Token | were |
Token ID | 547 |
Feature activation | -6.61e-03 |
Pos logit contributions | |
ors | +0.144 |
badges | +0.141 |
round | +0.140 |
affe | +0.140 |
cream | +0.140 |
Neg logit contributions | |
also | -0.091 |
known | -0.067 |
narrative | -0.064 |
sch | -0.062 |
Acc | -0.057 |
Token | no |
Token ID | 645 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
also | +0.006 |
known | +0.005 |
Acc | +0.004 |
sch | +0.004 |
Always | +0.004 |
Neg logit contributions | |
ors | -0.013 |
affe | -0.012 |
cream | -0.012 |
badges | -0.012 |
ops | -0.012 |
Token | other |
Token ID | 584 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ors | +0.082 |
cream | +0.077 |
badges | +0.076 |
ops | +0.075 |
ted | +0.074 |
Neg logit contributions | |
also | -0.070 |
known | -0.067 |
welcome | -0.066 |
narrative | -0.065 |
Deal | -0.063 |
Token | av |
Token ID | 1196 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ors | +0.159 |
round | +0.155 |
cream | +0.153 |
stret | +0.141 |
affe | +0.141 |
Neg logit contributions | |
welcome | -0.127 |
also | -0.125 |
narrative | -0.116 |
winning | -0.116 |
Do | -0.115 |
Token | oc |
Token ID | 420 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
ors | +0.076 |
badges | +0.072 |
affe | +0.070 |
cream | +0.065 |
les | +0.060 |
Neg logit contributions | |
Deal | -0.215 |
Acc | -0.213 |
also | -0.213 |
sch | -0.205 |
narrative | -0.205 |
Token | ados |
Token ID | 22484 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
badges | +0.070 |
stret | +0.069 |
les | +0.063 |
le | +0.060 |
round | +0.058 |
Neg logit contributions | |
Deal | -0.151 |
Always | -0.149 |
narrative | -0.147 |
winning | -0.147 |
welcome | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ors | +0.551 |
badges | +0.551 |
affe | +0.545 |
cream | +0.531 |
oos | +0.505 |
Neg logit contributions | |
also | -0.564 |
doing | -0.480 |
known | -0.467 |
living | -0.456 |
supposed | -0.454 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
badges | +0.259 |
ors | +0.258 |
cream | +0.246 |
affe | +0.246 |
les | +0.243 |
Neg logit contributions | |
also | -0.144 |
Deal | -0.141 |
Do | -0.135 |
Acc | -0.135 |
Always | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
Deal | +0.014 |
Acc | +0.013 |
narrative | +0.013 |
sch | +0.012 |
Amen | +0.012 |
Neg logit contributions | |
ors | -0.020 |
affe | -0.019 |
badges | -0.019 |
cream | -0.019 |
ops | -0.018 |
Token | The |
Token ID | 464 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
also | +0.011 |
Deal | +0.010 |
Acc | +0.010 |
narrative | +0.009 |
known | +0.009 |
Neg logit contributions | |
ors | -0.022 |
badges | -0.021 |
cream | -0.021 |
affe | -0.021 |
ted | -0.020 |
Token | little |
Token ID | 1310 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
ors | +0.126 |
affe | +0.125 |
badges | +0.124 |
cream | +0.120 |
als | +0.116 |
Neg logit contributions | |
Deal | -0.135 |
Acc | -0.132 |
also | -0.130 |
Amen | -0.127 |
sch | -0.127 |
Token | broken |
Token ID | 5445 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ors | +0.246 |
cream | +0.234 |
ages | +0.222 |
als | +0.218 |
lets | +0.218 |
Neg logit contributions | |
also | -0.155 |
sch | -0.141 |
narrative | -0.137 |
Deal | -0.128 |
welcome | -0.126 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
cream | +0.194 |
ages | +0.187 |
ors | +0.179 |
rots | +0.175 |
ados | +0.173 |
Neg logit contributions | |
also | -0.170 |
sch | -0.158 |
first | -0.156 |
living | -0.151 |
doing | -0.146 |
Token | - |
Token ID | 12 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
cream | +0.123 |
als | +0.121 |
ked | +0.111 |
rots | +0.111 |
badges | +0.108 |
Neg logit contributions | |
also | -0.156 |
day | -0.153 |
living | -0.150 |
doing | -0.150 |
sch | -0.150 |
Token | go |
Token ID | 2188 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
badges | +0.210 |
ors | +0.197 |
cheeks | +0.186 |
als | +0.185 |
ados | +0.184 |
Neg logit contributions | |
also | -0.196 |
Acc | -0.187 |
Amen | -0.186 |
Do | -0.175 |
known | -0.175 |
Token | - |
Token ID | 12 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ados | +0.098 |
badges | +0.098 |
affe | +0.093 |
cream | +0.088 |
als | +0.087 |
Neg logit contributions | |
also | -0.170 |
first | -0.159 |
sch | -0.158 |
living | -0.156 |
doing | -0.156 |
Token | round |
Token ID | 744 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
badges | +0.100 |
cheeks | +0.082 |
ados | +0.079 |
ors | +0.077 |
ishes | +0.075 |
Neg logit contributions | |
also | -0.298 |
Acc | -0.292 |
Amen | -0.290 |
Do | -0.281 |
sch | -0.281 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
badges | +0.573 |
affe | +0.558 |
ors | +0.529 |
cream | +0.524 |
tal | +0.514 |
Neg logit contributions | |
also | -0.542 |
first | -0.458 |
sch | -0.449 |
winning | -0.440 |
doing | -0.436 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
als | +0.133 |
badges | +0.133 |
affe | +0.127 |
ted | +0.127 |
aw | +0.124 |
Neg logit contributions | |
Amen | -0.214 |
Acc | -0.214 |
sch | -0.204 |
narrative | -0.203 |
willing | -0.203 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
Deal | +0.019 |
Acc | +0.018 |
narrative | +0.018 |
Amen | +0.017 |
known | +0.017 |
Neg logit contributions | |
ors | -0.024 |
badges | -0.023 |
affe | -0.023 |
cream | -0.023 |
les | -0.022 |
Token | But |
Token ID | 1537 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
Deal | +0.022 |
Amen | +0.021 |
sch | +0.020 |
Acc | +0.020 |
Always | +0.020 |
Neg logit contributions | |
aw | -0.018 |
affe | -0.018 |
ops | -0.018 |
badges | -0.018 |
les | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
ted | +0.066 |
ors | +0.065 |
badges | +0.063 |
als | +0.063 |
affe | +0.061 |
Neg logit contributions | |
Deal | -0.121 |
Acc | -0.119 |
Amen | -0.117 |
sch | -0.114 |
narrative | -0.112 |
Token | says |
Token ID | 1139 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
ors | +0.344 |
badges | +0.337 |
cream | +0.335 |
affe | +0.334 |
ops | +0.316 |
Neg logit contributions | |
also | -0.236 |
Deal | -0.193 |
Always | -0.185 |
sch | -0.183 |
Acc | -0.179 |
Token | they |
Token ID | 484 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
ors | +0.074 |
cream | +0.070 |
les | +0.067 |
badges | +0.065 |
ales | +0.064 |
Neg logit contributions | |
Do | -0.067 |
also | -0.066 |
welcome | -0.059 |
doing | -0.054 |
known | -0.054 |
Token | are |
Token ID | 389 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
ors | +0.169 |
cream | +0.165 |
badges | +0.163 |
affe | +0.162 |
ted | +0.159 |
Neg logit contributions | |
also | -0.063 |
Deal | -0.050 |
Amen | -0.045 |
Do | -0.045 |
narrative | -0.045 |
Token | av |
Token ID | 1196 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Deal | +0.034 |
Acc | +0.034 |
also | +0.032 |
narrative | +0.031 |
sch | +0.031 |
Neg logit contributions | |
badges | -0.075 |
ors | -0.075 |
cream | -0.072 |
affe | -0.072 |
als | -0.070 |
Token | oc |
Token ID | 420 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
ors | +0.069 |
badges | +0.066 |
affe | +0.063 |
cream | +0.059 |
les | +0.054 |
Neg logit contributions | |
Deal | -0.213 |
Acc | -0.212 |
also | -0.211 |
sch | -0.204 |
narrative | -0.204 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
stret | +0.078 |
le | +0.069 |
badges | +0.067 |
les | +0.067 |
luggage | +0.065 |
Neg logit contributions | |
Always | -0.133 |
Deal | -0.131 |
winning | -0.127 |
Acc | -0.123 |
Do | -0.122 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
ors | +0.533 |
badges | +0.523 |
cream | +0.507 |
affe | +0.501 |
ted | +0.491 |
Neg logit contributions | |
also | -0.570 |
welcome | -0.490 |
living | -0.482 |
first | -0.470 |
Do | -0.468 |
Token | Sara |
Token ID | 24799 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ors | +0.239 |
badges | +0.233 |
affe | +0.227 |
cream | +0.226 |
les | +0.217 |
Neg logit contributions | |
Deal | -0.149 |
also | -0.149 |
Acc | -0.141 |
Do | -0.135 |
sch | -0.135 |
Token | wants |
Token ID | 3382 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
ors | +0.374 |
cream | +0.365 |
badges | +0.364 |
affe | +0.353 |
ted | +0.343 |
Neg logit contributions | |
also | -0.253 |
Deal | -0.210 |
sch | -0.196 |
Acc | -0.193 |
Always | -0.191 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ors | +0.052 |
ops | +0.049 |
affe | +0.049 |
les | +0.047 |
badges | +0.047 |
Neg logit contributions | |
also | -0.028 |
known | -0.024 |
Do | -0.023 |
welcome | -0.021 |
Always | -0.021 |
Token | try |
Token ID | 1949 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
ors | +0.173 |
badges | +0.168 |
affe | +0.161 |
cream | +0.161 |
les | +0.159 |
Neg logit contributions | |
also | -0.110 |
Deal | -0.102 |
known | -0.097 |
welcome | -0.095 |
Do | -0.093 |
Token | everything |
Token ID | 2279 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ors | +0.209 |
affe | +0.197 |
badges | +0.196 |
cream | +0.192 |
ops | +0.189 |
Neg logit contributions | |
also | -0.139 |
Acc | -0.130 |
Deal | -0.125 |
known | -0.122 |
narrative | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ors | +0.254 |
badges | +0.249 |
affe | +0.240 |
cream | +0.239 |
ted | +0.229 |
Neg logit contributions | |
Deal | -0.238 |
also | -0.236 |
Acc | -0.232 |
narrative | -0.222 |
sch | -0.222 |
Token | including |
Token ID | 1390 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
ors | +0.181 |
badges | +0.179 |
cream | +0.173 |
ted | +0.171 |
affe | +0.168 |
Neg logit contributions | |
Deal | -0.270 |
Amen | -0.245 |
acy | -0.233 |
narrative | -0.231 |
itates | -0.217 |
Token | av |
Token ID | 1196 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
round | +0.125 |
affe | +0.121 |
ors | +0.120 |
cream | +0.114 |
ops | +0.113 |
Neg logit contributions | |
also | -0.065 |
Acc | -0.056 |
known | -0.055 |
winning | -0.054 |
welcome | -0.053 |
Token | oc |
Token ID | 420 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
ors | +0.067 |
badges | +0.064 |
affe | +0.062 |
cream | +0.058 |
les | +0.054 |
Neg logit contributions | |
Deal | -0.204 |
also | -0.201 |
Acc | -0.201 |
sch | -0.196 |
narrative | -0.195 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
badges | +0.058 |
stret | +0.054 |
round | +0.049 |
affe | +0.046 |
les | +0.046 |
Neg logit contributions | |
Acc | -0.156 |
Always | -0.154 |
Deal | -0.148 |
narrative | -0.147 |
known | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ors | +0.551 |
badges | +0.527 |
cream | +0.510 |
affe | +0.508 |
oos | +0.501 |
Neg logit contributions | |
also | -0.566 |
living | -0.480 |
welcome | -0.458 |
Always | -0.453 |
doing | -0.451 |
Token | They |
Token ID | 1119 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
ors | +0.180 |
affe | +0.168 |
ted | +0.164 |
als | +0.163 |
ops | +0.159 |
Neg logit contributions | |
Deal | -0.194 |
known | -0.192 |
also | -0.188 |
narrative | -0.183 |
Amen | -0.181 |
Token | were |
Token ID | 547 |
Feature activation | -8.41e-03 |
Pos logit contributions | |
ors | +0.108 |
badges | +0.105 |
cream | +0.100 |
affe | +0.100 |
ted | +0.096 |
Neg logit contributions | |
also | -0.077 |
Acc | -0.069 |
known | -0.067 |
narrative | -0.066 |
Deal | -0.065 |
Token | never |
Token ID | 1239 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
Deal | +0.010 |
narrative | +0.009 |
Acc | +0.009 |
sch | +0.009 |
Do | +0.009 |
Neg logit contributions | |
badges | -0.012 |
ors | -0.011 |
cream | -0.011 |
affe | -0.011 |
aw | -0.011 |
Token | jealous |
Token ID | 19354 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
badges | +0.014 |
cream | +0.014 |
ors | +0.013 |
affe | +0.013 |
ted | +0.013 |
Neg logit contributions | |
Deal | -0.010 |
Amen | -0.009 |
narrative | -0.009 |
also | -0.008 |
Acc | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
ors | +0.294 |
affe | +0.292 |
badges | +0.290 |
cream | +0.280 |
als | +0.278 |
Neg logit contributions | |
also | -0.116 |
Acc | -0.102 |
Do | -0.100 |
known | -0.100 |
Deal | -0.099 |
Token | picked |
Token ID | 6497 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
ors | +0.086 |
badges | +0.086 |
round | +0.079 |
ados | +0.078 |
affe | +0.078 |
Neg logit contributions | |
also | -0.060 |
known | -0.051 |
Acc | -0.047 |
sch | -0.047 |
Always | -0.047 |
Token | his |
Token ID | 465 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
badges | +0.132 |
ors | +0.132 |
ops | +0.129 |
round | +0.128 |
affe | +0.127 |
Neg logit contributions | |
welcome | -0.061 |
also | -0.060 |
right | -0.057 |
known | -0.056 |
Do | -0.052 |
Token | av |
Token ID | 1196 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ors | +0.142 |
badges | +0.140 |
affe | +0.129 |
ted | +0.128 |
les | +0.127 |
Neg logit contributions | |
also | -0.140 |
Deal | -0.137 |
Acc | -0.132 |
known | -0.129 |
welcome | -0.128 |
Token | oc |
Token ID | 420 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
ors | +0.058 |
affe | +0.055 |
cream | +0.051 |
badges | +0.050 |
les | +0.044 |
Neg logit contributions | |
Deal | -0.215 |
Acc | -0.214 |
also | -0.213 |
narrative | -0.211 |
sch | -0.209 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
badges | +0.056 |
ors | +0.046 |
stret | +0.044 |
