 |
Don | -0.229 |
Deal | -0.228 |
One | -0.227 |
Token | she |
Token ID | 673 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
Deal | +0.218 |
� | +0.197 |
Don | +0.188 |
She | +0.183 |
Why | +0.181 |
Neg logit contributions | |
aches | -0.275 |
coins | -0.263 |
cream | -0.262 |
seeds | -0.262 |
food | -0.254 |
Token | found |
Token ID | 1043 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
She | +0.012 |
� | +0.012 |
Don | +0.011 |
Why | +0.011 |
Deal | +0.011 |
Neg logit contributions | |
aches | -0.011 |
cream | -0.010 |
seeds | -0.010 |
coins | -0.009 |
ers | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
aches | +0.232 |
ating | +0.213 |
ils | +0.211 |
asis | +0.208 |
cream | +0.206 |
Neg logit contributions | |
� | -0.158 |
She | -0.155 |
Why | -0.139 |
Don | -0.138 |
Deal | -0.136 |
Token | very |
Token ID | 845 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
ils | +0.180 |
ating | +0.179 |
led | +0.177 |
aches | +0.176 |
ers | +0.173 |
Neg logit contributions | |
� | -0.250 |
Don | -0.217 |
Daddy | -0.212 |
She | -0.210 |
Deal | -0.205 |
Token | delicate |
Token ID | 19217 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ers | +0.084 |
ating | +0.081 |
ils | +0.080 |
aches | +0.074 |
ts | +0.073 |
Neg logit contributions | |
� | -0.113 |
She | -0.108 |
Dad | -0.102 |
Deal | -0.102 |
One | -0.101 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ils | +0.284 |
aches | +0.279 |
led | +0.275 |
ating | +0.267 |
ers | +0.263 |
Neg logit contributions | |
� | -0.429 |
She | -0.390 |
Don | -0.377 |
Daddy | -0.374 |
Today | -0.370 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
aches | +0.395 |
seeds | +0.379 |
stamps | +0.377 |
coins | +0.363 |
ils | +0.358 |
Neg logit contributions | |
� | -0.609 |
She | -0.604 |
Deal | -0.551 |
Today | -0.549 |
Don | -0.541 |
Token | on |
Token ID | 319 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
aches | +0.192 |
cream | +0.171 |
seeds | +0.168 |
ers | +0.168 |
ating | +0.167 |
Neg logit contributions | |
She | -0.167 |
� | -0.165 |
Why | -0.144 |
Don | -0.143 |
Deal | -0.141 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
aches | +0.233 |
seeds | +0.213 |
coins | +0.210 |
cream | +0.209 |
stamps | +0.207 |
Neg logit contributions | |
Deal | -0.335 |
� | -0.309 |
Don | -0.307 |
Why | -0.304 |
She | -0.291 |
Token | beach |
Token ID | 10481 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
aches | +0.258 |
led | +0.247 |
ating | +0.244 |
ils | +0.241 |
powers | +0.230 |
Neg logit contributions | |
� | -0.314 |
She | -0.294 |
Don | -0.287 |
Deal | -0.280 |
Daddy | -0.274 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
aches | +0.428 |
seeds | +0.394 |
stamps | +0.392 |
ils | +0.392 |
coins | +0.390 |
Neg logit contributions | |
� | -0.234 |
She | -0.233 |
Don | -0.207 |
Why | -0.200 |
They | -0.191 |
Token | sand |
Token ID | 6450 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
asis | +0.319 |
an | +0.313 |
ery | +0.309 |
aches | +0.307 |
ils | +0.307 |
Neg logit contributions | |
She | -0.404 |
� | -0.389 |
They | -0.358 |
Why | -0.331 |
One | -0.331 |
Token | cast |
Token ID | 2701 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
aches | +0.415 |
powers | +0.403 |
ils | +0.395 |
ymes | +0.394 |
riches | +0.390 |
Neg logit contributions | |
She | -0.384 |
� | -0.353 |
They | -0.338 |
Dad | -0.320 |
Why | -0.313 |
Token | les |
Token ID | 829 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
aches | +0.111 |
seeds | +0.104 |
powers | +0.099 |
crown | +0.098 |
cream | +0.096 |
Neg logit contributions | |
� | -0.281 |
She | -0.279 |
One | -0.263 |
They | -0.261 |
Today | -0.254 |
Token | and |
Token ID | 290 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
aches | +0.298 |
cream | +0.273 |
coins | +0.271 |
seeds | +0.270 |
stamps | +0.266 |
Neg logit contributions | |
She | -0.211 |
� | -0.208 |
Don | -0.183 |
Why | -0.182 |
They | -0.171 |
Token | collecting |
Token ID | 13157 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
� | +0.090 |
She | +0.089 |
Don | +0.082 |
Daddy | +0.081 |
They | +0.081 |
Neg logit contributions | |
aches | -0.089 |
an | -0.085 |
ating | -0.084 |
ery | -0.084 |
ers | -0.082 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
asis | +0.199 |
uch | +0.192 |
ating | +0.188 |
web | +0.184 |
iflower | +0.183 |
Neg logit contributions | |
� | -0.269 |
She | -0.264 |
They | -0.260 |
Dad | -0.257 |
Daddy | -0.242 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
stamps | +0.395 |
aches | +0.390 |
seeds | +0.386 |
ating | +0.377 |
coins | +0.371 |
Neg logit contributions | |
� | -0.548 |
She | -0.548 |
They | -0.499 |
One | -0.499 |
| -0.497 |
Token | s |
Token ID | 82 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
aches | +0.221 |
powers | +0.205 |
stamps | +0.202 |
cream | +0.201 |
ating | +0.201 |
Neg logit contributions | |
She | -0.125 |
� | -0.115 |
They | -0.106 |
One | -0.094 |
Why | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
aches | +0.173 |
stamps | +0.164 |
ils | +0.162 |
ymes | +0.158 |
ating | +0.157 |
Neg logit contributions | |
� | -0.084 |
She | -0.079 |
They | -0.069 |
Don | -0.068 |
Dad | -0.065 |
Token | |
Token ID | 220 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Deal | +0.395 |
istent | +0.285 |
oning | +0.268 |
arse | +0.261 |
Why | +0.257 |
Neg logit contributions | |
seeds | -0.593 |
nests | -0.582 |
stamps | -0.571 |
aches | -0.550 |
flowers | -0.549 |
Token |
|
Token ID | 198 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
Deal | +0.255 |
� | +0.214 |
Don | +0.205 |
Why | +0.185 |
Today | +0.174 |
Neg logit contributions | |
aches | -0.462 |
ers | -0.440 |
ves | -0.422 |
ery | -0.417 |
seeds | -0.404 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
aches | +0.127 |
cream | +0.119 |
coins | +0.117 |
seeds | +0.116 |
food | +0.113 |
Neg logit contributions | |
Deal | -0.174 |
� | -0.164 |
Don | -0.159 |
She | -0.155 |
Why | -0.153 |
Token | she |
Token ID | 673 |
Feature activation | +3.06e-03 |
Pos logit contributions | |
Deal | +0.233 |
� | +0.207 |
Don | +0.201 |
Why | +0.192 |
Today | +0.189 |
Neg logit contributions | |
aches | -0.253 |
cream | -0.249 |
seeds | -0.243 |
coins | -0.242 |
food | -0.239 |
Token | found |
Token ID | 1043 |
Feature activation | -9.91e-02 |
Pos logit contributions | |
She | +0.006 |
Don | +0.005 |
� | +0.005 |
Why | +0.005 |
They | +0.005 |
Neg logit contributions | |
aches | -0.006 |
cream | -0.005 |
powers | -0.005 |
coins | -0.005 |
seeds | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
aches | +0.209 |
coins | +0.189 |
ils | +0.187 |
cream | +0.186 |
ating | +0.186 |
Neg logit contributions | |
� | -0.166 |
She | -0.166 |
Deal | -0.161 |
Don | -0.154 |
Why | -0.153 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ils | +0.186 |
ating | +0.185 |
ers | +0.182 |
aches | +0.182 |
led | +0.180 |
Neg logit contributions | |
� | -0.241 |
She | -0.208 |
Daddy | -0.207 |
Don | -0.206 |
Dad | -0.201 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ils | +0.266 |
aches | +0.252 |
led | +0.245 |
ers | +0.241 |
ts | +0.238 |
Neg logit contributions | |
� | -0.391 |
She | -0.349 |
Daddy | -0.340 |
Today | -0.338 |
Dad | -0.325 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
aches | +0.368 |
seeds | +0.341 |
stamps | +0.335 |
coins | +0.334 |
cream | +0.326 |
Neg logit contributions | |
� | -0.643 |
She | -0.638 |
Deal | -0.616 |
Don | -0.598 |
Today | -0.589 |
Token | and |
Token ID | 290 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
aches | +0.180 |
cream | +0.160 |
seeds | +0.159 |
coins | +0.159 |
ers | +0.158 |
Neg logit contributions | |
She | -0.170 |
� | -0.170 |
Deal | -0.158 |
Don | -0.155 |
Why | -0.153 |
Token | showed |
Token ID | 3751 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
She | +0.092 |
� | +0.088 |
Don | +0.078 |
Deal | +0.077 |
Daddy | +0.077 |
Neg logit contributions | |
aches | -0.108 |
ating | -0.104 |
asis | -0.100 |
ers | -0.100 |
ery | -0.099 |
Token | it |
Token ID | 340 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
aches | +0.051 |
cream | +0.048 |
ating | +0.047 |
seeds | +0.046 |
ers | +0.046 |
Neg logit contributions | |
She | -0.040 |
� | -0.040 |
Don | -0.037 |
Deal | -0.037 |
Why | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
aches | +0.260 |
seeds | +0.240 |
coins | +0.237 |
cream | +0.236 |
stamps | +0.232 |
Neg logit contributions | |
Deal | -0.286 |
� | -0.281 |
She | -0.272 |
Don | -0.268 |
Why | -0.259 |
Token | shells |
Token ID | 19679 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
� | +0.108 |
She | +0.102 |
Johnny | +0.100 |
Daddy | +0.100 |
They | +0.098 |
Neg logit contributions | |
aches | -0.083 |
ating | -0.075 |
asis | -0.074 |
an | -0.074 |
ilt | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
aches | +0.440 |
seeds | +0.398 |
ils | +0.397 |
stamps | +0.397 |
cream | +0.396 |
Neg logit contributions | |
� | -0.315 |
She | -0.304 |
Don | -0.260 |
They | -0.256 |
Why | -0.254 |
Token | even |
Token ID | 772 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
� | +0.109 |
She | +0.102 |
Daddy | +0.100 |
Johnny | +0.098 |
They | +0.098 |
Neg logit contributions | |
aches | -0.087 |
ating | -0.080 |
asis | -0.079 |
ilt | -0.077 |
an | -0.076 |
Token | found |
Token ID | 1043 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
aches | +0.100 |
asis | +0.097 |
an | +0.094 |
ating | +0.091 |
ves | +0.091 |
Neg logit contributions | |
� | -0.098 |
She | -0.091 |
Johnny | -0.090 |
Sammy | -0.087 |
Daddy | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
aches | +0.214 |
asis | +0.201 |
ating | +0.193 |
ils | +0.186 |
cream | +0.185 |
Neg logit contributions | |
� | -0.191 |
She | -0.176 |
What | -0.161 |
Dad | -0.161 |
Why | -0.159 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
aches | +0.166 |
led | +0.158 |
ils | +0.156 |
ating | +0.153 |
ers | +0.150 |
Neg logit contributions | |
� | -0.259 |
Don | -0.230 |
Deal | -0.229 |
She | -0.227 |
Daddy | -0.224 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
aches | +0.401 |
seeds | +0.401 |
stamps | +0.394 |
ils | +0.373 |
coins | +0.366 |
Neg logit contributions | |
� | -0.587 |
She | -0.555 |
Today | -0.519 |
Deal | -0.512 |
One | -0.511 |
Token | for |
Token ID | 329 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
aches | +0.206 |
seeds | +0.187 |
stamps | +0.186 |
cream | +0.184 |
coins | +0.183 |
Neg logit contributions | |
� | -0.139 |
She | -0.135 |
Don | -0.119 |
Deal | -0.117 |
Why | -0.117 |
Token | his |
Token ID | 465 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
aches | +0.177 |
seeds | +0.164 |
cream | +0.161 |
stamps | +0.161 |
ating | +0.160 |
Neg logit contributions | |
� | -0.133 |
Deal | -0.126 |
She | -0.125 |
Don | -0.123 |
Why | -0.114 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
aches | +0.249 |
ers | +0.220 |
seeds | +0.216 |
ils | +0.215 |
cream | +0.214 |
Neg logit contributions | |
� | -0.342 |
Deal | -0.332 |
Don | -0.327 |
She | -0.324 |
Daddy | -0.310 |
Token | my |
Token ID | 1820 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
aches | +0.158 |
seeds | +0.147 |
coins | +0.146 |
cream | +0.146 |
stamps | +0.143 |
Neg logit contributions | |
Deal | -0.117 |
� | -0.116 |
She | -0.112 |
Don | -0.109 |
Why | -0.105 |
Token | what |
Token ID | 644 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
aches | +0.226 |
seeds | +0.208 |
coins | +0.208 |
cream | +0.208 |
stamps | +0.203 |
Neg logit contributions | |
Deal | -0.220 |
� | -0.215 |
She | -0.210 |
Don | -0.206 |
Why | -0.198 |
Token | I |
Token ID | 314 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
aches | +0.023 |
ers | +0.022 |
led | +0.022 |
cream | +0.021 |
ating | +0.021 |
Neg logit contributions | |
She | -0.006 |
Don | -0.006 |
Why | -0.005 |
� | -0.005 |
What | -0.005 |
Token | found |
Token ID | 1043 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Deal | +0.086 |
� | +0.085 |
Don | +0.085 |
She | +0.085 |
Why | +0.082 |
Neg logit contributions | |
aches | -0.057 |
seeds | -0.051 |
cream | -0.051 |
coins | -0.051 |
stamps | -0.049 |
Token | ! |
Token ID | 0 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
aches | +0.225 |
seeds | +0.197 |
crown | +0.197 |
cream | +0.197 |
coins | +0.196 |
Neg logit contributions | |
She | -0.166 |
� | -0.164 |
Why | -0.156 |
Don | -0.154 |
You | -0.143 |
Token | This |
Token ID | 770 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
Deal | +0.363 |
� | +0.290 |
symp | +0.285 |
arse | +0.256 |
� | +0.255 |
Neg logit contributions | |
seeds | -0.501 |
coins | -0.498 |
coin | -0.496 |
stamps | -0.494 |
rings | -0.483 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
aches | +0.032 |
ils | +0.029 |
ating | +0.027 |
cream | +0.027 |
seeds | +0.025 |
Neg logit contributions | |
She | -0.074 |
� | -0.074 |
One | -0.071 |
Don | -0.071 |
Today | -0.069 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
stamps | +0.464 |
seeds | +0.446 |
nests | +0.435 |
aches | +0.434 |
coins | +0.427 |
Neg logit contributions | |
She | -0.520 |
� | -0.498 |
That | -0.449 |
They | -0.445 |
Today | -0.444 |
Token | is |
Token ID | 318 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
aches | +0.190 |
ers | +0.169 |
stamps | +0.169 |
riches | +0.168 |
cream | +0.168 |
Neg logit contributions | |
She | -0.158 |
� | -0.133 |
That | -0.131 |
They | -0.128 |
Why | -0.124 |
Token | so |
Token ID | 523 |
Feature activation | -7.41e-04 |
Pos logit contributions | |
aches | +0.096 |
ating | +0.096 |
ils | +0.094 |
led | +0.094 |
ymes | +0.092 |
Neg logit contributions | |
� | -0.064 |
She | -0.057 |
Don | -0.056 |
Why | -0.052 |
One | -0.050 |
Token | pretty |
Token ID | 2495 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
aches | +0.001 |
ers | +0.001 |
ating | +0.001 |
ils | +0.001 |
stamps | +0.001 |
Neg logit contributions | |
She | -0.002 |
� | -0.002 |
Don | -0.002 |
Deal | -0.002 |
Why | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
aches | +0.411 |
ils | +0.366 |
ating | +0.361 |
ves | +0.354 |
ts | +0.352 |
Neg logit contributions | |
She | -0.311 |
� | -0.297 |
Why | -0.270 |
They | -0.256 |
Today | -0.254 |
Token | cast |
Token ID | 2701 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
aches | +0.363 |
ils | +0.345 |
powers | +0.337 |
stamps | +0.336 |
seeds | +0.325 |
Neg logit contributions | |
She | -0.438 |
� | -0.428 |
They | -0.403 |
Dad | -0.388 |
Deal | -0.386 |
Token | les |
Token ID | 829 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
aches | +0.101 |
seeds | +0.091 |
cream | +0.085 |
powers | +0.082 |
crown | +0.078 |
Neg logit contributions | |
� | -0.305 |
She | -0.300 |
One | -0.281 |
Deal | -0.279 |
Today | -0.278 |
Token | and |
Token ID | 290 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
aches | +0.289 |
cream | +0.264 |
coins | +0.263 |
seeds | +0.262 |
stamps | +0.260 |
Neg logit contributions | |
� | -0.221 |
She | -0.219 |
Don | -0.197 |
Why | -0.193 |
Deal | -0.190 |
Token | collect |
Token ID | 2824 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
� | +0.088 |
She | +0.086 |
Don | +0.081 |
Why | +0.078 |
Deal | +0.077 |
Neg logit contributions | |
aches | -0.097 |
ating | -0.091 |
ers | -0.091 |
ils | -0.089 |
seeds | -0.089 |
Token | pretty |
Token ID | 2495 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ating | +0.222 |
asis | +0.217 |
aches | +0.211 |
ils | +0.201 |
ves | +0.198 |
Neg logit contributions | |
� | -0.367 |
She | -0.366 |
Dad | -0.345 |
They | -0.331 |
Daddy | -0.331 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
aches | +0.242 |
ils | +0.221 |
ating | +0.205 |
ymes | +0.204 |
ery | +0.203 |
Neg logit contributions | |
� | -0.403 |
She | -0.399 |
Dad | -0.384 |
Daddy | -0.382 |
They | -0.382 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
aches | +0.381 |
stamps | +0.362 |
seeds | +0.361 |
cream | +0.352 |
coins | +0.349 |
Neg logit contributions | |
� | -0.588 |
She | -0.582 |
Deal | -0.542 |
Today | -0.540 |
One | -0.535 |
Token | s |
Token ID | 82 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
aches | +0.202 |
cream | +0.184 |
ating | +0.183 |
stamps | +0.181 |
coins | +0.181 |
Neg logit contributions | |
She | -0.143 |
� | -0.136 |
They | -0.121 |
One | -0.116 |
Today | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
aches | +0.164 |
stamps | +0.154 |
ils | +0.152 |
cream | +0.151 |
seeds | +0.150 |
Neg logit contributions | |
� | -0.094 |
She | -0.090 |
Deal | -0.082 |
Don | -0.081 |
Today | -0.077 |
Token | One |
Token ID | 1881 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Deal | +0.358 |
istent | +0.268 |
� | +0.236 |
symp | +0.235 |
oning | +0.231 |
Neg logit contributions | |
nests | -0.608 |
seeds | -0.607 |
stamps | -0.590 |
kingdom | -0.582 |
aches | -0.577 |
Token | day |
Token ID | 1110 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
� | +0.231 |
She | +0.228 |
Today | +0.219 |
Dad | +0.216 |
One | +0.212 |
Neg logit contributions | |
stamps | -0.259 |
ils | -0.257 |
aches | -0.256 |
ers | -0.250 |
coins | -0.242 |
Token | in |
Token ID | 287 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
aches | +0.265 |
stamps | +0.233 |
coins | +0.230 |
powers | +0.229 |
asis | +0.221 |
Neg logit contributions | |
She | -0.217 |
They | -0.208 |
� | -0.206 |
Why | -0.199 |
He | -0.195 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
aches | +0.158 |
seeds | +0.144 |
coins | +0.143 |
cream | +0.143 |
stamps | +0.140 |
Neg logit contributions | |
Deal | -0.181 |
� | -0.180 |
She | -0.175 |
Don | -0.171 |
Why | -0.166 |
Token | waves |
Token ID | 9813 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
aches | +0.258 |
coins | +0.219 |
ils | +0.217 |
stamps | +0.216 |
ers | +0.208 |
Neg logit contributions | |
She | -0.342 |
� | -0.340 |
Deal | -0.329 |
Don | -0.329 |
Why | -0.320 |
Token | and |
Token ID | 290 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
aches | +0.210 |
seeds | +0.195 |
cream | +0.194 |
coins | +0.193 |
stamps | +0.188 |
Neg logit contributions | |
Deal | -0.202 |
� | -0.197 |
She | -0.190 |
Don | -0.187 |
Why | -0.182 |
Token | collect |
Token ID | 2824 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
� | +0.076 |
She | +0.073 |
Don | +0.073 |
Deal | +0.071 |
Why | +0.066 |
Neg logit contributions | |
aches | -0.102 |
ers | -0.100 |
ils | -0.099 |
ating | -0.098 |
stamps | -0.096 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
aches | +0.243 |
ating | +0.222 |
web | +0.219 |
asis | +0.213 |
ils | +0.207 |
Neg logit contributions | |
Dad | -0.321 |
They | -0.315 |
� | -0.312 |
She | -0.312 |
He | -0.309 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
aches | +0.372 |
stamps | +0.357 |
seeds | +0.354 |
coins | +0.345 |
ating | +0.344 |
Neg logit contributions | |
She | -0.586 |
� | -0.576 |
Deal | -0.547 |
One | -0.537 |
Today | -0.536 |
Token | s |
Token ID | 82 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
aches | +0.204 |
cream | +0.186 |
seeds | +0.186 |
coins | +0.186 |
ers | +0.186 |
Neg logit contributions | |
She | -0.144 |
� | -0.138 |
Deal | -0.128 |
Don | -0.126 |
Why | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
aches | +0.182 |
stamps | +0.174 |
ils | +0.171 |
ating | +0.166 |
coins | +0.166 |
Neg logit contributions | |
� | -0.070 |
She | -0.069 |
They | -0.063 |
Don | -0.063 |
Today | -0.060 |
Token | One |
Token ID | 1881 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Deal | +0.427 |
oled | +0.312 |
Why | +0.303 |
istent | +0.294 |
oning | +0.286 |
Neg logit contributions | |
way | -0.622 |
food | -0.608 |
aches | -0.587 |
seeds | -0.583 |
bread | -0.580 |
Token | day |
Token ID | 1110 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
� | +0.252 |
She | +0.247 |
Today | +0.245 |
Don | +0.237 |
One | +0.232 |
Neg logit contributions | |
aches | -0.246 |
stamps | -0.236 |
coins | -0.230 |
ils | -0.228 |
ers | -0.225 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
aches | +0.098 |
ery | +0.091 |
seeds | +0.091 |
stamps | +0.091 |
coins | +0.091 |
Neg logit contributions | |
� | -0.064 |
She | -0.062 |
Why | -0.056 |
Don | -0.056 |
They | -0.052 |
Token | sail |
Token ID | 14936 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
aches | +0.217 |
seeds | +0.205 |
coins | +0.204 |
cream | +0.203 |
stamps | +0.202 |
Neg logit contributions | |
� | -0.191 |
Deal | -0.188 |
She | -0.186 |
Don | -0.185 |
Why | -0.172 |
Token | on |
Token ID | 319 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
aches | +0.275 |
coins | +0.240 |
seeds | +0.238 |
stamps | +0.238 |
asis | +0.235 |
Neg logit contributions | |
� | -0.248 |
She | -0.237 |
Why | -0.218 |
Don | -0.215 |
They | -0.213 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
aches | +0.302 |
ating | +0.266 |
coins | +0.266 |
cream | +0.265 |
seeds | +0.265 |
Neg logit contributions | |
� | -0.250 |
She | -0.243 |
Don | -0.226 |
Deal | -0.216 |
One | -0.216 |
Token | high |
Token ID | 1029 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
aches | +0.277 |
ating | +0.238 |
ils | +0.237 |
led | +0.230 |
stamps | +0.226 |
Neg logit contributions | |
� | -0.321 |
Deal | -0.291 |
Don | -0.291 |
Daddy | -0.289 |
She | -0.288 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
aches | +0.324 |
ils | +0.269 |
stamps | +0.257 |
led | +0.255 |
coins | +0.250 |
Neg logit contributions | |
� | -0.351 |
Today | -0.334 |
One | -0.329 |
She | -0.316 |
Daddy | -0.309 |
Token | . |
Token ID | 13 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
aches | +0.495 |
seeds | +0.476 |
stamps | +0.472 |
coins | +0.471 |
cream | +0.459 |
Neg logit contributions | |
� | -0.516 |
She | -0.499 |
Deal | -0.486 |
Don | -0.469 |
Today | -0.458 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
Deal | +0.431 |
Don | +0.343 |
istent | +0.314 |
Why | +0.311 |
� | +0.311 |
Neg logit contributions | |
ers | -0.608 |
seeds | -0.581 |
pictures | -0.571 |
ves | -0.570 |
stamps | -0.570 |
Token | was |
Token ID | 373 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
aches | +0.088 |
seeds | +0.083 |
coins | +0.081 |
cream | +0.080 |
food | +0.078 |
Neg logit contributions | |
� | -0.067 |
She | -0.062 |
Don | -0.058 |
Daddy | -0.057 |
| -0.056 |
Token | happy |
Token ID | 3772 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