round | +0.043 |
les | +0.043 |
Neg logit contributions | |
Deal | -0.159 |
narrative | -0.156 |
Acc | -0.155 |
Always | -0.154 |
Amen | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
badges | +0.499 |
ors | +0.486 |
affe | +0.476 |
cream | +0.450 |
ted | +0.440 |
Neg logit contributions | |
also | -0.584 |
Deal | -0.538 |
Acc | -0.531 |
narrative | -0.510 |
known | -0.509 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ors | +0.202 |
cream | +0.199 |
affe | +0.190 |
ted | +0.186 |
badges | +0.184 |
Neg logit contributions | |
Deal | -0.179 |
also | -0.169 |
narrative | -0.169 |
Acc | -0.164 |
sch | -0.160 |
Token | Once |
Token ID | 7454 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
ors | +0.134 |
ted | +0.132 |
les | +0.129 |
ops | +0.129 |
cream | +0.128 |
Neg logit contributions | |
Deal | -0.131 |
Acc | -0.130 |
narrative | -0.122 |
known | -0.112 |
Amen | -0.111 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ors | +0.010 |
les | +0.009 |
ops | +0.009 |
affe | +0.009 |
- | +0.009 |
Neg logit contributions | |
Deal | -0.007 |
Acc | -0.007 |
Amen | -0.006 |
Looks | -0.006 |
narrative | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
narrative | +0.207 |
Deal | +0.204 |
impossible | +0.183 |
sch | +0.181 |
Always | +0.181 |
Neg logit contributions | |
cream | -0.086 |
bars | -0.080 |
badges | -0.077 |
affe | -0.076 |
aw | -0.071 |
Token | The |
Token ID | 383 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ors | +0.211 |
badges | +0.210 |
cream | +0.202 |
affe | +0.202 |
ted | +0.195 |
Neg logit contributions | |
Deal | -0.136 |
also | -0.135 |
Acc | -0.133 |
narrative | -0.126 |
Amen | -0.125 |
Token | merry |
Token ID | 44570 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
badges | +0.163 |
ors | +0.159 |
affe | +0.156 |
cream | +0.151 |
les | +0.148 |
Neg logit contributions | |
Deal | -0.206 |
Acc | -0.204 |
also | -0.196 |
Amen | -0.194 |
known | -0.192 |
Token | - |
Token ID | 12 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
cream | +0.091 |
ors | +0.088 |
badges | +0.087 |
als | +0.083 |
rots | +0.082 |
Neg logit contributions | |
also | -0.172 |
sch | -0.167 |
first | -0.157 |
welcome | -0.154 |
End | -0.153 |
Token | go |
Token ID | 2188 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ors | +0.193 |
badges | +0.192 |
affe | +0.170 |
cream | +0.169 |
als | +0.168 |
Neg logit contributions | |
also | -0.195 |
Acc | -0.188 |
Deal | -0.185 |
sch | -0.180 |
Amen | -0.179 |
Token | - |
Token ID | 12 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ados | +0.113 |
chicks | +0.108 |
badges | +0.106 |
opes | +0.104 |
ors | +0.102 |
Neg logit contributions | |
also | -0.158 |
first | -0.143 |
sch | -0.140 |
welcome | -0.134 |
upon | -0.133 |
Token | round |
Token ID | 744 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
badges | +0.095 |
ors | +0.086 |
ishes | +0.071 |
ries | +0.070 |
ados | +0.070 |
Neg logit contributions | |
also | -0.289 |
Acc | -0.284 |
Do | -0.275 |
sch | -0.274 |
Amen | -0.274 |
Token | went |
Token ID | 1816 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
affe | +0.750 |
ors | +0.736 |
ados | +0.722 |
badges | +0.712 |
cream | +0.702 |
Neg logit contributions | |
also | -0.462 |
sch | -0.374 |
first | -0.355 |
very | -0.338 |
only | -0.327 |
Token | faster |
Token ID | 5443 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ors | +0.146 |
badges | +0.143 |
ted | +0.136 |
affe | +0.135 |
cream | +0.135 |
Neg logit contributions | |
Deal | -0.142 |
Acc | -0.136 |
also | -0.131 |
narrative | -0.131 |
Amen | -0.128 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
cream | +0.142 |
ors | +0.140 |
badges | +0.139 |
affe | +0.131 |
ted | +0.120 |
Neg logit contributions | |
also | -0.225 |
sch | -0.205 |
Acc | -0.203 |
Deal | -0.202 |
Do | -0.201 |
Token | faster |
Token ID | 5443 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
badges | +0.195 |
ted | +0.185 |
ors | +0.185 |
als | +0.183 |
bars | +0.181 |
Neg logit contributions | |
Deal | -0.252 |
Amen | -0.238 |
narrative | -0.230 |
Acc | -0.229 |
Always | -0.216 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
cream | +0.200 |
ors | +0.193 |
badges | +0.189 |
affe | +0.184 |
als | +0.168 |
Neg logit contributions | |
also | -0.175 |
Do | -0.154 |
winning | -0.149 |
sch | -0.149 |
welcome | -0.148 |
Token | ! |
Token ID | 0 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
badges | +0.088 |
ors | +0.086 |
affe | +0.080 |
cream | +0.079 |
les | +0.078 |
Neg logit contributions | |
also | -0.089 |
Always | -0.079 |
Acc | -0.078 |
welcome | -0.078 |
Do | -0.078 |
Token | She |
Token ID | 1375 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
ors | +0.191 |
affe | +0.189 |
als | +0.186 |
ted | +0.184 |
ops | +0.179 |
Neg logit contributions | |
Acc | -0.157 |
Deal | -0.151 |
narrative | -0.143 |
Amen | -0.142 |
also | -0.142 |
Token | thought |
Token ID | 1807 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
ors | +0.066 |
badges | +0.064 |
affe | +0.060 |
cream | +0.059 |
ted | +0.058 |
Neg logit contributions | |
also | -0.045 |
Acc | -0.037 |
Always | -0.036 |
known | -0.036 |
sch | -0.034 |
Token | av |
Token ID | 1196 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
badges | +0.117 |
ors | +0.114 |
cream | +0.112 |
affe | +0.109 |
ted | +0.105 |
Neg logit contributions | |
also | -0.095 |
Acc | -0.088 |
Deal | -0.086 |
Do | -0.084 |
Always | -0.083 |
Token | oc |
Token ID | 420 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
ors | +0.065 |
badges | +0.061 |
affe | +0.059 |
cream | +0.058 |
les | +0.052 |
Neg logit contributions | |
Deal | -0.191 |
also | -0.188 |
Acc | -0.187 |
sch | -0.183 |
narrative | -0.182 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
stret | +0.065 |
badges | +0.061 |
luggage | +0.052 |
gloves | +0.050 |
boots | +0.050 |
Neg logit contributions | |
Always | -0.138 |
Acc | -0.135 |
Deal | -0.132 |
Do | -0.128 |
known | -0.127 |
Token | were |
Token ID | 547 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
badges | +0.705 |
ors | +0.693 |
eros | +0.674 |
affe | +0.671 |
stret | +0.671 |
Neg logit contributions | |
also | -0.437 |
known | -0.327 |
welcome | -0.299 |
Always | -0.297 |
doing | -0.287 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Deal | +0.017 |
also | +0.016 |
Acc | +0.016 |
sch | +0.015 |
narrative | +0.015 |
Neg logit contributions | |
ors | -0.038 |
badges | -0.038 |
cream | -0.037 |
affe | -0.037 |
ted | -0.036 |
Token | most |
Token ID | 749 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
badges | +0.227 |
affe | +0.223 |
ors | +0.218 |
cream | +0.217 |
als | +0.216 |
Neg logit contributions | |
Acc | -0.104 |
Deal | -0.102 |
Amen | -0.099 |
sch | -0.099 |
Do | -0.094 |
Token | interesting |
Token ID | 3499 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
ors | +0.070 |
cream | +0.069 |
affe | +0.068 |
badges | +0.068 |
les | +0.066 |
Neg logit contributions | |
Deal | -0.041 |
Amen | -0.038 |
Acc | -0.037 |
sch | -0.036 |
narrative | -0.036 |
Token | food |
Token ID | 2057 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ors | +0.098 |
badges | +0.098 |
cream | +0.091 |
affe | +0.090 |
ted | +0.089 |
Neg logit contributions | |
also | -0.104 |
Acc | -0.100 |
narrative | -0.099 |
Deal | -0.098 |
welcome | -0.096 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
also | +0.049 |
Deal | +0.043 |
sch | +0.042 |
Do | +0.041 |
known | +0.041 |
Neg logit contributions | |
ors | -0.087 |
affe | -0.084 |
cream | -0.082 |
badges | -0.082 |
ops | -0.081 |
Token | merry |
Token ID | 44570 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
ors | +0.196 |
cream | +0.184 |
ages | +0.173 |
badges | +0.171 |
affe | +0.168 |
Neg logit contributions | |
also | -0.160 |
sch | -0.150 |
Deal | -0.140 |
welcome | -0.139 |
living | -0.137 |
Token | - |
Token ID | 12 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
cream | +0.094 |
badges | +0.087 |
rots | +0.083 |
als | +0.082 |
ted | +0.082 |
Neg logit contributions | |
also | -0.140 |
sch | -0.137 |
first | -0.133 |
welcome | -0.128 |
week | -0.128 |
Token | go |
Token ID | 2188 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
badges | +0.191 |
ors | +0.177 |
ted | +0.165 |
affe | +0.163 |
als | +0.161 |
Neg logit contributions | |
also | -0.185 |
Acc | -0.175 |
Amen | -0.163 |
sch | -0.163 |
Do | -0.161 |
Token | - |
Token ID | 12 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
badges | +0.084 |
ados | +0.074 |
affe | +0.073 |
ors | +0.073 |
cream | +0.070 |
Neg logit contributions | |
also | -0.158 |
first | -0.148 |
sch | -0.145 |
welcome | -0.143 |
very | -0.138 |
Token | round |
Token ID | 744 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
badges | +0.091 |
ors | +0.069 |
cheeks | +0.063 |
ted | +0.059 |
ishes | +0.059 |
Neg logit contributions | |
also | -0.285 |
Acc | -0.273 |
Amen | -0.265 |
Do | -0.263 |
sch | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
badges | +0.555 |
affe | +0.538 |
ors | +0.525 |
cream | +0.496 |
eros | +0.487 |
Neg logit contributions | |
also | -0.514 |
sch | -0.435 |
first | -0.424 |
winning | -0.405 |
doing | -0.404 |
Token | He |
Token ID | 679 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
badges | +0.185 |
ors | +0.185 |
affe | +0.183 |
cream | +0.179 |
ted | +0.175 |
Neg logit contributions | |
Acc | -0.146 |
Deal | -0.142 |
narrative | -0.142 |
known | -0.140 |
also | -0.138 |
Token | thought |
Token ID | 1807 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
ors | +0.060 |
ados | +0.056 |
ops | +0.054 |
eros | +0.054 |
affe | +0.053 |
Neg logit contributions | |
also | -0.047 |
sch | -0.033 |
known | -0.032 |
Acc | -0.031 |
Always | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
cream | +0.141 |
badges | +0.141 |
ors | +0.138 |
affe | +0.135 |
als | +0.134 |
Neg logit contributions | |
also | -0.090 |
Do | -0.074 |
winning | -0.068 |
first | -0.067 |
welcome | -0.067 |
Token | might |
Token ID | 1244 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
ors | +0.296 |
affe | +0.289 |
badges | +0.285 |
ados | +0.276 |
round | +0.274 |
Neg logit contributions | |
also | -0.151 |
known | -0.111 |
Do | -0.105 |
Acc | -0.103 |
sch | -0.103 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
ors | +0.238 |
badges | +0.232 |
cream | +0.226 |
affe | +0.225 |
ted | +0.215 |
Neg logit contributions | |
Deal | -0.222 |
Acc | -0.207 |
also | -0.206 |
narrative | -0.200 |
known | -0.199 |
Token | to |
Token ID | 284 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
ors | +0.025 |
badges | +0.025 |
affe | +0.024 |
cream | +0.024 |
les | +0.023 |
Neg logit contributions | |
also | -0.020 |
Acc | -0.020 |
Deal | -0.020 |
sch | -0.019 |
known | -0.019 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ors | +0.146 |
affe | +0.136 |
badges | +0.134 |
les | +0.133 |
ted | +0.132 |
Neg logit contributions | |
also | -0.078 |
welcome | -0.070 |
Deal | -0.068 |
Amen | -0.067 |
Do | -0.067 |
Token | av |
Token ID | 1196 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
ors | +0.181 |
affe | +0.179 |
badges | +0.174 |
als | +0.160 |
phones | +0.159 |
Neg logit contributions | |
also | -0.170 |
Acc | -0.154 |
Do | -0.154 |
welcome | -0.151 |
sch | -0.149 |
Token | oc |
Token ID | 420 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
ors | +0.052 |
affe | +0.049 |
cream | +0.044 |
badges | +0.043 |
ops | +0.041 |
Neg logit contributions | |
Deal | -0.199 |
Acc | -0.194 |
also | -0.191 |
sch | -0.189 |
narrative | -0.188 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
badges | +0.056 |
stret | +0.050 |
round | +0.049 |
affe | +0.046 |
le | +0.045 |
Neg logit contributions | |
Always | -0.127 |
Acc | -0.125 |
Deal | -0.124 |
narrative | -0.118 |
Amen | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ors | +0.402 |
badges | +0.385 |
cream | +0.370 |
affe | +0.369 |
ted | +0.346 |
Neg logit contributions | |
Deal | -0.628 |
Acc | -0.612 |
also | -0.607 |
sch | -0.590 |
Amen | -0.588 |
Token | they |
Token ID | 484 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
badges | +0.244 |
ors | +0.243 |
cream | +0.235 |
affe | +0.234 |
ted | +0.224 |
Neg logit contributions | |
Deal | -0.175 |
Acc | -0.156 |
Amen | -0.155 |
narrative | -0.154 |
sch | -0.152 |
Token | were |
Token ID | 547 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
ors | +0.108 |
badges | +0.105 |
affe | +0.102 |
cream | +0.101 |
ted | +0.097 |
Neg logit contributions | |
also | -0.088 |
Deal | -0.085 |
Acc | -0.084 |
known | -0.081 |
narrative | -0.081 |
Token | her |
Token ID | 607 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Deal | +0.027 |
Acc | +0.026 |
sch | +0.025 |
narrative | +0.025 |
Amen | +0.023 |
Neg logit contributions | |
badges | -0.030 |
ors | -0.029 |
cream | -0.029 |
affe | -0.028 |
ries | -0.028 |
Token | favorite |
Token ID | 4004 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
badges | +0.125 |
affe | +0.122 |
ors | +0.121 |
cream | +0.117 |
als | +0.112 |
Neg logit contributions | |
Deal | -0.159 |
Acc | -0.158 |
narrative | -0.153 |
sch | -0.152 |
Amen | -0.150 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
badges | +0.080 |
cream | +0.078 |
ors | +0.078 |
affe | +0.075 |
als | +0.067 |
Neg logit contributions | |
also | -0.141 |
Deal | -0.136 |
Acc | -0.132 |
narrative | -0.132 |
Do | -0.130 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ted | +0.123 |
ops | +0.117 |
ors | +0.115 |
als | +0.114 |
les | +0.113 |
Neg logit contributions | |
Deal | -0.276 |
Amen | -0.267 |
sch | -0.249 |
narrative | -0.243 |
known | -0.236 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
badges | +0.297 |
ors | +0.293 |
cream | +0.282 |
affe | +0.280 |
ted | +0.266 |
Neg logit contributions | |
also | -0.187 |
Acc | -0.174 |
known | -0.163 |
Always | -0.159 |
sch | -0.156 |
Token | av |
Token ID | 1196 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
ors | +0.026 |
badges | +0.026 |
cream | +0.025 |
affe | +0.024 |
ted | +0.024 |
Neg logit contributions | |
Deal | -0.023 |
also | -0.022 |
narrative | -0.021 |
Acc | -0.021 |
Amen | -0.021 |
Token | oc |
Token ID | 420 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
affe | +0.048 |
ors | +0.048 |
badges | +0.041 |
ops | +0.041 |
cream | +0.040 |
Neg logit contributions | |
Deal | -0.198 |
Acc | -0.192 |
also | -0.191 |
narrative | -0.189 |
sch | -0.189 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
badges | +0.053 |
stret | +0.048 |
les | +0.043 |
ors | +0.041 |
affe | +0.041 |
Neg logit contributions | |
Deal | -0.133 |
Acc | -0.132 |
Always | -0.130 |
narrative | -0.127 |
welcome | -0.126 |
Token | and |
Token ID | 290 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ors | +0.422 |
badges | +0.421 |
cream | +0.391 |
affe | +0.388 |
ted | +0.368 |
Neg logit contributions | |
also | -0.607 |
Acc | -0.580 |
Deal | -0.574 |
known | -0.561 |
narrative | -0.556 |
Token | would |
Token ID | 561 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
cream | +0.209 |
ors | +0.206 |
badges | +0.204 |
ted | +0.201 |
affe | +0.196 |
Neg logit contributions | |
Deal | -0.231 |
Amen | -0.192 |
narrative | -0.190 |
sch | -0.186 |
Acc | -0.180 |
Token | ask |
Token ID | 1265 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
Deal | +0.052 |
sch | +0.049 |
narrative | +0.049 |
Acc | +0.047 |
Looks | +0.045 |
Neg logit contributions | |
affe | -0.083 |
ors | -0.082 |
badges | -0.081 |
ops | -0.080 |
cream | -0.078 |
Token | for |
Token ID | 329 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
ors | +0.098 |
badges | +0.098 |
affe | +0.095 |
cream | +0.095 |
ops | +0.091 |
Neg logit contributions | |
also | -0.059 |
Deal | -0.057 |
Acc | -0.057 |
known | -0.053 |
Do | -0.053 |
Token | them |
Token ID | 606 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
badges | +0.101 |
ors | +0.100 |
cream | +0.096 |
affe | +0.095 |
ted | +0.092 |
Neg logit contributions | |
Deal | -0.092 |
also | -0.090 |
Acc | -0.089 |
sch | -0.086 |
narrative | -0.086 |
Token | could |
Token ID | 714 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ors | +0.135 |
badges | +0.131 |
affe | +0.126 |
eros | +0.126 |
ados | +0.125 |
Neg logit contributions | |
also | -0.059 |
known | -0.037 |
Acc | -0.034 |
narrative | -0.033 |
Always | -0.032 |
Token | grow |
Token ID | 1663 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
Deal | +0.121 |
Acc | +0.118 |
sch | +0.114 |
narrative | +0.112 |
also | +0.111 |
Neg logit contributions | |
ors | -0.164 |
badges | -0.162 |
affe | -0.158 |
cream | -0.156 |
als | -0.151 |
Token | more |
Token ID | 517 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
ors | +0.136 |
badges | +0.133 |
affe | +0.129 |
cream | +0.128 |
ted | +0.123 |
Neg logit contributions | |
Deal | -0.101 |
also | -0.100 |
Acc | -0.098 |
narrative | -0.093 |
sch | -0.093 |
Token | av |
Token ID | 1196 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
ors | +0.049 |
badges | +0.047 |
affe | +0.046 |
cream | +0.045 |
les | +0.044 |
Neg logit contributions | |
Deal | -0.083 |
Acc | -0.080 |
also | -0.080 |
sch | -0.078 |
Amen | -0.077 |
Token | oc |
Token ID | 420 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
ors | +0.051 |
affe | +0.048 |
badges | +0.044 |
cream | +0.042 |
les | +0.040 |
Neg logit contributions | |
Deal | -0.195 |
Acc | -0.192 |
also | -0.189 |
sch | -0.188 |
narrative | -0.185 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
badges | +0.058 |
stret | +0.056 |
luggage | +0.050 |
boots | +0.049 |
umbrella | +0.047 |
Neg logit contributions | |
Always | -0.122 |
Acc | -0.121 |
Deal | -0.119 |
narrative | -0.118 |
welcome | -0.112 |
Token | and |
Token ID | 290 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
badges | +0.475 |
ors | +0.472 |
affe | +0.447 |
cream | +0.446 |
ted | +0.430 |
Neg logit contributions | |
also | -0.573 |
Deal | -0.510 |
Acc | -0.506 |
narrative | -0.501 |
Do | -0.499 |
Token | share |
Token ID | 2648 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
badges | +0.190 |
cream | +0.190 |
als | +0.184 |
ors | +0.182 |
affe | +0.179 |
Neg logit contributions | |
Deal | -0.202 |
Acc | -0.187 |
sch | -0.186 |
narrative | -0.183 |
Amen | -0.176 |
Token | them |
Token ID | 606 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ors | +0.205 |
affe | +0.200 |
badges | +0.197 |
ops | +0.195 |
cream | +0.189 |
Neg logit contributions | |
also | -0.152 |
Do | -0.130 |
Acc | -0.121 |
welcome | -0.121 |
narrative | -0.114 |
Token | with |
Token ID | 351 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
badges | +0.294 |
ted | +0.283 |
ors | +0.277 |
affe | +0.276 |
anged | +0.272 |
Neg logit contributions | |
also | -0.157 |
welcome | -0.118 |
first | -0.117 |
Acc | -0.117 |
narrative | -0.116 |
Token | their |
Token ID | 511 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
affe | +0.087 |
ors | +0.086 |
round | +0.086 |
cream | +0.083 |
badges | +0.079 |
Neg logit contributions | |
also | -0.050 |
known | -0.042 |
first | -0.035 |
Do | -0.035 |
Acc | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
ors | +0.196 |
cream | +0.191 |
ted | +0.186 |
affe | +0.185 |
badges | +0.183 |
Neg logit contributions | |
narrative | -0.134 |
Deal | -0.134 |
also | -0.132 |
Acc | -0.126 |
Amen | -0.125 |
Token | learned |
Token ID | 4499 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
ors | +0.066 |
badges | +0.064 |
affe | +0.061 |
ados | +0.059 |
eros | +0.059 |
Neg logit contributions | |
also | -0.045 |
Acc | -0.036 |
known | -0.033 |
sch | -0.032 |
Always | -0.031 |
Token | that |
Token ID | 326 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
ors | +0.047 |
badges | +0.045 |
cream | +0.043 |
affe | +0.043 |
ted | +0.041 |
Neg logit contributions | |
Deal | -0.077 |
also | -0.076 |
Acc | -0.075 |
narrative | -0.073 |
sch | -0.073 |
Token | av |
Token ID | 1196 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
ors | +0.108 |
badges | +0.099 |
cream | +0.097 |
ted | +0.096 |
affe | +0.096 |
Neg logit contributions | |
Deal | -0.124 |
Amen | -0.110 |
sch | -0.108 |
Acc | -0.108 |
known | -0.105 |
Token | oc |
Token ID | 420 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
ors | +0.050 |
affe | +0.048 |
badges | +0.043 |
cream | +0.043 |
les | +0.040 |
Neg logit contributions | |
Deal | -0.191 |
Acc | -0.187 |
also | -0.185 |
sch | -0.184 |
narrative | -0.180 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
badges | +0.045 |
stret | +0.040 |
ors | +0.035 |
les | +0.034 |
affe | +0.033 |
Neg logit contributions | |
Acc | -0.139 |
Deal | -0.139 |
Always | -0.138 |
narrative | -0.137 |
known | -0.133 |
Token | are |
Token ID | 389 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
badges | +0.680 |
ors | +0.666 |
affe | +0.659 |
cream | +0.655 |
ted | +0.630 |
Neg logit contributions | |
also | -0.388 |
narrative | -0.302 |
known | -0.301 |
Always | -0.301 |
welcome | -0.296 |
Token | good |
Token ID | 922 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
Deal | +0.041 |
Amen | +0.038 |
sch | +0.038 |
Acc | +0.038 |
narrative | +0.035 |
Neg logit contributions | |
badges | -0.089 |
ors | -0.088 |
cream | -0.086 |
affe | -0.085 |
ted | -0.082 |
Token | for |
Token ID | 329 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
badges | +0.077 |
ors | +0.075 |
cream | +0.075 |
affe | +0.074 |
round | +0.070 |
Neg logit contributions | |
also | -0.065 |
Always | -0.060 |
Acc | -0.060 |
Deal | -0.060 |
Do | -0.059 |
Token | her |
Token ID | 607 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
badges | +0.131 |
ors | +0.131 |
affe | +0.130 |
cream | +0.129 |
als | +0.124 |
Neg logit contributions | |
also | -0.062 |
Deal | -0.059 |
Acc | -0.058 |
known | -0.055 |
Always | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
badges | +0.173 |
ors | +0.171 |
round | +0.163 |
cream | +0.162 |
ted | +0.162 |
Neg logit contributions | |
also | -0.139 |
welcome | -0.123 |
Acc | -0.121 |
Always | -0.119 |
first | -0.118 |
Token | a |
Token ID | 257 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
ors | +0.068 |
affe | +0.063 |
badges | +0.062 |
cream | +0.062 |
ops | +0.060 |
Neg logit contributions | |
also | -0.043 |
known | -0.037 |
Do | -0.037 |
Acc | -0.036 |
sch | -0.035 |
Token | merry |
Token ID | 44570 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
ors | +0.150 |
cream | +0.143 |
badges | +0.141 |
ted | +0.136 |
affe | +0.130 |
Neg logit contributions | |
also | -0.113 |
Deal | -0.104 |
Acc | -0.101 |
known | -0.098 |
sch | -0.098 |
Token | - |
Token ID | 12 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
cream | +0.076 |
badges | +0.076 |
ors | +0.069 |
ted | +0.067 |
als | +0.067 |
Neg logit contributions | |
also | -0.139 |
welcome | -0.130 |
sch | -0.129 |
sunny | -0.126 |
narrative | -0.124 |
Token | go |
Token ID | 2188 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
badges | +0.164 |
ors | +0.158 |
affe | +0.140 |
ted | +0.139 |
cream | +0.138 |
Neg logit contributions | |
also | -0.181 |
Acc | -0.179 |
known | -0.168 |
Deal | -0.167 |
sch | -0.164 |
Token | - |
Token ID | 12 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
badges | +0.087 |
cream | +0.072 |
ors | +0.071 |
affe | +0.067 |
ted | +0.067 |
Neg logit contributions | |
also | -0.138 |
welcome | -0.130 |
possible | -0.128 |
first | -0.127 |
sunny | -0.125 |
Token | round |
Token ID | 744 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
badges | +0.151 |
ors | +0.131 |
ries | +0.123 |
cheeks | +0.122 |
ted | +0.117 |
Neg logit contributions | |
Acc | -0.201 |
also | -0.197 |
known | -0.183 |
Do | -0.180 |
Always | -0.179 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
badges | +0.584 |
affe | +0.521 |
ors | +0.516 |
cream | +0.510 |
wo | +0.490 |
Neg logit contributions | |
also | -0.491 |
first | -0.431 |
winning | -0.407 |
doing | -0.402 |
sch | -0.394 |
Token |
|
Token ID | 198 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
als | +0.173 |
ted | +0.173 |
ors | +0.173 |
cream | +0.173 |
ed | +0.170 |
Neg logit contributions | |
Amen | -0.138 |
narrative | -0.129 |
Acc | -0.128 |
also | -0.128 |
Deal | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
Deal | +0.037 |
Acc | +0.036 |
narrative | +0.035 |
Amen | +0.035 |
sch | +0.034 |
Neg logit contributions | |
ors | -0.053 |
affe | -0.052 |
cream | -0.051 |
les | -0.050 |
badges | -0.050 |
Token | S |
Token ID | 50 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Deal | +0.048 |
Amen | +0.048 |
Acc | +0.046 |
Do | +0.046 |
sch | +0.045 |
Neg logit contributions | |
affe | -0.039 |
ors | -0.038 |
badges | -0.038 |
les | -0.038 |
aw | -0.037 |
Token | oph |
Token ID | 2522 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ors | +0.200 |
badges | +0.191 |
affe | +0.190 |
cream | +0.189 |
les | +0.184 |
Neg logit contributions | |
Deal | -0.253 |
also | -0.251 |
Amen | -0.245 |
Acc | -0.244 |
sch | -0.238 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ors | +0.240 |
badges | +0.232 |
affe | +0.228 |
cream | +0.218 |
ops | +0.213 |
Neg logit contributions | |
also | -0.171 |
known | -0.150 |
sch | -0.146 |
Do | -0.139 |
Always | -0.135 |
Token | merry |
Token ID | 44570 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
ors | +0.177 |
badges | +0.167 |
cream | +0.165 |
affe | +0.164 |
ted | +0.158 |
Neg logit contributions | |
also | -0.132 |
Deal | -0.129 |
Acc | -0.124 |
sch | -0.123 |
known | -0.122 |
Token | - |
Token ID | 12 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
als | +0.066 |
badges | +0.064 |
ors | +0.063 |
cream | +0.062 |
ted | +0.060 |
Neg logit contributions | |
sch | -0.141 |
also | -0.139 |
welcome | -0.131 |
winning | -0.128 |
known | -0.128 |
Token | go |
Token ID | 2188 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
badges | +0.200 |
ors | +0.197 |
les | +0.178 |
als | +0.178 |
cheeks | +0.176 |
Neg logit contributions | |
also | -0.131 |
Acc | -0.127 |
sch | -0.122 |
Always | -0.122 |
known | -0.122 |
Token | - |
Token ID | 12 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
chicks | +0.077 |
badges | +0.077 |
ados | +0.075 |
berries | +0.073 |
iv | +0.070 |
Neg logit contributions | |
also | -0.123 |
sch | -0.120 |
known | -0.119 |
first | -0.116 |
welcome | -0.116 |
Token | round |