aches | +0.074 |
seeds | +0.072 |
ils | +0.070 |
coins | +0.070 |
stamps | +0.069 |
Neg logit contributions | |
� | -0.045 |
She | -0.044 |
Don | -0.041 |
Why | -0.041 |
Deal | -0.040 |
Token | that |
Token ID | 326 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
aches | +0.161 |
seeds | +0.152 |
cream | +0.151 |
coins | +0.150 |
stamps | +0.146 |
Neg logit contributions | |
Deal | -0.169 |
� | -0.158 |
Don | -0.153 |
She | -0.152 |
Why | -0.146 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
aches | +0.095 |
cream | +0.083 |
coins | +0.083 |
iest | +0.082 |
ating | +0.082 |
Neg logit contributions | |
She | -0.082 |
� | -0.077 |
Don | -0.074 |
Why | -0.073 |
Daddy | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
aches | +0.085 |
seeds | +0.078 |
coins | +0.078 |
cream | +0.077 |
ils | +0.076 |
Neg logit contributions | |
� | -0.077 |
She | -0.075 |
Deal | -0.075 |
Don | -0.072 |
Why | -0.070 |
Token | bright |
Token ID | 6016 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
aches | +0.183 |
ils | +0.175 |
ers | +0.169 |
ating | +0.169 |
led | +0.167 |
Neg logit contributions | |
� | -0.252 |
She | -0.223 |
Don | -0.223 |
Deal | -0.216 |
Daddy | -0.215 |
Token | and |
Token ID | 290 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
aches | +0.285 |
ils | +0.271 |
ers | +0.246 |
ts | +0.245 |
led | +0.241 |
Neg logit contributions | |
� | -0.355 |
She | -0.345 |
Today | -0.323 |
Daddy | -0.308 |
Don | -0.307 |
Token | attractive |
Token ID | 10966 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
� | +0.128 |
She | +0.124 |
Deal | +0.120 |
Don | +0.119 |
Why | +0.116 |
Neg logit contributions | |
aches | -0.068 |
ers | -0.061 |
ils | -0.060 |
ating | -0.059 |
coins | -0.057 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
aches | +0.267 |
ils | +0.258 |
led | +0.244 |
ers | +0.243 |
ating | +0.232 |
Neg logit contributions | |
� | -0.405 |
She | -0.379 |
Daddy | -0.363 |
Don | -0.362 |
Today | -0.360 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
aches | +0.380 |
seeds | +0.359 |
stamps | +0.356 |
coins | +0.350 |
cream | +0.343 |
Neg logit contributions | |
� | -0.619 |
She | -0.617 |
Deal | -0.580 |
Don | -0.567 |
Today | -0.565 |
Token | . |
Token ID | 13 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
aches | +0.187 |
cream | +0.169 |
seeds | +0.168 |
ers | +0.168 |
coins | +0.167 |
Neg logit contributions | |
She | -0.155 |
� | -0.155 |
Deal | -0.141 |
Don | -0.140 |
Why | -0.136 |
Token | She |
Token ID | 1375 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
Deal | +0.354 |
Okay | +0.240 |
Don | +0.205 |
istent | +0.177 |
Daddy | +0.174 |
Neg logit contributions | |
seeds | -0.739 |
food | -0.720 |
coins | -0.713 |
stamps | -0.711 |
rings | -0.703 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
� | +0.173 |
She | +0.167 |
Deal | +0.162 |
Don | +0.158 |
Why | +0.153 |
Neg logit contributions | |
aches | -0.172 |
cream | -0.159 |
seeds | -0.158 |
ers | -0.157 |
coins | -0.157 |
Token | it |
Token ID | 340 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
� | +0.033 |
She | +0.033 |
Don | +0.029 |
Dad | +0.028 |
One | +0.028 |
Neg logit contributions | |
aches | -0.054 |
ating | -0.053 |
ery | -0.052 |
asis | -0.052 |
led | -0.052 |
Token | sand |
Token ID | 6450 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
aches | +0.168 |
iest | +0.159 |
ils | +0.158 |
asis | +0.157 |
powers | +0.153 |
Neg logit contributions | |
She | -0.270 |
� | -0.254 |
They | -0.250 |
He | -0.238 |
Dad | -0.235 |
Token | cast |
Token ID | 2701 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
aches | +0.337 |
powers | +0.309 |
ils | +0.307 |
seeds | +0.298 |
stamps | +0.295 |
Neg logit contributions | |
She | -0.474 |
� | -0.446 |
They | -0.431 |
Deal | -0.430 |
Don | -0.421 |
Token | les |
Token ID | 829 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
aches | +0.104 |
seeds | +0.094 |
cream | +0.091 |
powers | +0.090 |
crown | +0.085 |
Neg logit contributions | |
She | -0.297 |
� | -0.291 |
One | -0.278 |
They | -0.274 |
Today | -0.269 |
Token | and |
Token ID | 290 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
aches | +0.273 |
cream | +0.246 |
coins | +0.245 |
seeds | +0.244 |
stamps | +0.239 |
Neg logit contributions | |
She | -0.221 |
� | -0.212 |
Why | -0.196 |
Don | -0.194 |
They | -0.186 |
Token | collect |
Token ID | 2824 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
� | +0.095 |
She | +0.094 |
Deal | +0.091 |
Don | +0.090 |
Why | +0.086 |
Neg logit contributions | |
aches | -0.100 |
ers | -0.093 |
seeds | -0.092 |
cream | -0.092 |
coins | -0.092 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ating | +0.215 |
asis | +0.214 |
aches | +0.205 |
web | +0.204 |
ils | +0.193 |
Neg logit contributions | |
She | -0.355 |
� | -0.340 |
Dad | -0.336 |
They | -0.332 |
He | -0.325 |
Token | hell |
Token ID | 12758 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
aches | +0.361 |
seeds | +0.341 |
stamps | +0.333 |
cream | +0.333 |
coins | +0.326 |
Neg logit contributions | |
She | -0.610 |
� | -0.607 |
Deal | -0.581 |
Today | -0.560 |
One | -0.560 |
Token | s |
Token ID | 82 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
aches | +0.197 |
cream | +0.181 |
seeds | +0.180 |
coins | +0.180 |
ers | +0.179 |
Neg logit contributions | |
She | -0.144 |
� | -0.139 |
Deal | -0.127 |
Don | -0.125 |
Why | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
aches | +0.178 |
ils | +0.166 |
stamps | +0.166 |
ating | +0.162 |
ymes | +0.160 |
Neg logit contributions | |
She | -0.071 |
� | -0.070 |
They | -0.065 |
Don | -0.060 |
Today | -0.060 |
Token | One |
Token ID | 1881 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Deal | +0.416 |
istent | +0.323 |
Don | +0.279 |
Why | +0.276 |
Okay | +0.266 |
Neg logit contributions | |
way | -0.640 |
seeds | -0.638 |
aches | -0.633 |
necklace | -0.632 |
nests | -0.629 |
Token | day |
Token ID | 1110 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
� | +0.278 |
She | +0.272 |
Today | +0.263 |
Don | +0.259 |
Deal | +0.259 |
Neg logit contributions | |
aches | -0.238 |
stamps | -0.224 |
coins | -0.220 |
ers | -0.218 |
ils | -0.218 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
aches | +0.375 |
seeds | +0.340 |
coins | +0.330 |
cream | +0.329 |
ils | +0.326 |
Neg logit contributions | |
� | -0.220 |
She | -0.216 |
Don | -0.209 |
Why | -0.205 |
Deal | -0.192 |
Token | who |
Token ID | 508 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
� | +0.206 |
She | +0.200 |
Deal | +0.198 |
Don | +0.193 |
Why | +0.186 |
Neg logit contributions | |
aches | -0.271 |
seeds | -0.251 |
coins | -0.248 |
cream | -0.248 |
stamps | -0.245 |
Token | loved |
Token ID | 6151 |
Feature activation | -9.40e-03 |
Pos logit contributions | |
She | +0.117 |
They | +0.112 |
Don | +0.110 |
Why | +0.109 |
He | +0.109 |
Neg logit contributions | |
aches | -0.124 |
seeds | -0.116 |
cream | -0.114 |
coins | -0.111 |
bread | -0.109 |
Token | exploring |
Token ID | 13504 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
aches | +0.023 |
ery | +0.021 |
ers | +0.021 |
ating | +0.021 |
iest | +0.020 |
Neg logit contributions | |
� | -0.013 |
Don | -0.013 |
She | -0.012 |
Daddy | -0.012 |
Why | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
aches | +0.343 |
cream | +0.298 |
seeds | +0.290 |
ils | +0.288 |
ers | +0.284 |
Neg logit contributions | |
� | -0.263 |
She | -0.240 |
One | -0.232 |
They | -0.232 |
Don | -0.231 |
Token | seas |
Token ID | 21547 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
aches | +0.338 |
led | +0.284 |
ves | +0.280 |
ils | +0.275 |
ating | +0.257 |
Neg logit contributions | |
Don | -0.247 |
One | -0.242 |
| -0.240 |
� | -0.237 |
She | -0.236 |
Token | . |
Token ID | 13 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
aches | +0.565 |
stamps | +0.559 |
seeds | +0.553 |
coins | +0.550 |
cream | +0.530 |
Neg logit contributions | |
She | -0.399 |
� | -0.390 |
One | -0.359 |
Today | -0.354 |
| -0.344 |
Token |
|
Token ID | 198 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Deal | +0.408 |
� | +0.323 |
ishly | +0.312 |
Okay | +0.305 |
� | +0.304 |
Neg logit contributions | |
way | -0.670 |
skills | -0.628 |
place | -0.623 |
kingdom | -0.612 |
places | -0.609 |
Token |
|
Token ID | 198 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Deal | +0.442 |
� | +0.340 |
Don | +0.340 |
Why | +0.309 |
ishly | +0.303 |
Neg logit contributions | |
ves | -0.600 |
ers | -0.572 |
aches | -0.572 |
ating | -0.545 |
spot | -0.532 |
Token | One |
Token ID | 3198 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Deal | +0.474 |
� | +0.403 |
Don | +0.391 |
� | +0.385 |
She | +0.376 |
Neg logit contributions | |
ep | -0.542 |
ers | -0.521 |
ves | -0.517 |
ating | -0.512 |
aches | -0.508 |
Token | day |
Token ID | 1110 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
� | +0.232 |
She | +0.230 |
Today | +0.226 |
Don | +0.220 |
One | +0.216 |
Neg logit contributions | |
aches | -0.226 |
stamps | -0.207 |
ils | -0.204 |
coins | -0.202 |
seeds | -0.201 |
Token | " |
Token ID | 366 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Deal | +0.192 |
Today | +0.150 |
She | +0.140 |
Don | +0.139 |
Johnny | +0.137 |
Neg logit contributions | |
aches | -0.289 |
cream | -0.276 |
coins | -0.276 |
seeds | -0.272 |
crown | -0.270 |
Token | You |
Token ID | 1639 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
� | +0.189 |
Deal | +0.187 |
Don | +0.167 |
Today | +0.163 |
She | +0.161 |
Neg logit contributions | |
aches | -0.293 |
cream | -0.287 |
seeds | -0.285 |
ers | -0.280 |
coins | -0.276 |
Token | are |
Token ID | 389 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
She | +0.144 |
Deal | +0.144 |
Don | +0.141 |
� | +0.133 |
Why | +0.130 |
Neg logit contributions | |
aches | -0.267 |
ating | -0.257 |
cream | -0.255 |
seeds | -0.247 |
ils | -0.247 |
Token | safe |
Token ID | 3338 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
aches | +0.051 |
seeds | +0.047 |
coins | +0.047 |
cream | +0.047 |
stamps | +0.046 |
Neg logit contributions | |
Deal | -0.055 |
� | -0.055 |
She | -0.053 |
Don | -0.052 |
Why | -0.051 |
Token | now |
Token ID | 783 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
aches | +0.330 |
seeds | +0.302 |
coins | +0.298 |
cream | +0.297 |
stamps | +0.295 |
Neg logit contributions | |
� | -0.274 |
Deal | -0.274 |
She | -0.270 |
Don | -0.261 |
Why | -0.254 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
aches | +0.090 |
cream | +0.085 |
coins | +0.084 |
ers | +0.084 |
seeds | +0.083 |
Neg logit contributions | |
Deal | -0.094 |
� | -0.093 |
She | -0.087 |
Don | -0.087 |
Why | -0.084 |
Token | What |
Token ID | 1867 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
� | +0.319 |
Deal | +0.262 |
symp | +0.222 |
She | +0.218 |
'' | +0.205 |
Neg logit contributions | |
food | -0.644 |
seeds | -0.639 |
ers | -0.638 |
powers | -0.636 |
aches | -0.633 |
Token | were |
Token ID | 547 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
Don | +0.072 |
She | +0.071 |
Why | +0.067 |
� | +0.067 |
Deal | +0.066 |
Neg logit contributions | |