Token ID | 744 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
badges | +0.126 |
ries | +0.114 |
ors | +0.113 |
chicks | +0.112 |
ishes | +0.112 |
Neg logit contributions | |
also | -0.199 |
Acc | -0.195 |
Always | -0.193 |
sch | -0.192 |
known | -0.191 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
affe | +0.595 |
badges | +0.583 |
tal | +0.560 |
chicks | +0.559 |
ados | +0.558 |
Neg logit contributions | |
also | -0.456 |
first | -0.408 |
very | -0.387 |
sch | -0.382 |
going | -0.370 |
Token | He |
Token ID | 679 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
ors | +0.222 |
badges | +0.221 |
affe | +0.211 |
cream | +0.209 |
les | +0.204 |
Neg logit contributions | |
Deal | -0.111 |
also | -0.110 |
Acc | -0.103 |
sch | -0.101 |
Always | -0.101 |
Token | had |
Token ID | 550 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
ados | +0.043 |
ors | +0.043 |
affe | +0.041 |
ries | +0.040 |
badges | +0.040 |
Neg logit contributions | |
also | -0.038 |
known | -0.031 |
sch | -0.030 |
Always | -0.026 |
first | -0.026 |
Token | never |
Token ID | 1239 |
Feature activation | -8.28e-03 |
Pos logit contributions | |
also | +0.033 |
known | +0.030 |
sch | +0.028 |
Do | +0.027 |
Always | +0.026 |
Neg logit contributions | |
ors | -0.076 |
affe | -0.072 |
badges | -0.070 |
cream | -0.070 |
ops | -0.069 |
Token | had |
Token ID | 550 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
also | +0.011 |
Deal | +0.011 |
Acc | +0.011 |
known | +0.010 |
sch | +0.010 |
Neg logit contributions | |
ors | -0.011 |
badges | -0.011 |
affe | -0.010 |
cream | -0.010 |
ted | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
ache | +0.301 |
les | +0.295 |
ors | +0.290 |
ops | +0.284 |
affe | +0.281 |
Neg logit contributions | |
also | -0.107 |
Do | -0.106 |
sch | -0.092 |
welcome | -0.086 |
Always | -0.085 |
Token | pretend |
Token ID | 16614 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
ors | +0.116 |
cream | +0.114 |
affe | +0.111 |
badges | +0.111 |
ted | +0.107 |
Neg logit contributions | |
also | -0.069 |
Deal | -0.061 |
known | -0.056 |
sch | -0.056 |
narrative | -0.055 |
Token | to |
Token ID | 284 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
affe | +0.172 |
ors | +0.171 |
cream | +0.168 |
int | +0.163 |
ops | +0.162 |
Neg logit contributions | |
also | -0.084 |
Do | -0.073 |
sch | -0.072 |
living | -0.072 |
not | -0.064 |
Token | fight |
Token ID | 1907 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ors | +0.168 |
badges | +0.163 |
cream | +0.162 |
affe | +0.159 |
ted | +0.155 |
Neg logit contributions | |
also | -0.106 |
Deal | -0.103 |
Acc | -0.098 |
sch | -0.095 |
known | -0.095 |
Token | bad |
Token ID | 2089 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
cream | +0.351 |
affe | +0.335 |
ors | +0.331 |
ops | +0.327 |
eros | +0.326 |
Neg logit contributions | |
also | -0.232 |
Do | -0.204 |
winning | -0.194 |
sch | -0.191 |
very | -0.189 |
Token | guys |
Token ID | 3730 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
cream | +0.127 |
round | +0.114 |
ors | +0.113 |
affe | +0.107 |
uddled | +0.106 |
Neg logit contributions | |
Do | -0.131 |
welcome | -0.120 |
sch | -0.119 |
You | -0.114 |
Listen | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
badges | +0.514 |
cream | +0.505 |
ted | +0.474 |
ors | +0.471 |
affe | +0.471 |
Neg logit contributions | |
also | -0.545 |
Do | -0.458 |
welcome | -0.444 |
winning | -0.439 |
first | -0.438 |
Token | They |
Token ID | 1119 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
ache | +0.323 |
les | +0.318 |
ors | +0.305 |
affe | +0.298 |
le | +0.295 |
Neg logit contributions | |
also | -0.111 |
Do | -0.106 |
Always | -0.087 |
Sometimes | -0.083 |
sch | -0.082 |
Token | jump |
Token ID | 4391 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ors | +0.130 |
cream | +0.128 |
badges | +0.123 |
affe | +0.123 |
ted | +0.121 |
Neg logit contributions | |
also | -0.070 |
Deal | -0.061 |
narrative | -0.055 |
known | -0.055 |
Amen | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
cream | +0.216 |
ors | +0.202 |
affe | +0.202 |
badges | +0.198 |
ops | +0.190 |
Neg logit contributions | |
also | -0.200 |
very | -0.178 |
first | -0.173 |
sch | -0.165 |
Do | -0.165 |
Token | roll |
Token ID | 4836 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ors | +0.295 |
cream | +0.282 |
affe | +0.279 |
badges | +0.277 |
ted | +0.264 |
Neg logit contributions | |
also | -0.186 |
Deal | -0.180 |
Amen | -0.165 |
Do | -0.164 |
sch | -0.163 |
Token | window |
Token ID | 4324 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ors | +0.224 |
cream | +0.212 |
badges | +0.206 |
les | +0.201 |
ted | +0.200 |
Neg logit contributions | |
also | -0.153 |
Deal | -0.145 |
sch | -0.138 |
welcome | -0.133 |
narrative | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ors | +0.198 |
badges | +0.196 |
cream | +0.187 |
affe | +0.185 |
ted | +0.173 |
Neg logit contributions | |
also | -0.231 |
Do | -0.208 |
Deal | -0.206 |
known | -0.201 |
sch | -0.201 |
Token | It |
Token ID | 632 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
ors | +0.206 |
badges | +0.203 |
affe | +0.196 |
cream | +0.195 |
ted | +0.188 |
Neg logit contributions | |
Deal | -0.164 |
also | -0.163 |
Acc | -0.161 |
narrative | -0.153 |
sch | -0.153 |
Token | said |
Token ID | 531 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
ors | +0.190 |
ados | +0.172 |
affe | +0.170 |
oos | +0.168 |
badges | +0.166 |
Neg logit contributions | |
also | -0.098 |
known | -0.063 |
Do | -0.058 |
sch | -0.057 |
narrative | -0.057 |
Token | " |
Token ID | 366 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
ors | +0.104 |
ales | +0.099 |
cream | +0.098 |
badges | +0.096 |
les | +0.096 |
Neg logit contributions | |
Do | -0.073 |
also | -0.065 |
welcome | -0.063 |
not | -0.056 |
glad | -0.054 |
Token | Army |
Token ID | 45272 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
ors | +0.100 |
badges | +0.093 |
cheeks | +0.090 |
les | +0.089 |
affe | +0.088 |
Neg logit contributions | |
Do | -0.036 |
also | -0.035 |
Do | -0.035 |
known | -0.033 |
Oh | -0.032 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
badges | +0.535 |
cream | +0.532 |
ors | +0.511 |
affe | +0.472 |
cheeks | +0.461 |
Neg logit contributions | |
Do | -0.451 |
welcome | -0.448 |
also | -0.437 |
Deal | -0.436 |
Amen | -0.422 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
ors | +0.374 |
badges | +0.365 |
affe | +0.358 |
cream | +0.358 |
ted | +0.346 |
Neg logit contributions | |
also | -0.134 |
Deal | -0.132 |
Acc | -0.123 |
Do | -0.116 |
narrative | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
Deal | +0.018 |
Acc | +0.017 |
narrative | +0.016 |
sch | +0.016 |
known | +0.015 |
Neg logit contributions | |
badges | -0.029 |
ors | -0.029 |
affe | -0.028 |
cream | -0.028 |
les | -0.027 |
Token | " |
Token ID | 1 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Deal | +0.019 |
also | +0.019 |
Acc | +0.019 |
narrative | +0.018 |
sch | +0.018 |
Neg logit contributions | |
ors | -0.024 |
badges | -0.024 |
affe | -0.023 |
cream | -0.023 |
ted | -0.022 |
Token | Wow |
Token ID | 22017 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
ors | +0.239 |
badges | +0.221 |
cream | +0.220 |
affe | +0.218 |
les | +0.213 |
Neg logit contributions | |
also | -0.119 |
Deal | -0.118 |
Acc | -0.113 |
narrative | -0.110 |
Amen | -0.108 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ors | +0.243 |
affe | +0.232 |
cream | +0.223 |
ops | +0.217 |
badges | +0.215 |
Neg logit contributions | |
also | -0.173 |
Do | -0.136 |
Acc | -0.135 |
welcome | -0.132 |
sch | -0.132 |
Token | merry |
Token ID | 44570 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
ors | +0.193 |
cream | +0.171 |
ted | +0.159 |
affe | +0.156 |
ops | +0.155 |
Neg logit contributions | |
also | -0.157 |
narrative | -0.143 |
welcome | -0.142 |
sch | -0.138 |
Deal | -0.134 |
Token | - |
Token ID | 12 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
cream | +0.104 |
ted | +0.098 |
badges | +0.096 |
ors | +0.095 |
phones | +0.094 |
Neg logit contributions | |
also | -0.117 |
welcome | -0.113 |
first | -0.109 |
sch | -0.105 |
doing | -0.105 |
Token | go |
Token ID | 2188 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
badges | +0.201 |
ors | +0.197 |
ted | +0.177 |
affe | +0.174 |
ible | +0.172 |
Neg logit contributions | |
also | -0.156 |
Acc | -0.147 |
sch | -0.139 |
welcome | -0.139 |
Amen | -0.139 |
Token | - |
Token ID | 12 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
badges | +0.088 |
ors | +0.078 |
cream | +0.078 |
ted | +0.077 |
ache | +0.076 |
Neg logit contributions | |
also | -0.137 |
welcome | -0.135 |
first | -0.130 |
upon | -0.125 |
sunny | -0.122 |
Token | round |
Token ID | 744 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
badges | +0.108 |
ors | +0.087 |
cheeks | +0.080 |
vered | +0.077 |
ishes | +0.076 |
Neg logit contributions | |
also | -0.246 |
Acc | -0.238 |
sill | -0.234 |
Do | -0.230 |
Amen | -0.228 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
badges | +0.577 |
affe | +0.574 |
cream | +0.554 |
ors | +0.547 |
wo | +0.532 |
Neg logit contributions | |
also | -0.488 |
first | -0.414 |
doing | -0.388 |
winning | -0.381 |
living | -0.377 |
Token | They |
Token ID | 1119 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
ors | +0.209 |
badges | +0.204 |
affe | +0.198 |
cream | +0.198 |
les | +0.191 |
Neg logit contributions | |
Deal | -0.117 |
also | -0.116 |
Acc | -0.111 |
Do | -0.105 |
narrative | -0.105 |
Token | think |
Token ID | 892 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
ors | +0.085 |
cream | +0.082 |
badges | +0.079 |
affe | +0.079 |
ted | +0.078 |
Neg logit contributions | |
also | -0.044 |
Deal | -0.037 |
welcome | -0.034 |
narrative | -0.033 |
known | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
affe | +0.158 |
ors | +0.157 |
cream | +0.156 |
badges | +0.154 |
ted | +0.150 |
Neg logit contributions | |
also | -0.085 |
Do | -0.062 |
winning | -0.061 |
not | -0.061 |
first | -0.059 |
Token | They |
Token ID | 1119 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
ors | +0.210 |
badges | +0.206 |
affe | +0.200 |
cream | +0.200 |
ted | +0.193 |
Neg logit contributions | |
Deal | -0.118 |
also | -0.117 |
Acc | -0.115 |
narrative | -0.108 |
sch | -0.108 |
Token | plan |
Token ID | 1410 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
ors | +0.119 |
cream | +0.116 |
affe | +0.113 |
ted | +0.112 |
badges | +0.111 |
Neg logit contributions | |
also | -0.061 |
Deal | -0.048 |
known | -0.047 |
narrative | -0.046 |
Amen | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
affe | +0.206 |
ors | +0.199 |
eros | +0.195 |
ops | +0.189 |
als | +0.188 |
Neg logit contributions | |
also | -0.080 |
not | -0.065 |
known | -0.060 |
living | -0.059 |
very | -0.055 |
Token | fight |
Token ID | 1907 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
badges | +0.147 |
ors | +0.146 |
affe | +0.138 |
cream | +0.137 |
les | +0.132 |
Neg logit contributions | |
Acc | -0.116 |
Deal | -0.114 |
also | -0.107 |
narrative | -0.107 |
sch | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
eros | +0.430 |
affe | +0.429 |
cream | +0.418 |
ittens | +0.408 |
itten | +0.408 |
Neg logit contributions | |
also | -0.158 |
very | -0.134 |
first | -0.126 |
not | -0.126 |
right | -0.125 |
Token | bad |
Token ID | 2089 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
ors | +0.181 |
cream | +0.170 |
badges | +0.170 |
affe | +0.164 |
ted | +0.159 |
Neg logit contributions | |
also | -0.193 |
Deal | -0.186 |
narrative | -0.181 |
sch | -0.179 |
Do | -0.177 |
Token | guys |
Token ID | 3730 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
cream | +0.100 |
ors | +0.095 |
ries | +0.089 |
vered | +0.086 |
affe | +0.086 |
Neg logit contributions | |
also | -0.143 |
narrative | -0.141 |
weekend | -0.140 |
first | -0.139 |
living | -0.138 |
Token | and |
Token ID | 290 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
badges | +0.576 |
ted | +0.563 |
cream | +0.547 |
affe | +0.533 |
cheeks | +0.525 |
Neg logit contributions | |
also | -0.504 |
first | -0.414 |
welcome | -0.386 |
Do | -0.376 |
not | -0.375 |
Token | win |
Token ID | 1592 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ors | +0.272 |
badges | +0.268 |
affe | +0.259 |
cream | +0.259 |
ted | +0.249 |
Neg logit contributions | |
Deal | -0.183 |
also | -0.181 |
Acc | -0.178 |
narrative | -0.168 |
sch | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
affe | +0.329 |
cream | +0.323 |
ors | +0.312 |
ted | +0.309 |
round | +0.305 |
Neg logit contributions | |
also | -0.184 |
winning | -0.150 |
known | -0.150 |
Do | -0.141 |
first | -0.136 |
Token | They |
Token ID | 1119 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
ors | +0.225 |
badges | +0.222 |
cream | +0.217 |
affe | +0.211 |
bars | +0.209 |
Neg logit contributions | |
Acc | -0.161 |
known | -0.157 |
Deal | -0.156 |
narrative | -0.155 |
Amen | -0.151 |
Token | hide |
Token ID | 7808 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ors | +0.129 |
cream | +0.126 |
affe | +0.122 |
badges | +0.122 |
ted | +0.122 |
Neg logit contributions | |
also | -0.069 |
Deal | -0.058 |
narrative | -0.055 |
known | -0.055 |
Amen | -0.053 |
Token | a |
Token ID | 257 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
ors | +0.058 |
affe | +0.055 |
badges | +0.054 |
ops | +0.053 |
cream | +0.052 |
Neg logit contributions | |
also | -0.037 |
Acc | -0.033 |
known | -0.032 |
sch | -0.031 |
Do | -0.030 |
Token | merry |
Token ID | 44570 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
ors | +0.136 |
badges | +0.130 |
cream | +0.127 |
affe | +0.126 |
ted | +0.122 |
Neg logit contributions | |
also | -0.101 |
Deal | -0.099 |
Acc | -0.097 |
sch | -0.093 |
narrative | -0.092 |
Token | - |
Token ID | 12 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ors | +0.047 |
badges | +0.046 |
cream | +0.044 |
als | +0.040 |
affe | +0.039 |
Neg logit contributions | |
also | -0.149 |
sch | -0.143 |
Deal | -0.143 |
Acc | -0.143 |
narrative | -0.140 |
Token | go |
Token ID | 2188 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
ors | +0.156 |
badges | +0.153 |
affe | +0.146 |
cream | +0.146 |
ted | +0.139 |
Neg logit contributions | |
Deal | -0.172 |
also | -0.172 |
Acc | -0.169 |
sch | -0.162 |
narrative | -0.162 |
Token | - |
Token ID | 12 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
badges | +0.059 |
ors | +0.057 |
cream | +0.049 |
als | +0.045 |
ados | +0.044 |
Neg logit contributions | |
also | -0.142 |
sch | -0.140 |
welcome | -0.139 |
Amen | -0.136 |
Do | -0.133 |
Token | round |
Token ID | 744 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
badges | +0.085 |
ors | +0.080 |
als | +0.063 |
ries | +0.061 |
les | +0.061 |
Neg logit contributions | |
also | -0.241 |
Acc | -0.239 |
Amen | -0.233 |
sch | -0.230 |
Do | -0.227 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
badges | +0.503 |
ors | +0.492 |
affe | +0.482 |
cream | +0.454 |
les | +0.424 |
Neg logit contributions | |
also | -0.528 |
sch | -0.480 |
Acc | -0.458 |
known | -0.442 |
winning | -0.438 |
Token | She |
Token ID | 1375 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
badges | +0.265 |
ors | +0.261 |
cream | +0.255 |
ops | +0.253 |
affe | +0.251 |
Neg logit contributions | |
Do | -0.054 |
sch | -0.049 |
Always | -0.048 |
also | -0.047 |
Acc | -0.046 |
Token | climbed |
Token ID | 19952 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ors | +0.058 |
ados | +0.054 |
ales | +0.053 |
badges | +0.053 |
eros | +0.052 |
Neg logit contributions | |
also | -0.042 |
sch | -0.030 |
known | -0.029 |
Acc | -0.028 |
Always | -0.028 |
Token | on |
Token ID | 319 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
ors | +0.254 |
badges | +0.249 |
affe | +0.242 |
cream | +0.239 |
ops | +0.228 |
Neg logit contributions | |
also | -0.195 |
Deal | -0.187 |
Acc | -0.184 |
sch | -0.177 |
known | -0.176 |
Token | and |
Token ID | 290 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ors | +0.154 |
affe | +0.153 |
cream | +0.149 |
ages | +0.145 |
badges | +0.144 |
Neg logit contributions | |
also | -0.069 |
sch | -0.057 |
Do | -0.056 |
first | -0.056 |
Acc | -0.052 |
Token | are |
Token ID | 389 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
badges | +0.174 |
ors | +0.172 |
affe | +0.171 |
als | +0.158 |
les | +0.152 |
Neg logit contributions | |
Acc | -0.261 |
Deal | -0.251 |
Amen | -0.241 |
sch | -0.239 |
narrative | -0.238 |
Token | you |
Token ID | 345 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
Deal | +0.030 |
also | +0.030 |
Acc | +0.028 |
narrative | +0.026 |
sch | +0.026 |
Neg logit contributions | |
ors | -0.081 |
badges | -0.079 |
affe | -0.077 |
cream | -0.077 |
ted | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ors | +0.070 |
badges | +0.068 |
cream | +0.066 |
affe | +0.066 |
ted | +0.064 |
Neg logit contributions | |
also | -0.045 |
Deal | -0.045 |
Acc | -0.041 |
Do | -0.041 |
known | -0.040 |
Token | pizza |
Token ID | 14256 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ors | +0.220 |
cream | +0.204 |
ted | +0.200 |
badges | +0.199 |
les | +0.196 |
Neg logit contributions | |
also | -0.158 |
Deal | -0.151 |
known | -0.147 |
narrative | -0.146 |
welcome | -0.144 |
Token | delivery |
Token ID | 7585 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ors | +0.543 |
badges | +0.519 |
ted | +0.488 |
cream | +0.483 |
oos | +0.477 |
Neg logit contributions | |
also | -0.356 |
welcome | -0.321 |
Do | -0.287 |
narrative | -0.285 |
Amen | -0.284 |
Token | guys |
Token ID | 3730 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
ors | +0.375 |
badges | +0.366 |
vered | +0.362 |
cream | +0.350 |
cheeks | +0.345 |
Neg logit contributions | |
also | -0.268 |
welcome | -0.259 |
Do | -0.236 |
first | -0.234 |
Amen | -0.227 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
badges | +0.622 |
ors | +0.605 |
affe | +0.600 |
cream | +0.585 |
ted | +0.572 |
Neg logit contributions | |
also | -0.434 |
welcome | -0.362 |
Do | -0.358 |
Always | -0.343 |
doing | -0.343 |
Token | Their |
Token ID | 5334 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
ors | +0.280 |
cream | +0.270 |
badges | +0.267 |
affe | +0.264 |
les | +0.258 |
Neg logit contributions | |
also | -0.179 |
Do | -0.170 |
Deal | -0.167 |
sch | -0.162 |
Acc | -0.161 |
Token | dad |
Token ID | 9955 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
ors | +0.108 |
cream | +0.107 |
affe | +0.101 |
ops | +0.098 |
ted | +0.097 |
Neg logit contributions | |
also | -0.075 |
Deal | -0.074 |
sch | -0.072 |
welcome | -0.068 |
narrative | -0.067 |
Token | said |
Token ID | 531 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
ors | +0.467 |
ages | +0.435 |
ados | +0.433 |
affe | +0.427 |
badges | +0.426 |
Neg logit contributions | |
also | -0.345 |
first | -0.229 |
Amen | -0.229 |
Do | -0.229 |
sch | -0.218 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ors | +0.069 |
badges | +0.067 |
cream | +0.067 |
affe | +0.063 |
ops | +0.061 |
Neg logit contributions | |
also | -0.100 |
welcome | -0.096 |
Do | -0.095 |
Deal | -0.094 |
Acc | -0.092 |
Token | at |
Token ID | 379 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
ors | +0.194 |
cream | +0.180 |
ted | +0.175 |
badges | +0.173 |
ries | +0.168 |
Neg logit contributions | |
also | -0.167 |
Deal | -0.155 |
welcome | -0.146 |
Amen | -0.145 |
sch | -0.143 |
Token | a |
Token ID | 257 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
also | +0.415 |
welcome | +0.345 |
Deal | +0.330 |
sch | +0.330 |
known | +0.328 |
Neg logit contributions | |
ors | -0.700 |
affe | -0.695 |
badges | -0.679 |
ops | -0.675 |
cream | -0.671 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
also | +0.339 |
Deal | +0.299 |
sch | +0.292 |
Acc | +0.288 |
welcome | +0.284 |
Neg logit contributions | |
ors | -0.584 |
cream | -0.557 |
badges | -0.554 |
ted | -0.548 |
als | -0.526 |
Token | who |
Token ID | 508 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
also | +0.315 |
Always | +0.280 |
Do | +0.279 |
Amen | +0.273 |
Acc | +0.269 |
Neg logit contributions | |
badges | -0.316 |
ors | -0.316 |
affe | -0.304 |
als | -0.295 |
ops | -0.293 |
Token | was |
Token ID | 373 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
also | +0.353 |
known | +0.300 |
sch | +0.283 |
Always | +0.277 |
Acc | +0.267 |
Neg logit contributions | |
ors | -0.471 |
badges | -0.456 |
ados | -0.440 |
cream | -0.437 |
affe | -0.436 |
Token | also |
Token ID | 635 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Deal | +0.357 |
also | +0.355 |
Acc | +0.345 |
narrative | +0.323 |
sch | +0.323 |
Neg logit contributions | |
ors | -0.674 |
badges | -0.662 |
affe | -0.644 |
cream | -0.642 |
ted | -0.621 |
Token | at |
Token ID | 379 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
also | +0.405 |
known | +0.352 |
Deal | +0.347 |
Acc | +0.344 |
sch | +0.335 |
Neg logit contributions | |
ors | -0.934 |
affe | -0.890 |
badges | -0.883 |
cream | -0.870 |
ops | -0.855 |
Token | the |
Token ID | 262 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
also | +0.247 |
first | +0.220 |
known | +0.219 |
winning | +0.212 |
Do | +0.209 |
Neg logit contributions | |
affe | -0.518 |
ors | -0.507 |
cream | -0.487 |
als | -0.486 |
badges | -0.475 |
Token | park |
Token ID | 3952 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
also | +0.238 |
sch | +0.212 |
Deal | +0.212 |
narrative | +0.210 |
welcome | +0.206 |
Neg logit contributions | |
ors | -0.343 |
badges | -0.314 |
cream | -0.309 |
affe | -0.306 |
ted | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
also | +0.137 |
first | +0.118 |
winning | +0.114 |
living | +0.112 |
sill | +0.109 |
Neg logit contributions | |
badges | -0.173 |
ors | -0.172 |
affe | -0.168 |
les | -0.164 |
cream | -0.158 |
Token | He |
Token ID | 679 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Deal | +0.161 |
also | +0.158 |
Do | +0.153 |
Acc | +0.147 |
Always | +0.146 |
Neg logit contributions | |
ors | -0.338 |
badges | -0.333 |
cream | -0.318 |
les | -0.318 |
affe | -0.317 |
Token | to |
Token ID | 284 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
ors | +0.002 |
badges | +0.002 |
ted | +0.002 |
cream | +0.002 |
aw | +0.002 |
Neg logit contributions | |
Deal | -0.002 |
Acc | -0.002 |
narrative | -0.002 |
Amen | -0.002 |
Do | -0.002 |
Token | find |
Token ID | 1064 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
also | +0.415 |
welcome | +0.352 |
Deal | +0.351 |
known | +0.333 |
Amen | +0.330 |
Neg logit contributions | |
ors | -0.749 |
affe | -0.720 |
cream | -0.715 |
badges | -0.706 |
ops | -0.704 |
Token | something |
Token ID | 1223 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
also | +0.299 |
welcome | +0.293 |
living | +0.268 |
Do | +0.232 |
right | +0.229 |
Neg logit contributions | |
ops | -0.756 |
affe | -0.715 |
round | -0.693 |
ors | -0.684 |
ages | -0.653 |
Token | fun |
Token ID | 1257 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
also | +0.231 |
welcome | +0.177 |
Do | +0.174 |
impossible | +0.161 |
living | +0.161 |
Neg logit contributions | |
ors | -0.518 |
badges | -0.514 |
affe | -0.508 |
ted | -0.498 |
ops | -0.496 |
Token | but |
Token ID | 475 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
also | +0.395 |
welcome | +0.352 |
doing | +0.351 |
Do | +0.350 |
living | +0.331 |
Neg logit contributions | |
affe | -0.480 |
badges | -0.458 |
ted | -0.453 |
ors | -0.449 |
cream | -0.447 |
Token | also |
Token ID | 635 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
also | +0.331 |
Deal | +0.305 |
Acc | +0.299 |
known | +0.294 |
Do | +0.287 |
Neg logit contributions | |
ors | -0.454 |
badges | -0.445 |
affe | -0.434 |
cream | -0.425 |
les | -0.417 |
Token | useful |
Token ID | 4465 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
also | +0.471 |
Acc | +0.419 |
known | +0.417 |
Deal | +0.413 |
Do | +0.389 |
Neg logit contributions | |
ors | -0.856 |
badges | -0.817 |
affe | -0.811 |
cream | -0.785 |
ops | -0.781 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
also | +0.313 |
welcome | +0.294 |
doing | +0.284 |
Do | +0.281 |
first | +0.280 |
Neg logit contributions | |
affe | -0.433 |
ors | -0.402 |
cream | -0.401 |
wo | -0.398 |
round | -0.391 |
Token | One |
Token ID | 1881 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Deal | +0.166 |
also | +0.162 |
Acc | +0.154 |
Do | +0.147 |
Always | +0.145 |
Neg logit contributions | |
ors | -0.370 |
badges | -0.366 |
cream | -0.353 |
affe | -0.351 |
les | -0.346 |
Token | of |
Token ID | 286 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
also | +0.123 |
welcome | +0.074 |
narrative | +0.070 |
known | +0.067 |
sch | +0.067 |
Neg logit contributions | |
ors | -0.540 |
badges | -0.535 |
affe | -0.504 |
cream | -0.504 |
ted | -0.493 |
Token | them |
Token ID | 606 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
also | +0.360 |
known | +0.310 |
Deal | +0.302 |
Do | +0.297 |
welcome | +0.289 |
Neg logit contributions | |
ors | -0.615 |
affe | -0.596 |
cream | -0.590 |
badges | -0.583 |
ops | -0.574 |
Token | The |
Token ID | 383 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ors | +0.274 |
badges | +0.272 |
cream | +0.262 |
affe | +0.262 |
les | +0.254 |
Neg logit contributions | |
Deal | -0.135 |
also | -0.132 |
Acc | -0.129 |
sch | -0.121 |
narrative | -0.119 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
also | +0.443 |
Deal | +0.417 |
narrative | +0.409 |
welcome | +0.396 |
Amen | +0.392 |
Neg logit contributions | |
ors | -0.489 |
cream | -0.451 |
badges | -0.434 |
ted | -0.425 |
ops | -0.417 |
Token | and |
Token ID | 290 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
also | +0.300 |
Always | +0.237 |
known | +0.222 |
Acc | +0.219 |
Amen | +0.218 |
Neg logit contributions | |
ors | -0.459 |
badges | -0.447 |
cream | -0.434 |
ados | -0.417 |
ales | -0.415 |
Token | her |
Token ID | 607 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
also | +0.201 |
known | +0.174 |
welcome | +0.152 |
narrative | +0.147 |
Deal | +0.146 |
Neg logit contributions | |
ors | -0.479 |
cream | -0.451 |
badges | -0.434 |
ops | -0.431 |
round | -0.422 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
also | +0.252 |
living | +0.231 |
welcome | +0.212 |