aches | -0.102 |
an | -0.099 |
asis | -0.097 |
led | -0.095 |
ating | -0.095 |
Token | you |
Token ID | 345 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
aches | +0.007 |
seeds | +0.007 |
ers | +0.007 |
crown | +0.007 |
cream | +0.007 |
Neg logit contributions | |
She | -0.003 |
� | -0.003 |
Deal | -0.003 |
Don | -0.003 |
Why | -0.003 |
Token | doing |
Token ID | 1804 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
aches | +0.087 |
seeds | +0.081 |
coins | +0.080 |
cream | +0.079 |
stamps | +0.078 |
Neg logit contributions | |
Deal | -0.109 |
� | -0.106 |
She | -0.104 |
Don | -0.104 |
Why | -0.100 |
Token | in |
Token ID | 287 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
aches | +0.140 |
seeds | +0.130 |
coins | +0.127 |
stamps | +0.123 |
crown | +0.123 |
Neg logit contributions | |
� | -0.121 |
Deal | -0.120 |
She | -0.119 |
Why | -0.118 |
Don | -0.118 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ils | +0.276 |
aches | +0.275 |
led | +0.258 |
ating | +0.258 |
ers | +0.248 |
Neg logit contributions | |
Don | -0.298 |
� | -0.296 |
She | -0.292 |
Deal | -0.279 |
Dad | -0.273 |
Token | until |
Token ID | 1566 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
aches | +0.355 |
ating | +0.345 |
iest | +0.333 |
cream | +0.327 |
ils | +0.324 |
Neg logit contributions | |
She | -0.146 |
� | -0.139 |
They | -0.128 |
Don | -0.119 |
One | -0.118 |
Token | it |
Token ID | 340 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
� | +0.128 |
Dad | +0.122 |
She | +0.121 |
Daddy | +0.119 |
Don | +0.118 |
Neg logit contributions | |
aches | -0.198 |
ers | -0.191 |
ils | -0.188 |
ery | -0.186 |
powers | -0.184 |
Token | is |
Token ID | 318 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
aches | +0.280 |
cream | +0.253 |
coins | +0.250 |
riches | +0.243 |
treasures | +0.243 |
Neg logit contributions | |
She | -0.264 |
� | -0.256 |
Don | -0.252 |
Today | -0.247 |
Deal | -0.245 |
Token | well |
Token ID | 880 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
aches | +0.048 |
ils | +0.045 |
coins | +0.044 |
stamps | +0.043 |
seeds | +0.043 |
Neg logit contributions | |
Deal | -0.066 |
� | -0.064 |
She | -0.063 |
Don | -0.061 |
Today | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
aches | +0.416 |
ils | +0.385 |
coins | +0.377 |
stamps | +0.377 |
ating | +0.374 |
Neg logit contributions | |
She | -0.113 |
� | -0.103 |
They | -0.097 |
Dad | -0.093 |
| -0.087 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Deal | +0.351 |
istent | +0.301 |
� | +0.282 |
oning | +0.279 |
'' | +0.272 |
Neg logit contributions | |
bread | -0.676 |
food | -0.660 |
seeds | -0.647 |
cream | -0.647 |
nests | -0.632 |
Token | they |
Token ID | 484 |
Feature activation | -3.32e-03 |
Pos logit contributions | |
� | +0.180 |
Deal | +0.176 |
She | +0.174 |
Don | +0.165 |
Why | +0.154 |
Neg logit contributions | |
aches | -0.409 |
seeds | -0.384 |
cream | -0.381 |
coins | -0.380 |
ers | -0.380 |
Token | take |
Token ID | 1011 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
aches | +0.007 |
cream | +0.006 |
seeds | +0.006 |
coins | +0.006 |
ers | +0.006 |
Neg logit contributions | |
Deal | -0.006 |
� | -0.006 |
She | -0.005 |
Don | -0.005 |
Why | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
aches | +0.195 |
asis | +0.177 |
ating | +0.164 |
iest | +0.162 |
ery | +0.161 |
Neg logit contributions | |
She | -0.122 |
They | -0.118 |
Dad | -0.116 |
� | -0.116 |
Daddy | -0.114 |
Token | back |
Token ID | 736 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
aches | +0.312 |
ils | +0.283 |
ating | +0.276 |
ts | +0.270 |
iest | +0.270 |
Neg logit contributions | |
She | -0.233 |
� | -0.223 |
Don | -0.198 |
Today | -0.196 |
They | -0.195 |
Token | sip |
Token ID | 31145 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
aches | +0.148 |
ers | +0.139 |
an | +0.137 |
ils | +0.136 |
iest | +0.136 |
Neg logit contributions | |
� | -0.127 |
She | -0.118 |
Don | -0.113 |
Deal | -0.111 |
They | -0.106 |
Token | ing |
Token ID | 278 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
aches | +0.193 |
asis | +0.173 |
coins | +0.171 |
crown | +0.170 |
stamps | +0.170 |
Neg logit contributions | |
� | -0.132 |
She | -0.125 |
They | -0.112 |
Daddy | -0.110 |
Don | -0.107 |
Token | smooth |
Token ID | 7209 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
aches | +0.367 |
asis | +0.338 |
ating | +0.318 |
iest | +0.318 |
an | +0.315 |
Neg logit contributions | |
� | -0.279 |
She | -0.258 |
They | -0.251 |
Daddy | -0.228 |
Don | -0.218 |
Token | ies |
Token ID | 444 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
aches | +0.392 |
asis | +0.354 |
kingdom | +0.338 |
ep | +0.338 |
ves | +0.334 |
Neg logit contributions | |
She | -0.301 |
� | -0.296 |
They | -0.284 |
Daddy | -0.268 |
One | -0.253 |
Token | together |
Token ID | 1978 |
Feature activation | -8.66e-03 |
Pos logit contributions | |
aches | +0.268 |
ating | +0.244 |
stamps | +0.240 |
cream | +0.240 |
coins | +0.239 |
Neg logit contributions | |
� | -0.145 |
She | -0.127 |
They | -0.106 |
Daddy | -0.105 |
Don | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
aches | +0.021 |
seeds | +0.020 |
cream | +0.019 |
stamps | +0.019 |
coins | +0.019 |
Neg logit contributions | |
� | -0.012 |
She | -0.011 |
Don | -0.010 |
Deal | -0.010 |
Why | -0.010 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Deal | +0.483 |
Why | +0.350 |
� | +0.349 |
Don | +0.344 |
Johnny | +0.334 |
Neg logit contributions | |
seeds | -0.660 |
stamps | -0.625 |
bread | -0.623 |
food | -0.613 |
ers | -0.605 |
Token | One |
Token ID | 3198 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Deal | +0.146 |
� | +0.123 |
Don | +0.108 |
She | +0.094 |
Why | +0.092 |
Neg logit contributions | |
ers | -0.361 |
aches | -0.350 |
cream | -0.342 |
seeds | -0.341 |
food | -0.340 |
Token | day |
Token ID | 1110 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
� | +0.250 |
She | +0.246 |
Today | +0.241 |
Don | +0.232 |
One | +0.231 |
Neg logit contributions | |
aches | -0.238 |
stamps | -0.231 |
coins | -0.230 |
ers | -0.223 |
seeds | -0.222 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
aches | +0.118 |
cream | +0.109 |
seeds | +0.108 |
coins | +0.108 |
ers | +0.104 |
Neg logit contributions | |
Deal | -0.133 |
� | -0.128 |
She | -0.125 |
Don | -0.124 |
Why | -0.120 |
Token | a |
Token ID | 257 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Deal | +0.300 |
� | +0.269 |
Don | +0.266 |
She | +0.255 |
Why | +0.253 |
Neg logit contributions | |
aches | -0.204 |
cream | -0.196 |
seeds | -0.194 |
coins | -0.192 |
food | -0.189 |
Token | could |
Token ID | 714 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
� | +0.020 |
She | +0.020 |
Don | +0.019 |
Deal | +0.019 |
Why | +0.018 |
Neg logit contributions | |
aches | -0.027 |
cream | -0.025 |
seeds | -0.025 |
coins | -0.024 |
stamps | -0.024 |
Token | keep |
Token ID | 1394 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
Deal | +0.065 |
� | +0.064 |
She | +0.061 |
Don | +0.060 |
Why | +0.059 |
Neg logit contributions | |
aches | -0.072 |
seeds | -0.066 |
coins | -0.065 |
cream | -0.065 |
stamps | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
aches | +0.134 |
ers | +0.122 |
ils | +0.122 |
cream | +0.121 |
iest | +0.121 |
Neg logit contributions | |
� | -0.094 |
Don | -0.094 |
She | -0.093 |
Deal | -0.089 |
Daddy | -0.089 |
Token | blanket |
Token ID | 18447 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
aches | +0.226 |
ils | +0.194 |
ating | +0.188 |
ers | +0.185 |
cream | +0.176 |
Neg logit contributions | |
She | -0.331 |
Deal | -0.321 |
� | -0.318 |
Today | -0.315 |
One | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
aches | +0.273 |
seeds | +0.252 |
ils | +0.251 |
stamps | +0.251 |
coins | +0.249 |
Neg logit contributions | |
� | -0.275 |
She | -0.268 |
Deal | -0.265 |
Don | -0.256 |
Today | -0.243 |
Token | |
Token ID | 220 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Deal | +0.497 |
Why | +0.360 |
Okay | +0.345 |
� | +0.344 |
Don | +0.342 |
Neg logit contributions | |
coins | -0.615 |
bread | -0.613 |
food | -0.611 |
seeds | -0.610 |
stamps | -0.609 |
Token |
|
Token ID | 198 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Deal | +0.307 |
� | +0.253 |
Don | +0.243 |
Why | +0.240 |
Today | +0.222 |
Neg logit contributions | |
aches | -0.475 |
ers | -0.460 |
ves | -0.453 |
ery | -0.421 |
ating | -0.419 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Deal | +0.447 |
Don | +0.368 |
Why | +0.355 |
� | +0.343 |
Today | +0.329 |
Neg logit contributions | |
ves | -0.656 |
aches | -0.654 |
ers | -0.643 |
cream | -0.614 |
bread | -0.596 |
Token | The |
Token ID | 464 |
Feature activation | +8.36e-03 |
Pos logit contributions | |
Deal | +0.576 |
Don | +0.527 |
She | +0.518 |
� | +0.514 |
Today | +0.508 |
Neg logit contributions | |
aches | -0.566 |
cream | -0.532 |
ers | -0.511 |
ves | -0.500 |
seeds | -0.499 |
Token | family |
Token ID | 1641 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
� | +0.017 |
Deal | +0.017 |
She | +0.016 |
Don | +0.016 |
Why | +0.015 |
Neg logit contributions | |
aches | -0.015 |
ils | -0.013 |
ers | -0.013 |
seeds | -0.013 |
cream | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
aches | +0.134 |
powers | +0.126 |
seeds | +0.124 |
asis | +0.121 |
potion | +0.119 |
Neg logit contributions | |
� | -0.117 |
She | -0.108 |
Dad | -0.101 |
Daddy | -0.100 |
They | -0.095 |
Token | very |
Token ID | 845 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
aches | +0.387 |
stamps | +0.340 |
ils | +0.338 |
crown | +0.337 |
necklace | +0.331 |
Neg logit contributions | |
� | -0.288 |
They | -0.288 |
| -0.284 |
Dad | -0.279 |
One | -0.272 |
Token | early |
Token ID | 1903 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
aches | +0.085 |
seeds | +0.078 |
stamps | +0.078 |
coins | +0.077 |
ers | +0.077 |
Neg logit contributions | |
� | -0.096 |
Deal | -0.094 |
She | -0.094 |
Don | -0.090 |
Why | -0.087 |
Token | in |
Token ID | 287 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
aches | +0.148 |
seeds | +0.131 |
coins | +0.128 |
ery | +0.126 |
ils | +0.126 |
Neg logit contributions | |
She | -0.096 |
� | -0.096 |
One | -0.087 |
Don | -0.086 |
Why | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
aches | +0.130 |
seeds | +0.121 |
coins | +0.119 |
cream | +0.119 |
stamps | +0.116 |
Neg logit contributions | |
Deal | -0.170 |
� | -0.168 |
She | -0.164 |
Don | -0.159 |
Why | -0.156 |
Token | morning |
Token ID | 3329 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
aches | +0.257 |
ils | +0.227 |
coins | +0.215 |
ers | +0.215 |
stamps | +0.212 |
Neg logit contributions | |
� | -0.313 |
She | -0.303 |
Don | -0.299 |
Deal | -0.296 |
One | -0.293 |
Token | . |
Token ID | 13 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
aches | +0.164 |
ils | +0.149 |
coins | +0.146 |
stamps | +0.145 |
seeds | +0.143 |
Neg logit contributions | |
� | -0.084 |
She | -0.083 |
Don | -0.079 |
Today | -0.077 |
They | -0.077 |
Token | The |
Token ID | 383 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
Deal | +0.383 |
� | +0.283 |
Don | +0.256 |
Okay | +0.247 |
Why | +0.235 |
Neg logit contributions | |
food | -0.793 |
cream | -0.783 |
seeds | -0.775 |
coins | -0.768 |
bread | -0.758 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
� | +0.040 |
Deal | +0.039 |
Don | +0.039 |
Today | +0.038 |
Dad | +0.037 |
Neg logit contributions | |
aches | -0.033 |
ils | -0.030 |
stamps | -0.028 |
ating | -0.027 |
ers | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
aches | +0.288 |
stamps | +0.265 |
ils | +0.257 |
coins | +0.252 |
ymes | +0.250 |
Neg logit contributions | |
� | -0.197 |
They | -0.191 |
Don | -0.186 |
She | -0.184 |
He | -0.181 |
Token | just |
Token ID | 655 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
aches | +0.036 |
coins | +0.033 |
ils | +0.032 |
stamps | +0.032 |
seeds | +0.032 |
Neg logit contributions | |
� | -0.039 |
Deal | -0.038 |
She | -0.037 |
Don | -0.036 |
Why | -0.035 |
Token | starting |
Token ID | 3599 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
� | +0.041 |
Deal | +0.038 |
She | +0.037 |
Don | +0.037 |
Why | +0.036 |
Neg logit contributions | |
aches | -0.050 |
stamps | -0.046 |
ils | -0.046 |
coins | -0.044 |
ves | -0.044 |
Token | park |
Token ID | 3952 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
aches | +0.219 |
ating | +0.213 |
ils | +0.209 |
led | +0.208 |
stamps | +0.195 |
Neg logit contributions | |
� | -0.345 |
She | -0.335 |
Don | -0.309 |
Deal | -0.306 |
One | -0.293 |
Token | bench |
Token ID | 7624 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
aches | +0.333 |
stamps | +0.306 |
ils | +0.305 |
seeds | +0.305 |
coins | +0.302 |
Neg logit contributions | |
� | -0.218 |
She | -0.209 |
Don | -0.186 |
They | -0.176 |
Why | -0.174 |
Token | underneath |
Token ID | 14638 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
aches | +0.383 |
seeds | +0.352 |
coins | +0.349 |
stamps | +0.348 |
ils | +0.346 |
Neg logit contributions | |
� | -0.258 |
She | -0.250 |
Deal | -0.230 |
Don | -0.230 |
Why | -0.222 |
Token | it |
Token ID | 340 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
aches | +0.238 |
seeds | +0.220 |
coins | +0.216 |
cream | +0.216 |
stamps | +0.212 |
Neg logit contributions | |
� | -0.182 |
She | -0.178 |
Deal | -0.174 |
Don | -0.167 |
Why | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
aches | +0.312 |
cream | +0.287 |
seeds | +0.285 |
coins | +0.283 |
stamps | +0.283 |
Neg logit contributions | |
� | -0.195 |
She | -0.186 |
Don | -0.169 |
Deal | -0.168 |
Why | -0.160 |
Token | " |
Token ID | 366 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Deal | +0.479 |
Don | +0.440 |
� | +0.423 |
Why | +0.408 |
She | +0.387 |
Neg logit contributions | |
aches | -0.645 |
cream | -0.630 |
coins | -0.626 |
stamps | -0.622 |
ers | -0.614 |
Token | Look |
Token ID | 8567 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
Deal | +0.200 |
� | +0.190 |
Don | +0.185 |
She | +0.179 |
Today | +0.166 |
Neg logit contributions | |
aches | -0.327 |
cream | -0.319 |
seeds | -0.307 |
ers | -0.306 |
stamps | -0.305 |
Token | Alice |
Token ID | 14862 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
� | +0.049 |
Deal | +0.047 |
She | +0.046 |
Don | +0.044 |
Why | +0.042 |
Neg logit contributions | |
aches | -0.060 |
seeds | -0.058 |
coins | -0.056 |
ers | -0.056 |
cream | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
aches | +0.134 |
seeds | +0.125 |
cream | +0.123 |
ils | +0.122 |
coins | +0.122 |
Neg logit contributions | |
� | -0.102 |
She | -0.099 |
Deal | -0.096 |
Don | -0.093 |
Why | -0.089 |
Token | that |
Token ID | 326 |
Feature activation | -1.90e-04 |
Pos logit contributions | |
� | +0.224 |
She | +0.213 |
Don | +0.207 |
Deal | +0.204 |
Why | +0.195 |
Neg logit contributions | |
aches | -0.314 |
ers | -0.300 |
led | -0.297 |
ating | -0.297 |
ils | -0.291 |
Token | 's |
Token ID | 338 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
ils | +0.000 |
led | +0.000 |
ers | +0.000 |
ating | +0.000 |
aches | +0.000 |
Neg logit contributions | |
She | -0.000 |
� | -0.000 |
Don | -0.000 |
� | -0.000 |
That | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
aches | +0.176 |
seeds | +0.161 |
cream | +0.160 |
coins | +0.160 |
stamps | +0.157 |
Neg logit contributions | |
Deal | -0.203 |
� | -0.201 |
She | -0.194 |
Don | -0.190 |
Why | -0.187 |
Token | lawyer |
Token ID | 6853 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
aches | +0.277 |
seeds | +0.249 |
led | +0.241 |
ils | +0.240 |
ers | +0.239 |
Neg logit contributions | |
She | -0.294 |
� | -0.290 |
Deal | -0.289 |
Don | -0.285 |
Why | -0.278 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
aches | +0.294 |
seeds | +0.262 |
cream | +0.256 |
ery | +0.254 |
iest | +0.249 |
Neg logit contributions | |
� | -0.266 |
She | -0.266 |
Don | -0.253 |
Why | -0.240 |
One | -0.237 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
� | +0.200 |
Deal | +0.199 |
She | +0.192 |
Don | +0.186 |
Why | +0.178 |
Neg logit contributions | |
aches | -0.331 |
seeds | -0.309 |
coins | -0.307 |
cream | -0.306 |
stamps | -0.303 |
Token | lawyer |
Token ID | 6853 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
aches | +0.322 |
seeds | +0.294 |
ils | +0.290 |
ating | +0.283 |
led | +0.282 |
Neg logit contributions | |
Deal | -0.246 |
She | -0.244 |
� | -0.241 |
Don | -0.237 |
Why | -0.234 |
Token | asked |
Token ID | 1965 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
aches | +0.308 |
seeds | +0.282 |
iest | +0.273 |
cream | +0.269 |
ery | +0.268 |
Neg logit contributions | |
� | -0.244 |
She | -0.239 |
Don | -0.214 |
Why | -0.214 |
Johnny | -0.211 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Deal | +0.110 |
� | +0.100 |
Don | +0.097 |
She | +0.097 |
Why | +0.093 |
Neg logit contributions | |
aches | -0.125 |
coins | -0.117 |
cream | -0.116 |
seeds | -0.115 |
ers | -0.114 |
Token | lot |
Token ID | 1256 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
aches | +0.180 |
seeds | +0.165 |
ils | +0.160 |
coins | +0.157 |
ers | +0.157 |
Neg logit contributions | |
� | -0.215 |
Deal | -0.210 |
She | -0.205 |
Don | -0.202 |
Why | -0.197 |
Token | of |
Token ID | 286 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
aches | +0.179 |
seeds | +0.163 |
ils | +0.158 |
asis | +0.158 |
coins | +0.157 |
Neg logit contributions | |
� | -0.177 |
She | -0.174 |
Deal | -0.168 |
Don | -0.162 |
Why | -0.162 |
Token | questions |
Token ID | 2683 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
aches | +0.276 |
asis | +0.270 |
ery | +0.259 |
soared | +0.258 |
an | +0.256 |
Neg logit contributions | |
Deal | -0.229 |
� | -0.226 |
Don | -0.225 |
She | -0.223 |
Why | -0.213 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
aches | +0.134 |
coins | +0.124 |
cream | +0.123 |
seeds | +0.122 |
ers | +0.121 |
Neg logit contributions | |
Deal | -0.127 |
� | -0.121 |
She | -0.117 |
Don | -0.117 |
Why | -0.112 |
Token | Go |
Token ID | 1514 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
� | +0.358 |
Deal | +0.279 |
symp | +0.261 |
� | +0.246 |
Johnny | +0.243 |
Neg logit contributions | |
ers | -0.632 |
coins | -0.627 |
aches | -0.626 |
stamps | -0.620 |
rings | -0.604 |
Token | away |
Token ID | 1497 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
aches | +0.067 |
cream | +0.060 |
coins | +0.058 |
ers | +0.056 |
seeds | +0.056 |
Neg logit contributions | |
Deal | -0.188 |
� | -0.186 |
She | -0.179 |
Don | -0.176 |
Why | -0.172 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
aches | +0.322 |
seeds | +0.295 |
stamps | +0.289 |
ils | +0.286 |
coins | +0.284 |
Neg logit contributions | |
She | -0.254 |
� | -0.247 |
Don | -0.244 |
Deal | -0.243 |
Why | -0.238 |
Token |
|
Token ID | 198 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
Deal | +0.410 |
istent | +0.356 |
Don | +0.338 |
� | +0.324 |
Today | +0.309 |
Neg logit contributions | |
ers | -0.529 |
cream | -0.519 |
coins | -0.518 |
bread | -0.513 |
ves | -0.510 |
Token |
|
Token ID | 198 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Deal | +0.449 |
� | +0.389 |
istent | +0.380 |
Don | +0.372 |
Why | +0.357 |
Neg logit contributions | |
ves | -0.561 |
ers | -0.543 |
aches | -0.541 |
cream | -0.512 |
lands | -0.506 |
Token | L |
Token ID | 43 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
Deal | +0.486 |
� | +0.482 |
Don | +0.471 |
Today | +0.458 |
Why | +0.431 |
Neg logit contributions | |
aches | -0.540 |
ers | -0.525 |
cream | -0.520 |
seeds | -0.497 |
coins | -0.491 |
Token | ily |
Token ID | 813 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
Deal | +0.053 |
� | +0.052 |
She | +0.051 |
Don | +0.050 |
Why | +0.048 |
Neg logit contributions | |
aches | -0.060 |
seeds | -0.055 |
cream | -0.055 |
coins | -0.055 |
stamps | -0.054 |
Token | was |
Token ID | 373 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
aches | +0.075 |
seeds | +0.070 |
iest | +0.068 |
ating | +0.066 |
powers | +0.066 |
Neg logit contributions | |
She | -0.076 |
� | -0.076 |
Why | -0.070 |
Deal | -0.070 |
Don | -0.069 |
Token | angry |
Token ID | 7954 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
seeds | +0.075 |
iest | +0.075 |
aches | +0.073 |
ils | +0.073 |
ating | +0.073 |
Neg logit contributions | |
She | -0.047 |
Deal | -0.047 |
� | -0.045 |
Why | -0.044 |
Don | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
cream | +0.116 |
- | +0.115 |
food | +0.113 |
coins | +0.113 |
ers | +0.111 |
Neg logit contributions | |
Deal | -0.270 |
� | -0.236 |
� | -0.236 |
Don | -0.229 |
Okay | -0.220 |
Token | She |
Token ID | 1375 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
Deal | +0.418 |
Johnny | +0.372 |
Okay | +0.340 |
Amen | +0.324 |
arse | +0.323 |
Neg logit contributions | |
lands | -0.560 |
stamps | -0.543 |
things | -0.536 |
holes | -0.530 |
flowers | -0.518 |
Token | marry |
Token ID | 12479 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
aches | +0.221 |
cream | +0.209 |
seeds | +0.209 |
coins | +0.209 |
ils | +0.206 |
Neg logit contributions | |
Deal | -0.167 |
� | -0.167 |
She | -0.166 |
Don | -0.162 |
Why | -0.149 |
Token | him |
Token ID | 683 |
Feature activation | -9.91e-02 |
Pos logit contributions | |
aches | +0.317 |
seeds | +0.294 |
cream | +0.291 |
coins | +0.285 |
stamps | +0.285 |
Neg logit contributions | |
She | -0.166 |
� | -0.166 |
Don | -0.154 |
Deal | -0.151 |
Why | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
aches | +0.228 |
seeds | +0.214 |
cream | +0.211 |
ils | +0.208 |
coins | +0.207 |
Neg logit contributions | |
� | -0.147 |
She | -0.143 |
Don | -0.133 |
Deal | -0.133 |
Why | -0.127 |
Token | She |
Token ID | 1375 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
Deal | +0.407 |
Don | +0.345 |
� | +0.334 |
Why | +0.313 |
Today | +0.306 |
Neg logit contributions | |
aches | -0.720 |
coins | -0.709 |
ers | -0.703 |
cream | -0.703 |
seeds | -0.690 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
� | +0.178 |
She | +0.162 |
Deal | +0.149 |
Don | +0.146 |
Daddy | +0.145 |
Neg logit contributions | |
aches | -0.204 |
ating | -0.194 |
seeds | -0.194 |
cream | -0.189 |
asis | -0.188 |
Token | and |
Token ID | 290 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
coins | +0.024 |