first | +0.203 |
narrative | +0.200 |
Neg logit contributions | |
ors | -0.476 |
cream | -0.436 |
round | -0.427 |
ales | -0.417 |
ted | -0.398 |
Token | also |
Token ID | 635 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
also | +0.130 |
known | +0.105 |
living | +0.098 |
very | +0.097 |
welcome | +0.097 |
Neg logit contributions | |
cream | -0.197 |
ors | -0.195 |
eros | -0.194 |
ados | -0.186 |
badges | -0.185 |
Token | spread |
Token ID | 4104 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
also | +0.545 |
known | +0.508 |
welcome | +0.474 |
living | +0.413 |
glad | +0.400 |
Neg logit contributions | |
ors | -0.916 |
affe | -0.813 |
cream | -0.811 |
eros | -0.776 |
ops | -0.775 |
Token | their |
Token ID | 511 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
also | +0.190 |
welcome | +0.177 |
known | +0.162 |
very | +0.161 |
right | +0.158 |
Neg logit contributions | |
ors | -0.424 |
affe | -0.410 |
ops | -0.398 |
cream | -0.390 |
round | -0.388 |
Token | honesty |
Token ID | 24345 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
also | +0.324 |
narrative | +0.311 |
welcome | +0.305 |
Deal | +0.304 |
living | +0.303 |
Neg logit contributions | |
ors | -0.351 |
cream | -0.318 |
affe | -0.316 |
round | -0.304 |
ops | -0.292 |
Token | throughout |
Token ID | 3690 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
also | +0.129 |
living | +0.111 |
first | +0.106 |
right | +0.104 |
very | +0.101 |
Neg logit contributions | |
ors | -0.175 |
cream | -0.173 |
badges | -0.173 |
wo | -0.164 |
affe | -0.159 |
Token | the |
Token ID | 262 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
also | +0.132 |
Deal | +0.125 |
Acc | +0.124 |
known | +0.121 |
narrative | +0.117 |
Neg logit contributions | |
ors | -0.203 |
badges | -0.199 |
affe | -0.198 |
cream | -0.198 |
ops | -0.187 |
Token | explore |
Token ID | 7301 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
also | +0.032 |
known | +0.027 |
welcome | +0.026 |
Acc | +0.026 |
Deal | +0.025 |
Neg logit contributions | |
ors | -0.080 |
badges | -0.078 |
affe | -0.076 |
ted | -0.076 |
ops | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
also | +0.308 |
welcome | +0.253 |
sch | +0.251 |
Acc | +0.250 |
living | +0.249 |
Neg logit contributions | |
badges | -0.484 |
affe | -0.475 |
ors | -0.473 |
cream | -0.473 |
ops | -0.450 |
Token | but |
Token ID | 475 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
also | +0.283 |
Do | +0.243 |
known | +0.232 |
Acc | +0.226 |
sch | +0.226 |
Neg logit contributions | |
ors | -0.492 |
badges | -0.477 |
cream | -0.476 |
affe | -0.476 |
ops | -0.462 |
Token | it |
Token ID | 340 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
also | +0.359 |
known | +0.312 |
Deal | +0.304 |
Do | +0.301 |
Acc | +0.299 |
Neg logit contributions | |
badges | -0.527 |
ors | -0.526 |
affe | -0.505 |
cream | -0.500 |
les | -0.491 |
Token | 's |
Token ID | 338 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
also | +0.245 |
known | +0.204 |
sch | +0.195 |
Deal | +0.192 |
Acc | +0.191 |
Neg logit contributions | |
badges | -0.374 |
ors | -0.374 |
cream | -0.365 |
affe | -0.353 |
round | -0.343 |
Token | also |
Token ID | 635 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
also | +0.300 |
Deal | +0.281 |
Acc | +0.272 |
known | +0.256 |
narrative | +0.248 |
Neg logit contributions | |
ors | -0.724 |
badges | -0.709 |
affe | -0.695 |
cream | -0.690 |
ted | -0.673 |
Token | important |
Token ID | 1593 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
also | +0.391 |
known | +0.313 |
Acc | +0.312 |
Deal | +0.308 |
welcome | +0.306 |
Neg logit contributions | |
ors | -0.943 |
badges | -0.883 |
cream | -0.878 |
affe | -0.877 |
ops | -0.874 |
Token | to |
Token ID | 284 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
also | +0.237 |
Always | +0.200 |
Do | +0.189 |
welcome | +0.185 |
known | +0.184 |
Neg logit contributions | |
affe | -0.524 |
badges | -0.519 |
ors | -0.514 |
ops | -0.500 |
wo | -0.500 |
Token | always |
Token ID | 1464 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Deal | +0.239 |
also | +0.232 |
Acc | +0.232 |
sch | +0.218 |
narrative | +0.218 |
Neg logit contributions | |
ors | -0.414 |
badges | -0.407 |
affe | -0.394 |
cream | -0.392 |
ted | -0.379 |
Token | be |
Token ID | 307 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Deal | +0.331 |
Acc | +0.324 |
also | +0.323 |
narrative | +0.305 |
sch | +0.304 |
Neg logit contributions | |
ors | -0.533 |
badges | -0.527 |
affe | -0.509 |
cream | -0.508 |
ted | -0.488 |
Token | careful |
Token ID | 8161 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
also | +0.232 |
known | +0.201 |
Acc | +0.190 |
welcome | +0.184 |
Always | +0.180 |
Neg logit contributions | |
ors | -0.618 |
ops | -0.608 |
affe | -0.607 |
badges | -0.594 |
cream | -0.589 |
Token | broken |
Token ID | 25826 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Deal | +0.052 |
Acc | +0.051 |
also | +0.051 |
narrative | +0.048 |
sch | +0.047 |
Neg logit contributions | |
ors | -0.122 |
badges | -0.119 |
affe | -0.116 |
cream | -0.116 |
ted | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
also | +0.421 |
Acc | +0.378 |
Amen | +0.373 |
Always | +0.371 |
living | +0.371 |
Neg logit contributions | |
cream | -0.380 |
badges | -0.376 |
ors | -0.364 |
ops | -0.359 |
als | -0.346 |
Token | but |
Token ID | 475 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
also | +0.280 |
Acc | +0.219 |
Do | +0.217 |
not | +0.215 |
glad | +0.212 |
Neg logit contributions | |
ors | -0.498 |
ops | -0.487 |
affe | -0.469 |
als | -0.468 |
cream | -0.464 |
Token | he |
Token ID | 339 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
also | +0.339 |
Acc | +0.303 |
Deal | +0.302 |
known | +0.300 |
Always | +0.291 |
Neg logit contributions | |
ors | -0.517 |
badges | -0.514 |
affe | -0.493 |
cream | -0.484 |
les | -0.474 |
Token | was |
Token ID | 373 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
also | +0.351 |
known | +0.277 |
Acc | +0.256 |
Always | +0.248 |
Amen | +0.229 |
Neg logit contributions | |
ors | -0.603 |
badges | -0.580 |
ries | -0.554 |
round | -0.549 |
cream | -0.548 |
Token | also |
Token ID | 635 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
also | +0.288 |
Deal | +0.282 |
Acc | +0.272 |
known | +0.253 |
sch | +0.249 |
Neg logit contributions | |
ors | -0.707 |
badges | -0.695 |
affe | -0.678 |
cream | -0.675 |
ted | -0.656 |
Token | very |
Token ID | 845 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
also | +0.322 |
Acc | +0.293 |
Deal | +0.291 |
known | +0.282 |
sch | +0.261 |
Neg logit contributions | |
ors | -0.955 |
badges | -0.919 |
affe | -0.915 |
cream | -0.898 |
ops | -0.879 |
Token | wise |
Token ID | 10787 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
also | +0.319 |
Deal | +0.303 |
Acc | +0.290 |
known | +0.273 |
Amen | +0.265 |
Neg logit contributions | |
ors | -0.825 |
badges | -0.811 |
affe | -0.792 |
cream | -0.788 |
ted | -0.772 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
also | +0.387 |
Acc | +0.359 |
Deal | +0.357 |
Do | +0.351 |
sch | +0.351 |
Neg logit contributions | |
ors | -0.272 |
badges | -0.269 |
cream | -0.260 |
ops | -0.246 |
affe | -0.243 |
Token | He |
Token ID | 679 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Deal | +0.148 |
also | +0.144 |
Acc | +0.139 |
Do | +0.132 |
Always | +0.131 |
Neg logit contributions | |
ors | -0.357 |
badges | -0.354 |
cream | -0.340 |
affe | -0.338 |
les | -0.334 |
Token | learned |
Token ID | 4499 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
also | +0.330 |
known | +0.243 |
Always | +0.216 |
Acc | +0.201 |
always | +0.196 |
Neg logit contributions | |
ors | -0.536 |
ados | -0.492 |
ries | -0.491 |
badges | -0.474 |
ops | -0.469 |
Token | are |
Token ID | 389 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
badges | +0.229 |
ors | +0.215 |
ted | +0.208 |
cream | +0.204 |
les | +0.204 |
Neg logit contributions | |
Deal | -0.244 |
narrative | -0.242 |
Acc | -0.238 |
Amen | -0.220 |
known | -0.213 |
Token | safe |
Token ID | 3338 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
also | +0.475 |
Deal | +0.460 |
Acc | +0.444 |
known | +0.420 |
narrative | +0.419 |
Neg logit contributions | |
ors | -1.002 |
badges | -0.975 |
affe | -0.957 |
cream | -0.953 |
ted | -0.926 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
also | +0.448 |
living | +0.408 |
welcome | +0.395 |
Always | +0.378 |
first | +0.374 |
Neg logit contributions | |
badges | -0.551 |
affe | -0.526 |
ors | -0.517 |
cream | -0.512 |
ops | -0.490 |
Token | They |
Token ID | 1119 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Deal | +0.238 |
also | +0.235 |
Acc | +0.228 |
narrative | +0.213 |
sch | +0.212 |
Neg logit contributions | |
ors | -0.489 |
badges | -0.482 |
affe | -0.467 |
cream | -0.467 |
ted | -0.451 |
Token | are |
Token ID | 389 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
also | +0.370 |
known | +0.253 |
welcome | +0.248 |
narrative | +0.247 |
Deal | +0.237 |
Neg logit contributions | |
ors | -0.642 |
ados | -0.578 |
cream | -0.578 |
eros | -0.577 |
ries | -0.571 |
Token | also |
Token ID | 635 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
also | +0.301 |
Deal | +0.273 |
Acc | +0.265 |
known | +0.247 |
sch | +0.236 |
Neg logit contributions | |
ors | -0.865 |
badges | -0.834 |
affe | -0.830 |
cream | -0.821 |
ops | -0.804 |
Token | sorry |
Token ID | 7926 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
also | +0.300 |
welcome | +0.227 |
glad | +0.216 |
known | +0.213 |
Acc | +0.213 |
Neg logit contributions | |
ors | -1.093 |
affe | -1.035 |
ops | -0.998 |
cream | -0.994 |
ted | -0.990 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
also | +0.318 |
Do | +0.293 |
Deal | +0.264 |
not | +0.262 |
welcome | +0.261 |
Neg logit contributions | |
badges | -0.479 |
cream | -0.473 |
ors | -0.458 |
ted | -0.445 |
affe | -0.443 |
Token | They |
Token ID | 1119 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Deal | +0.201 |
Acc | +0.201 |
also | +0.200 |
sch | +0.195 |
narrative | +0.193 |
Neg logit contributions | |
badges | -0.310 |
ors | -0.310 |
cream | -0.300 |
affe | -0.300 |
ted | -0.288 |
Token | did |
Token ID | 750 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
also | +0.259 |
Deal | +0.231 |
Acc | +0.219 |
narrative | +0.219 |
known | +0.211 |
Neg logit contributions | |
ors | -0.472 |
badges | -0.439 |
cream | -0.437 |
affe | -0.429 |
ted | -0.421 |
Token | not |
Token ID | 407 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
Deal | +0.292 |
sch | +0.283 |
narrative | +0.274 |
Acc | +0.269 |
acy | +0.269 |
Neg logit contributions | |
badges | -0.652 |
ors | -0.626 |
cream | -0.612 |
bars | -0.589 |
affe | -0.588 |
Token | knew |
Token ID | 2993 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ors | +0.089 |
ted | +0.086 |
badges | +0.083 |
les | +0.083 |
cream | +0.081 |
Neg logit contributions | |
Deal | -0.105 |
Amen | -0.100 |
narrative | -0.099 |
known | -0.099 |
sch | -0.097 |
Token | that |
Token ID | 326 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
also | +0.474 |
known | +0.412 |
Always | +0.408 |
Do | +0.405 |
Acc | +0.395 |
Neg logit contributions | |
badges | -0.696 |
ors | -0.683 |
affe | -0.654 |
les | -0.643 |
ops | -0.637 |
Token | only |
Token ID | 691 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
also | +0.342 |
Do | +0.304 |
Acc | +0.297 |
known | +0.290 |
Always | +0.286 |
Neg logit contributions | |
ors | -0.587 |
badges | -0.577 |
affe | -0.569 |
les | -0.547 |
cream | -0.543 |
Token | real |
Token ID | 1103 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
also | +0.449 |
known | +0.397 |
Do | +0.395 |
welcome | +0.388 |
Acc | +0.376 |
Neg logit contributions | |
ors | -0.790 |
affe | -0.733 |
badges | -0.731 |
ops | -0.718 |
les | -0.699 |
Token | wheat |
Token ID | 17135 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
living | +0.251 |
welcome | +0.247 |
also | +0.246 |
Do | +0.232 |
Always | +0.216 |
Neg logit contributions | |
ors | -0.334 |
cream | -0.320 |
round | -0.318 |
badges | -0.308 |
ked | -0.307 |
Token | could |
Token ID | 714 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
also | +0.062 |
living | +0.051 |
first | +0.049 |
doing | +0.049 |
welcome | +0.048 |
Neg logit contributions | |
badges | -0.099 |
ors | -0.093 |
affe | -0.091 |
wo | -0.090 |
round | -0.087 |
Token | make |
Token ID | 787 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
also | +0.439 |
known | +0.345 |
Deal | +0.342 |
welcome | +0.337 |
Always | +0.320 |
Neg logit contributions | |
ors | -0.890 |
badges | -0.866 |
cream | -0.854 |
ted | -0.848 |
affe | -0.842 |
Token | good |
Token ID | 922 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
also | +0.325 |
welcome | +0.303 |
known | +0.286 |
doing | +0.262 |
living | +0.262 |
Neg logit contributions | |
round | -0.580 |
badges | -0.577 |
affe | -0.572 |
ors | -0.559 |
cream | -0.553 |
Token | bread |
Token ID | 8509 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
also | +0.342 |
welcome | +0.341 |
doing | +0.318 |
narrative | +0.313 |
living | +0.309 |