aches | +0.024 |
seeds | +0.024 |
crown | +0.024 |
cream | +0.023 |
Neg logit contributions | |
Deal | -0.036 |
Don | -0.034 |
� | -0.032 |
Why | -0.032 |
She | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
� | +0.113 |
She | +0.107 |
Don | +0.095 |
Deal | +0.093 |
Daddy | +0.092 |
Neg logit contributions | |
aches | -0.137 |
ating | -0.127 |
ery | -0.126 |
seeds | -0.124 |
ers | -0.124 |
Token | yes |
Token ID | 3763 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
� | +0.088 |
Deal | +0.087 |
She | +0.084 |
Don | +0.081 |
Why | +0.078 |
Neg logit contributions | |
aches | -0.149 |
seeds | -0.140 |
cream | -0.139 |
coins | -0.139 |
stamps | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Deal | +0.004 |
Don | +0.004 |
� | +0.004 |
She | +0.004 |
Why | +0.004 |
Neg logit contributions | |
aches | -0.004 |
coins | -0.004 |
cream | -0.004 |
ers | -0.004 |
seeds | -0.004 |
Token | The |
Token ID | 383 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
Deal | +0.429 |
Don | +0.378 |
� | +0.340 |
Why | +0.330 |
Today | +0.324 |
Neg logit contributions | |
ers | -0.675 |
coins | -0.661 |
cream | -0.660 |
aches | -0.651 |
seeds | -0.647 |
Token | prince |
Token ID | 19716 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Deal | +0.033 |
She | +0.033 |
� | +0.032 |
Don | +0.031 |
Dad | +0.031 |
Neg logit contributions | |
aches | -0.024 |
ating | -0.022 |
cream | -0.020 |
ils | -0.020 |
ery | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
aches | +0.260 |
seeds | +0.241 |
coins | +0.239 |
cream | +0.239 |
stamps | +0.234 |
Neg logit contributions | |
Deal | -0.230 |
� | -0.227 |
She | -0.220 |
Don | -0.215 |
Why | -0.208 |
Token | " |
Token ID | 366 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Deal | +0.207 |
Today | +0.152 |
� | +0.147 |
Don | +0.143 |
istent | +0.143 |
Neg logit contributions | |
cream | -0.216 |
coins | -0.215 |
food | -0.211 |
stamps | -0.211 |
n | -0.209 |
Token | L |
Token ID | 43 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
Deal | +0.162 |
Today | +0.151 |
� | +0.148 |
She | +0.146 |
Don | +0.140 |
Neg logit contributions | |
cream | -0.296 |
ers | -0.291 |
seeds | -0.284 |
aches | -0.282 |
stamps | -0.281 |
Token | ily |
Token ID | 813 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
Deal | +0.045 |
� | +0.044 |
Don | +0.042 |
She | +0.041 |
Why | +0.040 |
Neg logit contributions | |
aches | -0.044 |
seeds | -0.040 |
ers | -0.040 |
cream | -0.040 |
coins | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
aches | +0.089 |
seeds | +0.084 |
coins | +0.082 |
cream | +0.081 |
stamps | +0.080 |
Neg logit contributions | |
� | -0.068 |
She | -0.068 |
Deal | -0.065 |
Don | -0.065 |
Why | -0.062 |
Token | why |
Token ID | 1521 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
� | +0.183 |
Deal | +0.175 |
She | +0.174 |
Don | +0.174 |
Why | +0.165 |
Neg logit contributions | |
aches | -0.291 |
seeds | -0.271 |
ers | -0.269 |
coins | -0.269 |
cream | -0.268 |
Token | are |
Token ID | 389 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
She | +0.074 |
Don | +0.072 |
� | +0.070 |
Why | +0.067 |
Deal | +0.067 |
Neg logit contributions | |
seeds | -0.096 |
aches | -0.095 |
ers | -0.093 |
coins | -0.093 |
led | -0.091 |
Token | you |
Token ID | 345 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
aches | +0.089 |
seeds | +0.083 |
cream | +0.082 |
coins | +0.082 |
ers | +0.082 |
Neg logit contributions | |
� | -0.052 |
Deal | -0.052 |
She | -0.051 |
Don | -0.049 |
Why | -0.047 |
Token | sad |
Token ID | 6507 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
aches | +0.112 |
seeds | +0.105 |
coins | +0.102 |
cream | +0.102 |
ers | +0.101 |
Neg logit contributions | |
Deal | -0.106 |
� | -0.105 |
She | -0.102 |
Don | -0.102 |
Why | -0.097 |
Token | ? |
Token ID | 30 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
aches | +0.167 |
seeds | +0.155 |
coins | +0.155 |
ils | +0.152 |
stamps | +0.151 |
Neg logit contributions | |
She | -0.133 |
� | -0.132 |
Deal | -0.131 |
Don | -0.127 |
Why | -0.124 |
Token | You |
Token ID | 921 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
Deal | +0.269 |
� | +0.246 |
Today | +0.165 |
symp | +0.163 |
� | +0.148 |
Neg logit contributions | |
stamps | -0.559 |
ers | -0.548 |
powers | -0.543 |
matches | -0.543 |
coins | -0.543 |
Token | can |
Token ID | 460 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
Don | +0.112 |
She | +0.112 |
� | +0.105 |
Why | +0.104 |
They | +0.098 |
Neg logit contributions | |
aches | -0.188 |
seeds | -0.172 |
cream | -0.172 |
ating | -0.168 |
ers | -0.167 |
Token | squeeze |
Token ID | 21229 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
Deal | +0.062 |
� | +0.062 |
She | +0.057 |
Don | +0.057 |
Why | +0.057 |
Neg logit contributions | |
aches | -0.053 |
seeds | -0.048 |
coins | -0.047 |
cream | -0.047 |
stamps | -0.046 |
Token | it |
Token ID | 340 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
aches | +0.170 |
cream | +0.149 |
seeds | +0.148 |
coins | +0.147 |
asis | +0.146 |
Neg logit contributions | |
� | -0.143 |
She | -0.138 |
Don | -0.136 |
Deal | -0.135 |
Why | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
aches | +0.264 |
coins | +0.241 |
stamps | +0.239 |
ils | +0.239 |
cream | +0.238 |
Neg logit contributions | |
� | -0.207 |
She | -0.207 |
Deal | -0.198 |
Don | -0.190 |
One | -0.186 |
Token | most |
Token ID | 749 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
aches | +0.208 |
ils | +0.174 |
ating | +0.173 |
cream | +0.170 |
seeds | +0.170 |
Neg logit contributions | |
Deal | -0.335 |
� | -0.329 |
She | -0.321 |
Don | -0.320 |
Why | -0.306 |
Token | times |
Token ID | 1661 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
aches | +0.277 |
ers | +0.242 |
ils | +0.240 |
ating | +0.239 |
led | +0.239 |
Neg logit contributions | |
� | -0.169 |
She | -0.152 |
One | -0.152 |
Today | -0.151 |
Why | -0.148 |
Token | ." |
Token ID | 526 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
aches | +0.150 |
seeds | +0.140 |
coins | +0.139 |
cream | +0.138 |
stamps | +0.137 |
Neg logit contributions | |
� | -0.097 |
She | -0.095 |
Deal | -0.095 |
Don | -0.091 |
Why | -0.087 |
Token | They |
Token ID | 1119 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Deal | +0.366 |
Don | +0.319 |
� | +0.317 |
Okay | +0.281 |
Why | +0.280 |
Neg logit contributions | |
seeds | -0.742 |
cream | -0.738 |
food | -0.737 |
bread | -0.735 |
stamps | -0.723 |
Token | took |
Token ID | 1718 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
� | +0.208 |
She | +0.199 |
Deal | +0.197 |
Don | +0.186 |
Why | +0.180 |
Neg logit contributions | |
aches | -0.224 |
seeds | -0.205 |
coins | -0.204 |
cream | -0.203 |
ating | -0.201 |
Token | turns |
Token ID | 4962 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
aches | +0.126 |
asis | +0.119 |
an | +0.103 |
powers | +0.103 |
web | +0.103 |
Neg logit contributions | |
She | -0.102 |
� | -0.102 |
They | -0.099 |
Dad | -0.096 |
Daddy | -0.094 |
Token | squeezing |
Token ID | 40237 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
aches | +0.305 |
seeds | +0.281 |
ils | +0.272 |
coins | +0.272 |
ers | +0.270 |
Neg logit contributions | |
� | -0.260 |
She | -0.244 |
Deal | -0.233 |
Don | -0.230 |
Why | -0.226 |
Token | energy |
Token ID | 2568 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ating | +0.233 |
ils | +0.228 |
aches | +0.215 |
ves | +0.211 |
erie | +0.209 |
Neg logit contributions | |
Deal | -0.307 |
She | -0.306 |
Today | -0.296 |
� | -0.290 |
One | -0.288 |
Token | and |
Token ID | 290 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
aches | +0.334 |
ils | +0.320 |
ating | +0.318 |
ves | +0.306 |
ers | +0.303 |
Neg logit contributions | |
� | -0.201 |
She | -0.200 |
Deal | -0.192 |
Don | -0.184 |
Daddy | -0.176 |
Token | fun |
Token ID | 1257 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
Deal | +0.105 |
Don | +0.104 |
She | +0.103 |
� | +0.101 |
Daddy | +0.097 |
Neg logit contributions | |
ating | -0.128 |
ils | -0.125 |
an | -0.124 |
ers | -0.121 |
aches | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
aches | +0.179 |
seeds | +0.162 |
ils | +0.160 |
cream | +0.160 |
stamps | +0.160 |
Neg logit contributions | |
She | -0.132 |
Deal | -0.131 |
� | -0.130 |
Don | -0.125 |
Why | -0.123 |
Token | Look |
Token ID | 6803 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
� | +0.311 |
Deal | +0.244 |
She | +0.230 |
symp | +0.226 |
� | +0.224 |
Neg logit contributions | |
food | -0.718 |
seeds | -0.717 |
bread | -0.704 |
aches | -0.685 |
n | -0.681 |
Token | at |
Token ID | 379 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
aches | +0.029 |
seeds | +0.027 |
cream | +0.026 |
ers | +0.026 |
coins | +0.026 |
Neg logit contributions | |
� | -0.023 |
Deal | -0.022 |
She | -0.021 |
Don | -0.021 |
Why | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
aches | +0.090 |
led | +0.087 |
ating | +0.087 |
ers | +0.085 |
ils | +0.084 |
Neg logit contributions | |
� | -0.076 |
Don | -0.074 |
She | -0.072 |
Daddy | -0.071 |
Deal | -0.071 |
Token | calendar |
Token ID | 11845 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ils | +0.229 |
led | +0.228 |
ating | +0.217 |
aches | +0.215 |
ves | +0.208 |
Neg logit contributions | |
She | -0.313 |
Deal | -0.313 |
Don | -0.312 |
� | -0.305 |
Today | -0.295 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
aches | +0.379 |
seeds | +0.343 |
ils | +0.340 |
coins | +0.339 |
ating | +0.336 |
Neg logit contributions | |
She | -0.251 |
� | -0.242 |
Don | -0.218 |
Deal | -0.209 |
Why | -0.209 |
Token | It |
Token ID | 632 |
Feature activation | -3.00e-03 |
Pos logit contributions | |
� | +0.333 |
Deal | +0.285 |
symp | +0.284 |
'' | +0.255 |
Johnny | +0.235 |
Neg logit contributions | |
food | -0.666 |
bread | -0.664 |
seeds | -0.662 |
stamps | -0.643 |
ers | -0.633 |
Token | is |
Token ID | 318 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
aches | +0.006 |
cream | +0.006 |
iest | +0.006 |
ating | +0.006 |
coins | +0.006 |
Neg logit contributions | |
She | -0.005 |
Don | -0.005 |
Why | -0.005 |
� | -0.005 |
They | -0.005 |
Token | is |
Token ID | 318 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
� | +0.162 |
Deal | +0.161 |
She | +0.160 |
Don | +0.155 |
Why | +0.151 |
Neg logit contributions | |
aches | -0.116 |
seeds | -0.106 |
cream | -0.104 |
coins | -0.102 |
ers | -0.100 |
Token | selling |
Token ID | 6301 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
aches | +0.086 |
seeds | +0.081 |
ils | +0.080 |
ating | +0.077 |
coins | +0.077 |
Neg logit contributions | |
� | -0.080 |
She | -0.078 |
Deal | -0.077 |
Don | -0.074 |
Why | -0.074 |
Token | them |
Token ID | 606 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
aches | +0.200 |
ils | +0.192 |
asis | +0.192 |
ating | +0.190 |
ery | +0.185 |
Neg logit contributions | |
She | -0.349 |
� | -0.348 |
Dad | -0.331 |
Deal | -0.324 |
Daddy | -0.318 |
Token | to |
Token ID | 284 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
aches | +0.290 |
seeds | +0.269 |
cream | +0.263 |
coins | +0.262 |
ating | +0.261 |
Neg logit contributions | |
� | -0.217 |