Neg logit contributions | |
affe | -0.421 |
badges | -0.412 |
ors | -0.408 |
round | -0.398 |
cream | -0.395 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
also | +0.092 |
welcome | +0.081 |
known | +0.075 |
Always | +0.074 |
narrative | +0.074 |
Neg logit contributions | |
badges | -0.099 |
ors | -0.096 |
ted | -0.093 |
affe | -0.092 |
cream | -0.091 |
Token | And |
Token ID | 843 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Deal | +0.154 |
also | +0.153 |
Acc | +0.147 |
Do | +0.137 |
Always | +0.137 |
Neg logit contributions | |
ors | -0.336 |
badges | -0.333 |
cream | -0.320 |
affe | -0.319 |
les | -0.312 |
Token | they |
Token ID | 484 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
ors | +0.156 |
affe | +0.156 |
ops | +0.151 |
omes | +0.149 |
les | +0.146 |
Neg logit contributions | |
also | -0.081 |
known | -0.063 |
welcome | -0.061 |
sch | -0.059 |
Do | -0.059 |
Token | finished |
Token ID | 5201 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
also | +0.471 |
known | +0.362 |
welcome | +0.317 |
first | +0.309 |
narrative | +0.293 |
Neg logit contributions | |
ors | -0.769 |
ados | -0.721 |
eros | -0.710 |
cream | -0.709 |
ries | -0.706 |
Token | ro |
Token ID | 686 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
also | +0.329 |
Acc | +0.294 |
Deal | +0.279 |
sch | +0.272 |
doing | +0.271 |
Neg logit contributions | |
affe | -0.529 |
ors | -0.491 |
badges | -0.491 |
als | -0.475 |
ted | -0.470 |
Token | asting |
Token ID | 9222 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
also | +0.421 |
Deal | +0.391 |
welcome | +0.387 |
narrative | +0.384 |
known | +0.382 |
Neg logit contributions | |
ors | -0.343 |
badges | -0.337 |
affe | -0.327 |
ted | -0.321 |
ries | -0.301 |
Token | marsh |
Token ID | 22397 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
refreshed | +0.246 |
also | +0.243 |
right | +0.234 |
living | +0.232 |
welcome | +0.226 |
Neg logit contributions | |
affe | -0.427 |
ors | -0.417 |
phones | -0.390 |
lets | -0.384 |
eman | -0.369 |
Token | m |
Token ID | 76 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
also | +0.058 |
Acc | +0.051 |
Deal | +0.050 |
Always | +0.048 |
Do | +0.046 |
Neg logit contributions | |
badges | -0.130 |
affe | -0.123 |
ors | -0.120 |
arrow | -0.118 |
omes | -0.111 |
Token | allows |
Token ID | 47205 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
also | +0.595 |
Acc | +0.540 |
doing | +0.522 |
glad | +0.510 |
welcome | +0.507 |
Neg logit contributions | |
affe | -0.711 |
badges | -0.688 |
ors | -0.644 |
als | -0.616 |
phones | -0.611 |
Token | , |
Token ID | 11 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
also | +0.112 |
first | +0.096 |
right | +0.092 |
ready | +0.090 |
very | +0.090 |
Neg logit contributions | |
badges | -0.180 |
affe | -0.166 |
ors | -0.161 |
eros | -0.160 |
tal | -0.155 |
Token | they |
Token ID | 484 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
also | +0.244 |
Acc | +0.200 |
Do | +0.196 |
Always | +0.195 |
glad | +0.193 |
Neg logit contributions | |
ors | -0.266 |
affe | -0.248 |
ops | -0.234 |
badges | -0.234 |
eros | -0.231 |
Token | went |
Token ID | 1816 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
also | +0.287 |
known | +0.204 |
welcome | +0.183 |
always | +0.182 |
full | +0.175 |
Neg logit contributions | |
ors | -0.449 |
eros | -0.432 |
badges | -0.423 |
ados | -0.411 |
affe | -0.409 |
Token | inside |
Token ID | 2641 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
also | +0.224 |
welcome | +0.197 |
sch | +0.195 |
Deal | +0.191 |
living | +0.190 |
Neg logit contributions | |
affe | -0.348 |
ors | -0.343 |
ops | -0.321 |
badges | -0.321 |
cream | -0.320 |
Token | had |
Token ID | 550 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
also | +0.500 |
known | +0.403 |
Always | +0.355 |
sch | +0.348 |
welcome | +0.347 |
Neg logit contributions | |
ors | -0.714 |
badges | -0.673 |
ados | -0.657 |
cream | -0.650 |
ries | -0.648 |
Token | done |
Token ID | 1760 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
also | +0.477 |
known | +0.476 |
winning | +0.371 |
sch | +0.370 |
Always | +0.368 |
Neg logit contributions | |
ors | -0.884 |
affe | -0.855 |
eros | -0.809 |
round | -0.794 |
ops | -0.778 |
Token | something |
Token ID | 1223 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
also | +0.435 |
Acc | +0.402 |
known | +0.389 |
winning | +0.382 |
Deal | +0.381 |
Neg logit contributions | |
affe | -0.495 |
ors | -0.479 |
badges | -0.474 |
als | -0.468 |
ted | -0.454 |
Token | brave |
Token ID | 14802 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
also | +0.205 |
Acc | +0.177 |
known | +0.162 |
Do | +0.159 |
Deal | +0.159 |
Neg logit contributions | |
ors | -0.436 |
badges | -0.433 |
affe | -0.421 |
als | -0.411 |
cream | -0.410 |
Token | but |
Token ID | 475 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
also | +0.365 |
Do | +0.345 |
welcome | +0.342 |
narrative | +0.330 |
known | +0.328 |
Neg logit contributions | |
ors | -0.337 |
badges | -0.336 |
cream | -0.323 |
ops | -0.292 |
affe | -0.291 |
Token | also |
Token ID | 635 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
Deal | +0.317 |
Acc | +0.305 |
also | +0.299 |
Amen | +0.291 |
sch | +0.291 |
Neg logit contributions | |
ors | -0.378 |
badges | -0.372 |
cream | -0.365 |
affe | -0.361 |
ted | -0.349 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
also | +0.445 |
Acc | +0.406 |
Deal | +0.402 |
known | +0.401 |
sch | +0.374 |
Neg logit contributions | |
ors | -0.831 |
badges | -0.795 |
affe | -0.782 |
cream | -0.761 |
ops | -0.749 |
Token | very |
Token ID | 845 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
also | +0.233 |
Deal | +0.225 |
Acc | +0.220 |
known | +0.207 |
narrative | +0.202 |
Neg logit contributions | |
ors | -0.485 |
badges | -0.475 |
affe | -0.463 |
cream | -0.461 |
ops | -0.445 |
Token | shy |
Token ID | 15800 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Deal | +0.365 |
Acc | +0.350 |
also | +0.347 |
sch | +0.331 |
narrative | +0.330 |
Neg logit contributions | |
ors | -0.722 |
badges | -0.705 |
affe | -0.690 |
cream | -0.688 |
les | -0.671 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
also | +0.317 |
Acc | +0.296 |
Deal | +0.294 |
Do | +0.294 |
sch | +0.284 |
Neg logit contributions | |
badges | -0.267 |
ors | -0.261 |
cream | -0.254 |
affe | -0.246 |
ops | -0.236 |
Token | He |
Token ID | 679 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Deal | +0.143 |
also | +0.141 |
Acc | +0.135 |
sch | +0.125 |
narrative | +0.125 |
Neg logit contributions | |
ors | -0.329 |
badges | -0.325 |
cream | -0.315 |
affe | -0.314 |
les | -0.305 |
Token | " |
Token ID | 366 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
ors | +0.117 |
badges | +0.107 |
affe | +0.105 |
cream | +0.102 |
les | +0.101 |
Neg logit contributions | |
also | -0.193 |
Deal | -0.188 |
Acc | -0.183 |
known | -0.182 |
narrative | -0.180 |
Token | That |
Token ID | 2504 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
Acc | +0.318 |
also | +0.317 |
Deal | +0.314 |
Amen | +0.282 |
known | +0.280 |
Neg logit contributions | |
ors | -0.845 |
badges | -0.823 |
affe | -0.793 |
cream | -0.780 |
les | -0.772 |
Token | 's |
Token ID | 338 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
also | +0.374 |
narrative | +0.259 |
welcome | +0.255 |
Do | +0.249 |
first | +0.246 |
Neg logit contributions | |
ors | -0.804 |
badges | -0.774 |
ted | -0.773 |
ked | -0.761 |
ged | -0.758 |
Token | what |
Token ID | 644 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
also | +0.336 |
Deal | +0.332 |
Acc | +0.315 |
narrative | +0.294 |
known | +0.290 |
Neg logit contributions | |
ors | -0.784 |
badges | -0.768 |
affe | -0.753 |
cream | -0.743 |
ted | -0.731 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
also | +0.181 |
Do | +0.155 |
welcome | +0.135 |
Always | +0.120 |
winning | +0.116 |
Neg logit contributions | |
ors | -0.681 |
badges | -0.660 |
les | -0.655 |
affe | -0.654 |
ted | -0.653 |
Token | m |
Token ID | 76 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
also | +0.115 |
known | +0.088 |
welcome | +0.086 |
doing | +0.085 |
Always | +0.084 |
Neg logit contributions | |
badges | -0.207 |
affe | -0.203 |
ors | -0.200 |
stret | -0.195 |
oos | -0.189 |
Token | ies |
Token ID | 444 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
also | +0.594 |
welcome | +0.537 |
Deal | +0.515 |
Acc | +0.511 |
doing | +0.500 |
Neg logit contributions | |
badges | -0.698 |
affe | -0.691 |
ted | -0.669 |
ors | -0.632 |
cream | -0.619 |
Token | are |
Token ID | 389 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
also | +0.052 |
welcome | +0.045 |
doing | +0.044 |
Always | +0.036 |
living | +0.036 |
Neg logit contributions | |
badges | -0.108 |
affe | -0.107 |
cream | -0.102 |
ors | -0.102 |
eros | -0.098 |
Token | for |
Token ID | 329 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
also | +0.384 |
welcome | +0.335 |
known | +0.328 |
doing | +0.314 |
Deal | +0.311 |
Neg logit contributions | |
affe | -0.718 |
ors | -0.715 |
cream | -0.712 |
badges | -0.711 |
ted | -0.691 |
Token | , |
Token ID | 11 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
welcome | +0.256 |
also | +0.255 |
doing | +0.245 |
Do | +0.230 |
living | +0.227 |
Neg logit contributions | |
affe | -0.529 |
cream | -0.478 |
badges | -0.473 |
round | -0.473 |
ked | -0.468 |
Token | to |
Token ID | 284 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
also | +0.167 |
Deal | +0.146 |
Do | +0.146 |
welcome | +0.135 |
Acc | +0.134 |
Neg logit contributions | |
ors | -0.284 |
badges | -0.271 |
cream | -0.269 |
affe | -0.268 |
ops | -0.265 |
Token | and |
Token ID | 290 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
badges | +0.204 |
ors | +0.200 |
cream | +0.191 |
affe | +0.190 |
als | +0.186 |
Neg logit contributions | |
Acc | -0.179 |
also | -0.173 |
Deal | -0.173 |
narrative | -0.170 |
known | -0.169 |
Token | dance |
Token ID | 9280 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
also | +0.403 |
known | +0.342 |
Do | +0.335 |
sch | +0.335 |
welcome | +0.334 |
Neg logit contributions | |
ors | -0.519 |
affe | -0.484 |
ops | -0.467 |
cream | -0.465 |
badges | -0.462 |
Token | , |
Token ID | 11 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
also | +0.277 |
welcome | +0.247 |
living | +0.246 |
Do | +0.243 |
sch | +0.239 |
Neg logit contributions | |
cream | -0.399 |
badges | -0.385 |
ors | -0.381 |
affe | -0.378 |
ries | -0.371 |
Token | but |
Token ID | 475 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
also | +0.297 |
Do | +0.261 |
Always | +0.247 |
Acc | +0.245 |
sch | +0.242 |
Neg logit contributions | |
ors | -0.405 |
cream | -0.390 |
badges | -0.386 |
affe | -0.378 |
ops | -0.371 |
Token | he |
Token ID | 339 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
also | +0.334 |
Deal | +0.291 |
known | +0.290 |
Acc | +0.283 |
Do | +0.278 |
Neg logit contributions | |
ors | -0.495 |
badges | -0.485 |
affe | -0.471 |
cream | -0.464 |
les | -0.454 |
Token | also |
Token ID | 635 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
also | +0.327 |
known | +0.244 |
Always | +0.217 |
Acc | +0.206 |
narrative | +0.204 |
Neg logit contributions | |
ors | -0.578 |
badges | -0.576 |
cream | -0.556 |
affe | -0.536 |
ados | -0.530 |
Token | liked |
Token ID | 8288 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
also | +0.537 |
known | +0.470 |
Acc | +0.441 |
Deal | +0.441 |
welcome | +0.436 |
Neg logit contributions | |
ors | -0.792 |
badges | -0.752 |
cream | -0.746 |
affe | -0.737 |
ted | -0.706 |
Token | to |
Token ID | 284 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
also | +0.288 |
Do | +0.249 |
known | +0.247 |
winning | +0.246 |
sch | +0.244 |
Neg logit contributions | |
affe | -0.555 |
ors | -0.547 |
badges | -0.532 |
ops | -0.531 |
cream | -0.519 |
Token | tell |
Token ID | 1560 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
also | +0.231 |
known | +0.181 |
welcome | +0.181 |
Amen | +0.176 |
Deal | +0.175 |
Neg logit contributions | |
cream | -0.462 |
ors | -0.459 |
badges | -0.449 |
ted | -0.447 |
affe | -0.441 |
Token | jokes |
Token ID | 14532 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
also | +0.213 |
welcome | +0.205 |
living | +0.195 |
winning | +0.183 |
Do | +0.179 |
Neg logit contributions | |
ops | -0.404 |
affe | -0.395 |
ked | -0.389 |
ors | -0.386 |
ged | -0.379 |
Token | and |
Token ID | 290 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
also | +0.040 |
living | +0.032 |
Do | +0.032 |
very | +0.031 |
first | +0.031 |
Neg logit contributions | |
badges | -0.056 |
ors | -0.054 |
eros | -0.052 |
tal | -0.052 |
anged | -0.051 |
Token | He |
Token ID | 679 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
ors | +0.273 |
badges | +0.265 |
cream | +0.260 |
affe | +0.260 |
ted | +0.252 |
Neg logit contributions | |
also | -0.133 |
Deal | -0.132 |
Acc | -0.128 |
narrative | -0.123 |
known | -0.121 |
Token | felt |
Token ID | 2936 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
also | +0.542 |
known | +0.399 |
Always | +0.383 |
Amen | +0.377 |
sch | +0.366 |