She | -0.212 |
Deal | -0.208 |
Don | -0.199 |
Why | -0.193 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
aches | +0.231 |
seeds | +0.214 |
coins | +0.213 |
cream | +0.213 |
stamps | +0.209 |
Neg logit contributions | |
Deal | -0.200 |
� | -0.198 |
She | -0.191 |
Don | -0.187 |
Why | -0.181 |
Token | children |
Token ID | 1751 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
aches | +0.260 |
ils | +0.232 |
ating | +0.232 |
powers | +0.225 |
led | +0.221 |
Neg logit contributions | |
� | -0.347 |
Deal | -0.337 |
She | -0.335 |
Don | -0.329 |
Dad | -0.321 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
aches | +0.178 |
seeds | +0.165 |
coins | +0.164 |
cream | +0.164 |
stamps | +0.161 |
Neg logit contributions | |
Deal | -0.146 |
� | -0.144 |
She | -0.138 |
Don | -0.135 |
Why | -0.131 |
Token | Anna |
Token ID | 11735 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
Deal | +0.342 |
istent | +0.309 |
� | +0.302 |
� | +0.295 |
Don | +0.283 |
Neg logit contributions | |
coins | -0.659 |
stamps | -0.657 |
bread | -0.655 |
rings | -0.650 |
food | -0.650 |
Token | wants |
Token ID | 3382 |
Feature activation | -2.14e-03 |
Pos logit contributions | |
aches | +0.107 |
seeds | +0.096 |
cream | +0.095 |
coins | +0.093 |
ers | +0.091 |
Neg logit contributions | |
� | -0.138 |
She | -0.137 |
Deal | -0.137 |
Don | -0.133 |
Why | -0.130 |
Token | a |
Token ID | 257 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
aches | +0.005 |
ating | +0.005 |
asis | +0.005 |
ery | +0.005 |
led | +0.004 |
Neg logit contributions | |
� | -0.003 |
She | -0.003 |
Dad | -0.003 |
Why | -0.003 |
Don | -0.003 |
Token | balloon |
Token ID | 21190 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
aches | +0.168 |
ating | +0.157 |
ers | +0.154 |
ils | +0.154 |
seeds | +0.149 |
Neg logit contributions | |
� | -0.272 |
Deal | -0.250 |
She | -0.247 |
Don | -0.243 |
Today | -0.242 |
Token | lived |
Token ID | 5615 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
aches | +0.033 |
coins | +0.030 |
seeds | +0.030 |
stamps | +0.030 |
cream | +0.030 |
Neg logit contributions | |
She | -0.043 |
� | -0.042 |
Don | -0.040 |
Deal | -0.039 |
Why | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
aches | +0.014 |
seeds | +0.013 |
cream | +0.013 |
coins | +0.013 |
ers | +0.013 |
Neg logit contributions | |
Deal | -0.016 |
� | -0.015 |
Don | -0.015 |
She | -0.014 |
Why | -0.014 |
Token | little |
Token ID | 1310 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
aches | +0.140 |
seeds | +0.127 |
coins | +0.125 |
cream | +0.124 |
stamps | +0.121 |
Neg logit contributions | |
Deal | -0.255 |
� | -0.250 |
She | -0.243 |
Don | -0.240 |
Why | -0.235 |
Token | girl |
Token ID | 2576 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
aches | +0.119 |
cream | +0.103 |
ers | +0.101 |
coins | +0.101 |
ils | +0.101 |
Neg logit contributions | |
� | -0.161 |
She | -0.161 |
Deal | -0.158 |
Don | -0.154 |
Why | -0.150 |
Token | named |
Token ID | 3706 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
aches | +0.144 |
seeds | +0.135 |
cream | +0.133 |
coins | +0.133 |
stamps | +0.131 |
Neg logit contributions | |
Deal | -0.114 |
� | -0.112 |
She | -0.108 |
Don | -0.106 |
Why | -0.102 |
Token | Amy |
Token ID | 14235 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
Deal | +0.138 |
� | +0.130 |
Don | +0.121 |
Why | +0.115 |
She | +0.110 |
Neg logit contributions | |
aches | -0.185 |
seeds | -0.178 |
food | -0.174 |
ers | -0.172 |
coins | -0.171 |
Token | . |
Token ID | 13 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
aches | +0.109 |
seeds | +0.102 |
cream | +0.101 |
stamps | +0.099 |
coins | +0.099 |
Neg logit contributions | |
Deal | -0.103 |
� | -0.096 |
Don | -0.091 |
She | -0.090 |
Why | -0.087 |
Token | She |
Token ID | 1375 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Deal | +0.479 |
� | +0.447 |
Don | +0.438 |
Johnny | +0.397 |
Why | +0.391 |
Neg logit contributions | |
seeds | -0.602 |
aches | -0.594 |
food | -0.593 |
cream | -0.580 |
ers | -0.580 |
Token | liked |
Token ID | 8288 |
Feature activation | +8.65e-03 |
Pos logit contributions | |
She | +0.188 |
� | +0.173 |
Why | +0.169 |
They | +0.164 |
Don | +0.161 |
Neg logit contributions | |
aches | -0.203 |
coins | -0.191 |
seeds | -0.185 |
cream | -0.182 |
stamps | -0.182 |
Token | to |
Token ID | 284 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
She | +0.012 |
� | +0.012 |
Don | +0.011 |
Why | +0.010 |
They | +0.010 |
Neg logit contributions | |
aches | -0.022 |
iest | -0.021 |
ers | -0.021 |
led | -0.020 |
ating | -0.020 |
Token | play |
Token ID | 711 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
aches | +0.205 |
coins | +0.198 |
ers | +0.197 |
led | +0.196 |
cream | +0.195 |
Neg logit contributions | |
She | -0.159 |
Deal | -0.152 |
� | -0.152 |
Don | -0.149 |
One | -0.142 |
Token | nearby |
Token ID | 6716 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
aches | +0.364 |
coins | +0.334 |
cream | +0.330 |
stamps | +0.328 |
seeds | +0.327 |
Neg logit contributions | |
She | -0.288 |
� | -0.285 |
Don | -0.271 |
Why | -0.262 |
Deal | -0.260 |
Token | . |
Token ID | 13 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
aches | +0.158 |
seeds | +0.147 |
coins | +0.146 |
cream | +0.146 |
stamps | +0.143 |
Neg logit contributions | |
Deal | -0.120 |
� | -0.119 |
She | -0.115 |
Don | -0.112 |
Why | -0.108 |
Token | She |
Token ID | 1375 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Deal | +0.296 |
Okay | +0.169 |
� | +0.161 |
Don | +0.151 |
Johnny | +0.126 |
Neg logit contributions | |
seeds | -0.872 |
food | -0.853 |
stamps | -0.840 |
coins | -0.835 |
aches | -0.831 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
� | +0.145 |
She | +0.143 |
One | +0.142 |
They | +0.141 |
| +0.130 |
Neg logit contributions | |
aches | -0.241 |
iest | -0.230 |
ating | -0.225 |
cream | -0.224 |
ymes | -0.216 |
Token | her |
Token ID | 607 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
aches | +0.069 |
ating | +0.067 |
asis | +0.066 |
ils | +0.064 |
ers | +0.064 |
Neg logit contributions | |
She | -0.043 |
� | -0.041 |
Why | -0.034 |
Don | -0.034 |
Dad | -0.034 |
Token | reflection |
Token ID | 14580 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ils | +0.235 |
ers | +0.232 |
aches | +0.228 |
ating | +0.221 |
led | +0.219 |
Neg logit contributions | |
Dad | -0.190 |
Mom | -0.187 |
� | -0.185 |
Daddy | -0.183 |
She | -0.178 |
Token | in |
Token ID | 287 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
aches | +0.211 |
coins | +0.195 |
stamps | +0.193 |
seeds | +0.189 |
cream | +0.186 |
Neg logit contributions | |
She | -0.196 |
� | -0.189 |
Why | -0.170 |
Don | -0.160 |
Daddy | -0.154 |
Token | the |
Token ID | 262 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
aches | +0.152 |
ils | +0.137 |
cream | +0.135 |
ers | +0.135 |
seeds | +0.134 |
Neg logit contributions | |
� | -0.137 |
She | -0.136 |
Deal | -0.132 |
Don | -0.130 |
Why | -0.121 |
Token | water |
Token ID | 1660 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
aches | +0.256 |
ils | +0.243 |
stamps | +0.233 |
ating | +0.228 |
powers | +0.222 |
Neg logit contributions | |
She | -0.295 |
� | -0.281 |
Don | -0.279 |
One | -0.275 |
They | -0.274 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
aches | +0.325 |
coins | +0.294 |
stamps | +0.293 |
ils | +0.290 |
cream | +0.289 |
Neg logit contributions | |
She | -0.239 |
� | -0.237 |
Don | -0.221 |
Why | -0.212 |
Deal | -0.209 |
Token | and |
Token ID | 290 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
� | +0.197 |
She | +0.192 |
Don | +0.170 |
Why | +0.161 |
They | +0.150 |
Neg logit contributions | |
aches | -0.357 |
ils | -0.342 |
ating | -0.337 |
ers | -0.329 |
iest | -0.328 |
Token | mom |
Token ID | 1995 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
aches | +0.266 |
coins | +0.252 |
seeds | +0.251 |
cream | +0.250 |
stamps | +0.245 |
Neg logit contributions | |
Deal | -0.180 |
� | -0.168 |
She | -0.164 |
Don | -0.163 |
Why | -0.155 |
Token | to |
Token ID | 284 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
aches | +0.094 |
coins | +0.090 |
food | +0.088 |
cream | +0.087 |
ers | +0.087 |
Neg logit contributions | |
Deal | -0.130 |
Don | -0.113 |
� | -0.111 |
She | -0.107 |
� | -0.106 |
Token | get |
Token ID | 651 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
aches | +0.177 |
cream | +0.167 |
coins | +0.158 |
food | +0.157 |
seeds | +0.152 |
Neg logit contributions | |
Deal | -0.189 |
� | -0.183 |
Why | -0.177 |
She | -0.177 |
Today | -0.172 |
Token | her |
Token ID | 607 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
aches | +0.149 |
seeds | +0.138 |
coins | +0.136 |
cream | +0.135 |
stamps | +0.133 |
Neg logit contributions | |
Deal | -0.142 |
� | -0.142 |
She | -0.138 |
Don | -0.135 |
Why | -0.130 |
Token | some |
Token ID | 617 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
aches | +0.226 |
ils | +0.208 |
ating | +0.207 |
ers | +0.202 |
asis | +0.201 |
Neg logit contributions | |
� | -0.218 |
Deal | -0.207 |
She | -0.204 |
Don | -0.202 |
Daddy | -0.195 |
Token | clay |
Token ID | 21558 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
aches | +0.248 |
ating | +0.223 |
asis | +0.220 |
ils | +0.220 |
ers | +0.211 |
Neg logit contributions | |
� | -0.392 |
She | -0.375 |
Deal | -0.373 |
Daddy | -0.357 |
Dad | -0.356 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
aches | +0.353 |
seeds | +0.331 |
cream | +0.328 |
coins | +0.328 |
stamps | +0.321 |
Neg logit contributions | |
Deal | -0.276 |
� | -0.271 |
She | -0.262 |
Don | -0.257 |
Why | -0.247 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
Deal | +0.446 |
Don | +0.294 |
istent | +0.286 |
Okay | +0.283 |
Why | +0.281 |
Neg logit contributions | |
skills | -0.686 |
powers | -0.642 |
way | -0.640 |
food | -0.638 |
rings | -0.638 |
Token | said |
Token ID | 531 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
aches | +0.054 |
seeds | +0.050 |
coins | +0.049 |
cream | +0.048 |
stamps | +0.048 |
Neg logit contributions | |
� | -0.059 |
She | -0.057 |
Deal | -0.056 |
Don | -0.054 |
Why | -0.053 |
Token | yes |
Token ID | 3763 |
Feature activation | +9.67e-03 |
Pos logit contributions | |
� | +0.109 |
Deal | +0.105 |
She | +0.103 |
Don | +0.100 |
Why | +0.096 |
Neg logit contributions | |
aches | -0.149 |
seeds | -0.139 |
cream | -0.138 |
coins | -0.137 |
stamps | -0.136 |
Token | and |
Token ID | 290 |
Feature activation | +7.05e-02 |
Pos logit contributions | |
Deal | +0.021 |
� | +0.019 |
Don | +0.019 |
Why | +0.018 |
She | +0.018 |
Neg logit contributions | |
aches | -0.016 |
cream | -0.015 |
coins | -0.015 |
ers | -0.015 |
seeds | -0.015 |
Token | friend |
Token ID | 1545 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
aches | +0.093 |
ils | +0.092 |
ating | +0.090 |
led | +0.088 |
asis | +0.083 |
Neg logit contributions | |
Deal | -0.124 |
� | -0.123 |
One | -0.122 |
She | -0.120 |
Today | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
aches | +0.110 |
ating | +0.100 |
seeds | +0.099 |
cream | +0.097 |
ils | +0.096 |
Neg logit contributions | |
� | -0.060 |
She | -0.059 |
Why | -0.057 |
Don | -0.057 |
Deal | -0.054 |
Token | He |
Token ID | 679 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
� | +0.333 |
Deal | +0.326 |
istent | +0.305 |
symp | +0.304 |
arse | +0.276 |
Neg logit contributions | |
cream | -0.656 |
food | -0.650 |
ers | -0.648 |
aches | -0.638 |
bread | -0.619 |
Token | has |
Token ID | 468 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
She | +0.173 |
Don | +0.169 |
Deal | +0.166 |
Why | +0.163 |
� | +0.162 |
Neg logit contributions | |
aches | -0.133 |
cream | -0.120 |
ating | -0.119 |
seeds | -0.118 |
iest | -0.115 |
Token | only |
Token ID | 691 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
ating | +0.101 |
aches | +0.100 |
asis | +0.099 |
an | +0.097 |
ils | +0.095 |
Neg logit contributions | |
She | -0.066 |
� | -0.063 |
Don | -0.062 |
One | -0.060 |
Deal | -0.058 |
Token | his |
Token ID | 465 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
aches | +0.100 |
ating | +0.094 |
asis | +0.094 |
ves | +0.094 |
ils | +0.092 |
Neg logit contributions | |
She | -0.088 |
� | -0.087 |
Don | -0.084 |
One | -0.083 |
Why | -0.082 |
Token | red |
Token ID | 2266 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
aches | +0.253 |
ils | +0.230 |
ers | +0.222 |
seeds | +0.221 |
ating | +0.221 |
Neg logit contributions | |
Deal | -0.358 |
� | -0.356 |
She | -0.343 |
Don | -0.342 |
Today | -0.329 |
Token | blocks |
Token ID | 7021 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
aches | +0.262 |
seeds | +0.235 |
cream | +0.232 |
coins | +0.232 |
stamps | +0.226 |
Neg logit contributions | |
Deal | -0.422 |
� | -0.419 |
She | -0.409 |
Don | -0.402 |
Why | -0.391 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
aches | +0.424 |
seeds | +0.397 |
ils | +0.392 |
stamps | +0.388 |
coins | +0.386 |
Neg logit contributions | |
� | -0.247 |
She | -0.242 |
Deal | -0.236 |
Don | -0.226 |
Why | -0.217 |
Token | And |
Token ID | 843 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Deal | +0.327 |
� | +0.315 |
symp | +0.308 |
istent | +0.303 |
arse | +0.274 |
Neg logit contributions | |
cream | -0.670 |
ers | -0.666 |
food | -0.660 |
aches | -0.650 |
coins | -0.632 |
Token | his |
Token ID | 465 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
� | +0.207 |
She | +0.205 |
Don | +0.189 |
Deal | +0.185 |
Why | +0.179 |
Neg logit contributions | |
aches | -0.411 |
ating | -0.389 |
ils | -0.385 |
seeds | -0.381 |
ers | -0.378 |
Token | on |
Token ID | 319 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
aches | +0.238 |
seeds | +0.215 |
ils | +0.212 |
cream | +0.212 |
coins | +0.206 |
Neg logit contributions | |
She | -0.268 |
� | -0.267 |
Don | -0.250 |
Why | -0.248 |
Deal | -0.247 |
Token | it |
Token ID | 340 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
aches | +0.229 |
coins | +0.213 |
seeds | +0.210 |
cream | +0.207 |
stamps | +0.204 |
Neg logit contributions | |
Deal | -0.294 |
� | -0.277 |
Don | -0.269 |
She | -0.266 |
Why | -0.266 |
Token | . |
Token ID | 13 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
aches | +0.282 |
seeds | +0.261 |
coins | +0.261 |
cream | +0.260 |
ers | +0.255 |
Neg logit contributions | |
Deal | -0.233 |
� | -0.224 |
She | -0.214 |
Don | -0.212 |
Why | -0.204 |
Token | He |
Token ID | 679 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
Deal | +0.398 |
� | +0.307 |
Don | +0.290 |
Okay | +0.252 |
Why | +0.244 |
Neg logit contributions | |
aches | -0.809 |
cream | -0.801 |
coins | -0.797 |
ers | -0.762 |
food | -0.748 |
Token | thinks |
Token ID | 6834 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
� | +0.197 |
Deal | +0.196 |
She | +0.194 |
Don | +0.188 |
Why | +0.183 |
Neg logit contributions | |
aches | -0.154 |
seeds | -0.140 |
cream | -0.139 |
coins | -0.136 |
ers | -0.135 |
Token | it |
Token ID | 340 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
� | +0.179 |
Deal | +0.172 |
She | +0.171 |
Don | +0.166 |
Why | +0.160 |
Neg logit contributions | |
aches | -0.185 |
seeds | -0.172 |
cream | -0.170 |
coins | -0.166 |
ers | -0.166 |
Token | is |
Token ID | 318 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
aches | +0.265 |
cream | +0.239 |
seeds | +0.231 |
bread | +0.227 |
coins | +0.224 |
Neg logit contributions | |
She | -0.278 |
� | -0.262 |
Why | -0.258 |
Don | -0.252 |
That | -0.249 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
aches | +0.053 |
seeds | +0.048 |
cream | +0.047 |
ils | +0.047 |
ating | +0.047 |
Neg logit contributions | |
� | -0.058 |
She | -0.056 |
Deal | -0.056 |
Don | -0.054 |
Why | -0.053 |
Token | best |
Token ID | 1266 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
aches | +0.219 |
ils | +0.207 |
led | +0.205 |
ers | +0.194 |
ating | +0.194 |
Neg logit contributions | |
� | -0.340 |
Deal | -0.340 |
She | -0.333 |
Don | -0.327 |
Why | -0.311 |
Token | top |
Token ID | 1353 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
aches | +0.188 |
ils | +0.174 |
led | +0.171 |
ers | +0.167 |
seeds | +0.167 |
Neg logit contributions | |
She | -0.279 |
� | -0.278 |
Today | -0.265 |
Don | -0.264 |
Deal | -0.261 |
Token | ever |
Token ID | 1683 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
aches | +0.210 |
seeds | +0.191 |
ils | +0.189 |
stamps | +0.187 |
cream | +0.186 |
Neg logit contributions | |
� | -0.129 |
She | -0.125 |
Don | -0.114 |
Why | -0.111 |
Today | -0.107 |
Token | open |
Token ID | 1280 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
aches | +0.220 |
ils | +0.213 |
ating | +0.209 |
stamps | +0.209 |
seeds | +0.208 |
Neg logit contributions | |
Deal | -0.197 |
� | -0.190 |
Don | -0.186 |
She | -0.186 |
One | -0.166 |
Token | the |
Token ID | 262 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
aches | +0.307 |
seeds | +0.280 |
cream | +0.277 |
coins | +0.275 |
stamps | +0.270 |
Neg logit contributions | |
� | -0.321 |
Deal | -0.318 |
She | -0.311 |
Don | -0.304 |
Why | -0.293 |
Token | rough |
Token ID | 5210 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
aches | +0.211 |
ils | +0.191 |
ating | +0.191 |
ves | +0.185 |
led | +0.182 |
Neg logit contributions | |
Deal | -0.398 |
� | -0.397 |
She | -0.385 |
Don | -0.382 |
What | -0.368 |
Token | nut |
Token ID | 6701 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
aches | +0.244 |
ils | +0.223 |
ating | +0.207 |
led | +0.205 |
ves | +0.200 |
Neg logit contributions | |
� | -0.346 |
She | -0.334 |
One | -0.332 |
He | -0.322 |
Don | -0.319 |
Token | with |
Token ID | 351 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
aches | +0.390 |
stamps | +0.358 |
cream | +0.356 |
seeds | +0.354 |
ils | +0.354 |
Neg logit contributions | |
� | -0.291 |
She | -0.280 |
Deal | -0.262 |
Don | -0.258 |
Why | -0.245 |
Token | his |
Token ID | 465 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
aches | +0.077 |
cream | +0.070 |
seeds | +0.069 |
ils | +0.068 |
ers | +0.068 |
Neg logit contributions | |
� | -0.081 |
Deal | -0.080 |
She | -0.079 |
Don | -0.077 |
Why | -0.073 |
Token | big |
Token ID | 1263 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
aches | +0.253 |
ils | +0.234 |
ers | +0.229 |
cream | +0.228 |
ating | +0.228 |
Neg logit contributions | |
Deal | -0.341 |
� | -0.340 |
Don | -0.325 |
She | -0.324 |
Today | -0.306 |
Token | paws |
Token ID | 49193 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
aches | +0.291 |
ils | +0.270 |
ers | +0.264 |
ating | +0.263 |
cream | +0.262 |
Neg logit contributions | |
� | -0.355 |
Deal | -0.350 |
She | -0.336 |
Don | -0.333 |
Today | -0.324 |
Token | . |
Token ID | 13 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
aches | +0.262 |
coins | +0.244 |
seeds | +0.244 |
cream | +0.241 |
ers | +0.237 |
Neg logit contributions | |
Deal | -0.254 |
� | -0.237 |
Don | -0.231 |
She | -0.230 |
Why | -0.224 |
Token | With |
Token ID | 2080 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
Deal | +0.344 |
� | +0.259 |
Don | +0.238 |
Daddy | +0.230 |
Why | +0.220 |
Neg logit contributions | |
coins | -0.724 |
ers | -0.708 |
cream | -0.699 |
seeds | -0.691 |
food | -0.688 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Deal | +0.043 |
� | +0.042 |
She | +0.041 |
Don | +0.040 |
Why | +0.039 |
Neg logit contributions | |
aches | -0.041 |
seeds | -0.038 |
coins | -0.038 |
cream | -0.038 |
stamps | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
aches | +0.207 |
ating | +0.187 |
cream | +0.183 |
ves | +0.181 |
asis | +0.181 |
Neg logit contributions | |
She | -0.151 |
� | -0.147 |
Don | -0.143 |
Why | -0.139 |
Deal | -0.136 |
Token | mail |
Token ID | 6920 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
aches | +0.172 |
ils | +0.164 |
led | +0.163 |
ating | +0.151 |
ers | +0.151 |
Neg logit contributions | |
� | -0.246 |
She | -0.225 |
Don | -0.221 |
Daddy | -0.214 |
Deal | -0.213 |
Token | box |
Token ID | 3091 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
aches | +0.197 |
seeds | +0.171 |
ils | +0.168 |
coins | +0.168 |
cream | +0.166 |
Neg logit contributions | |
� | -0.300 |
Deal | -0.292 |
She | -0.292 |
Don | -0.285 |
Why | -0.278 |
Token | in |
Token ID | 287 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
aches | +0.315 |
seeds | +0.283 |
ils | +0.282 |
ating | +0.278 |
stamps | +0.277 |
Neg logit contributions | |
She | -0.274 |
� | -0.268 |
Deal | -0.243 |
Why | -0.243 |
Don | -0.241 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
aches | +0.166 |
led | +0.149 |
ils | +0.149 |
cream | +0.147 |
seeds | +0.146 |
Neg logit contributions | |
She | -0.142 |
� | -0.140 |
Deal | -0.135 |
Don | -0.135 |
Daddy | -0.127 |
Token | garden |
Token ID | 11376 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
aches | +0.245 |
ils | +0.208 |
coins | +0.206 |
ers | +0.204 |
ating | +0.202 |
Neg logit contributions | |
� | -0.336 |
She | -0.334 |
Deal | -0.328 |
Don | -0.321 |
Why | -0.314 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
aches | +0.404 |
ils | +0.362 |
ating | +0.358 |
stamps | +0.355 |
seeds | +0.355 |
Neg logit contributions | |
She | -0.340 |
� | -0.335 |
Don | -0.312 |
Deal | -0.309 |
Why | -0.304 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
Deal | +0.453 |
� | +0.433 |
Don | +0.415 |
She | +0.407 |
Why | +0.395 |
Neg logit contributions | |
aches | -0.563 |
seeds | -0.526 |
cream | -0.524 |
coins | -0.521 |
stamps | -0.509 |
Token | said |
Token ID | 531 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
aches | +0.092 |
seeds | +0.085 |
cream | +0.085 |
ating | +0.084 |
coins | +0.084 |
Neg logit contributions | |
� | -0.084 |
She | -0.082 |
Deal | -0.077 |
Don | -0.076 |
Why | -0.073 |
Token | excited |
Token ID | 6568 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
Deal | +0.124 |
Don | +0.113 |
� | +0.112 |
Why | +0.109 |
She | +0.108 |
Neg logit contributions | |
aches | -0.104 |
seeds | -0.095 |
cream | -0.095 |
coins | -0.095 |
crown | -0.092 |
Token | ly |
Token ID | 306 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
aches | +0.076 |
cream | +0.073 |
seeds | +0.069 |
coins | +0.069 |
ers | +0.068 |
Neg logit contributions | |
Deal | -0.193 |
� | -0.184 |
Don | -0.183 |
Why | -0.174 |
She | -0.174 |