Neg logit contributions | |
ors | -0.750 |
ados | -0.690 |
ries | -0.684 |
cream | -0.673 |
ops | -0.672 |
Token | scared |
Token ID | 12008 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Deal | +0.379 |
narrative | +0.357 |
Acc | +0.355 |
sch | +0.347 |
Amen | +0.344 |
Neg logit contributions | |
badges | -0.579 |
ors | -0.578 |
cream | -0.559 |
affe | -0.556 |
les | -0.553 |
Token | , |
Token ID | 11 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
also | +0.554 |
Deal | +0.542 |
Acc | +0.536 |
Do | +0.522 |
sch | +0.518 |
Neg logit contributions | |
badges | -0.350 |
ors | -0.349 |
cream | -0.334 |
affe | -0.323 |
ops | -0.309 |
Token | but |
Token ID | 475 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
also | +0.251 |
Do | +0.221 |
Acc | +0.221 |
Deal | +0.218 |
sch | +0.209 |
Neg logit contributions | |
ors | -0.368 |
badges | -0.353 |
cream | -0.350 |
affe | -0.344 |
ops | -0.340 |
Token | also |
Token ID | 635 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Deal | +0.347 |
Acc | +0.334 |
also | +0.327 |
narrative | +0.324 |
sch | +0.323 |
Neg logit contributions | |
ors | -0.370 |
badges | -0.363 |
cream | -0.355 |
affe | -0.353 |
ted | -0.344 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
also | +0.446 |
Deal | +0.445 |
Acc | +0.433 |
narrative | +0.405 |
sch | +0.405 |
Neg logit contributions | |
ors | -0.771 |
badges | -0.757 |
affe | -0.735 |
cream | -0.732 |
ted | -0.706 |
Token | to |
Token ID | 284 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
also | +0.278 |
known | +0.240 |
Do | +0.221 |
first | +0.215 |
welcome | +0.209 |
Neg logit contributions | |
ors | -0.661 |
affe | -0.641 |
les | -0.623 |
ops | -0.620 |
omes | -0.601 |
Token | look |
Token ID | 804 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
also | +0.216 |
welcome | +0.186 |
known | +0.172 |
Deal | +0.164 |
Amen | +0.156 |
Neg logit contributions | |
ors | -0.474 |
badges | -0.457 |
cream | -0.452 |
ted | -0.449 |
affe | -0.443 |
Token | at |
Token ID | 379 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
also | +0.249 |
welcome | +0.229 |
Deal | +0.209 |
upon | +0.197 |
glad | +0.196 |
Neg logit contributions | |
ops | -0.515 |
affe | -0.480 |
ors | -0.476 |
badges | -0.468 |
cream | -0.464 |
Token | himself |
Token ID | 2241 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
also | +0.228 |
known | +0.174 |
welcome | +0.173 |
Do | +0.170 |
first | +0.170 |
Neg logit contributions | |
affe | -0.426 |
badges | -0.414 |
ops | -0.407 |
omes | -0.406 |
ors | -0.405 |
Token | a |
Token ID | 257 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
ors | +0.418 |
badges | +0.414 |
cream | +0.402 |
affe | +0.397 |
ted | +0.385 |
Neg logit contributions | |
also | -0.334 |
Deal | -0.334 |
Acc | -0.327 |
narrative | -0.311 |
sch | -0.310 |
Token | long |
Token ID | 890 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
also | +0.391 |
Deal | +0.369 |
Acc | +0.356 |
Amen | +0.352 |
sch | +0.350 |
Neg logit contributions | |
ors | -0.656 |
cream | -0.614 |
badges | -0.607 |
ted | -0.594 |
affe | -0.582 |
Token | cord |
Token ID | 15050 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
welcome | +0.355 |
also | +0.349 |
doing | +0.329 |
living | +0.312 |
sch | +0.307 |
Neg logit contributions | |
cream | -0.757 |
ors | -0.729 |
ted | -0.675 |
badges | -0.664 |
als | -0.657 |
Token | that |
Token ID | 326 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
also | +0.170 |
living | +0.147 |
doing | +0.143 |
going | +0.143 |
first | +0.135 |
Neg logit contributions | |
badges | -0.220 |
ors | -0.209 |
affe | -0.206 |
ishes | -0.201 |
cream | -0.201 |
Token | she |
Token ID | 673 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
also | +0.317 |
known | +0.257 |
Do | +0.253 |
welcome | +0.246 |
sch | +0.243 |
Neg logit contributions | |
ors | -0.537 |
badges | -0.518 |
affe | -0.515 |
cream | -0.496 |
omes | -0.485 |
Token | could |
Token ID | 714 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
also | +0.325 |
sch | +0.241 |
Acc | +0.229 |
known | +0.226 |
Always | +0.222 |
Neg logit contributions | |
ors | -0.584 |
ados | -0.572 |
badges | -0.570 |
cream | -0.553 |
affe | -0.553 |
Token | use |
Token ID | 779 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
also | +0.501 |
not | +0.358 |
't | +0.312 |
first | +0.303 |
Amen | +0.296 |
Neg logit contributions | |
badges | -0.890 |
cream | -0.878 |
ted | -0.861 |
ors | -0.859 |
ishes | -0.857 |
Token | to |
Token ID | 284 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
also | +0.299 |
first | +0.252 |
very | +0.247 |
Do | +0.245 |
living | +0.240 |
Neg logit contributions | |
affe | -0.589 |
cream | -0.559 |
round | -0.540 |
omes | -0.534 |
eros | -0.533 |
Token | jump |
Token ID | 4391 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
also | +0.254 |
welcome | +0.194 |
known | +0.189 |
first | +0.183 |
Deal | +0.182 |
Neg logit contributions | |
affe | -0.475 |
ors | -0.473 |
cream | -0.464 |
ted | -0.461 |
eros | -0.458 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
also | +0.200 |
first | +0.180 |
very | +0.179 |
right | +0.170 |
impossible | +0.161 |
Neg logit contributions | |
affe | -0.368 |
cream | -0.366 |
badges | -0.364 |
eros | -0.347 |
ages | -0.347 |
Token | play |
Token ID | 711 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
also | +0.173 |
Deal | +0.165 |
Acc | +0.156 |
Do | +0.153 |
sch | +0.153 |
Neg logit contributions | |
ors | -0.257 |
badges | -0.249 |
affe | -0.244 |
cream | -0.243 |
les | -0.233 |
Token | her |
Token ID | 607 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
ors | +0.137 |
badges | +0.134 |
affe | +0.131 |
cream | +0.130 |
als | +0.124 |
Neg logit contributions | |
Deal | -0.101 |
Acc | -0.097 |
sch | -0.094 |
Amen | -0.091 |
also | -0.090 |
Token | room |
Token ID | 2119 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
also | +0.446 |
Deal | +0.424 |
welcome | +0.393 |
sch | +0.389 |
Amen | +0.385 |
Neg logit contributions | |
ors | -0.545 |
cream | -0.515 |
badges | -0.509 |
affe | -0.494 |
ted | -0.489 |
Token | clean |
Token ID | 3424 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
also | +0.341 |
living | +0.312 |
first | +0.287 |
dining | +0.285 |
sch | +0.283 |
Neg logit contributions | |
affe | -0.452 |
ors | -0.438 |
badges | -0.438 |
cream | -0.410 |
eros | -0.405 |
Token | so |
Token ID | 523 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
also | +0.419 |
Acc | +0.380 |
Do | +0.370 |
sch | +0.366 |
living | +0.364 |
Neg logit contributions | |
affe | -0.521 |
badges | -0.488 |
cream | -0.456 |
ors | -0.449 |
ked | -0.443 |
Token | she |
Token ID | 673 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
also | +0.472 |
Deal | +0.469 |
Acc | +0.459 |
narrative | +0.434 |
sch | +0.432 |
Neg logit contributions | |
ors | -0.691 |
badges | -0.682 |
affe | -0.661 |
cream | -0.654 |
ted | -0.632 |
Token | could |
Token ID | 714 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
also | +0.344 |
Acc | +0.285 |
Always | +0.268 |
sch | +0.256 |
Amen | +0.254 |
Neg logit contributions | |
badges | -0.558 |
affe | -0.543 |
ors | -0.540 |
eros | -0.514 |
cream | -0.501 |
Token | find |
Token ID | 1064 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
also | +0.422 |
Deal | +0.370 |
Acc | +0.353 |
Amen | +0.338 |
sch | +0.330 |
Neg logit contributions | |
ors | -0.850 |
badges | -0.847 |
affe | -0.833 |
cream | -0.820 |
ted | -0.807 |
Token | all |
Token ID | 477 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
also | +0.208 |
welcome | +0.197 |
living | +0.177 |
known | +0.171 |
right | +0.166 |
Neg logit contributions | |
affe | -0.589 |
ops | -0.545 |
round | -0.543 |
ors | -0.540 |
eros | -0.519 |
Token | her |
Token ID | 607 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Deal | +0.264 |
Acc | +0.245 |
also | +0.240 |
Amen | +0.239 |
narrative | +0.238 |
Neg logit contributions | |
ors | -0.292 |
badges | -0.281 |
cream | -0.279 |
les | -0.273 |
ted | -0.267 |
Token | special |
Token ID | 2041 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
also | +0.225 |
living | +0.202 |
Acc | +0.201 |
sch | +0.195 |
welcome | +0.194 |
Neg logit contributions | |
affe | -0.335 |
ors | -0.331 |
round | -0.318 |
badges | -0.315 |
ked | -0.307 |
Token | toys |
Token ID | 14958 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
living | +0.338 |
welcome | +0.326 |
also | +0.306 |
sch | +0.295 |
narrative | +0.286 |
Neg logit contributions | |
affe | -0.428 |
ors | -0.407 |
ked | -0.383 |
round | -0.376 |
ops | -0.368 |
Token | fragile |
Token ID | 21049 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Deal | +0.004 |
also | +0.004 |
Acc | +0.004 |
narrative | +0.004 |
sch | +0.004 |
Neg logit contributions | |
ors | -0.013 |
badges | -0.013 |
affe | -0.012 |
cream | -0.012 |
ted | -0.012 |
Token | things |
Token ID | 1243 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
also | +0.550 |
living | +0.526 |
welcome | +0.511 |
Do | +0.511 |
narrative | +0.489 |
Neg logit contributions | |
badges | -0.561 |
cream | -0.560 |
ors | -0.548 |
ops | -0.516 |
ted | -0.510 |
Token | . |
Token ID | 13 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
also | +0.263 |
welcome | +0.217 |
doing | +0.207 |
possible | +0.205 |
Do | +0.205 |
Neg logit contributions | |
affe | -0.382 |
badges | -0.379 |
cream | -0.359 |
eros | -0.357 |
ted | -0.356 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Deal | +0.208 |
also | +0.205 |
Do | +0.200 |
Always | +0.192 |
Acc | +0.188 |
Neg logit contributions | |
ors | -0.495 |
badges | -0.494 |
cream | -0.472 |
les | -0.470 |
affe | -0.465 |
Token | Once |
Token ID | 7454 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Deal | +0.248 |
Acc | +0.241 |
also | +0.239 |
narrative | +0.224 |
sch | +0.220 |
Neg logit contributions | |
ors | -0.468 |
badges | -0.459 |
affe | -0.449 |
cream | -0.449 |
ted | -0.439 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Deal | +0.294 |
Amen | +0.270 |
Acc | +0.269 |
narrative | +0.254 |
sch | +0.251 |
Neg logit contributions | |
ors | -0.654 |
affe | -0.626 |
les | -0.621 |
ops | -0.598 |
ed | -0.587 |
Token | a |
Token ID | 257 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Deal | +0.736 |
narrative | +0.707 |
Acc | +0.677 |
Amen | +0.658 |
sch | +0.655 |
Neg logit contributions | |
badges | -0.474 |
cream | -0.472 |
affe | -0.459 |
bars | -0.435 |
ted | -0.430 |
Token | time |
Token ID | 640 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Deal | +0.206 |
Do | +0.204 |
Acc | +0.203 |
known | +0.201 |
Amen | +0.201 |
Neg logit contributions | |
affe | -0.360 |
ors | -0.354 |
badges | -0.347 |
les | -0.336 |
ops | -0.335 |
Token | there |
Token ID | 612 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Deal | +0.486 |
Acc | +0.483 |
also | +0.475 |
narrative | +0.471 |
Amen | +0.470 |
Neg logit contributions | |
ors | -0.135 |
badges | -0.115 |
affe | -0.112 |
ops | -0.103 |
cream | -0.099 |
Token | was |
Token ID | 373 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Deal | +0.326 |
Acc | +0.312 |
also | +0.301 |
narrative | +0.300 |
Amen | +0.299 |
Neg logit contributions | |
ors | -0.328 |
badges | -0.316 |
affe | -0.309 |
cream | -0.308 |
ted | -0.300 |
Token | a |
Token ID | 257 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
Deal | +0.459 |
narrative | +0.435 |
Amen | +0.421 |
Acc | +0.421 |
also | +0.418 |
Neg logit contributions | |
badges | -0.362 |
ors | -0.356 |
affe | -0.353 |
cream | -0.352 |
ted | -0.342 |
Token | was |
Token ID | 373 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
also | +0.421 |
known | +0.357 |
Always | +0.331 |
Amen | +0.319 |
Do | +0.312 |
Neg logit contributions | |
ors | -0.672 |
badges | -0.652 |
affe | -0.633 |
round | -0.617 |
ops | -0.609 |
Token | very |
Token ID | 845 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
also | +0.363 |
known | +0.313 |
Always | +0.277 |
Deal | +0.277 |
Acc | +0.276 |
Neg logit contributions | |
ors | -0.924 |
badges | -0.896 |
affe | -0.895 |
cream | -0.883 |
ops | -0.877 |
Token | smart |
Token ID | 4451 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
also | +0.391 |
Deal | +0.359 |
Acc | +0.342 |
known | +0.333 |
Amen | +0.317 |
Neg logit contributions | |
ors | -0.966 |
badges | -0.946 |
affe | -0.924 |
cream | -0.919 |
ted | -0.905 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
also | +0.415 |
living | +0.376 |
Do | +0.369 |
welcome | +0.364 |
doing | +0.361 |
Neg logit contributions | |
cream | -0.453 |
badges | -0.426 |
ors | -0.422 |
ops | -0.405 |
affe | -0.400 |
Token | but |
Token ID | 475 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
also | +0.258 |
Do | +0.226 |
Always | +0.216 |
welcome | +0.212 |
known | +0.211 |
Neg logit contributions | |
ors | -0.348 |
cream | -0.327 |
ops | -0.327 |
badges | -0.326 |
les | -0.318 |
Token | also |
Token ID | 635 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
also | +0.297 |
Deal | +0.294 |
Acc | +0.286 |
narrative | +0.272 |
known | +0.271 |
Neg logit contributions | |
ors | -0.424 |
badges | -0.416 |
affe | -0.403 |
cream | -0.401 |
ted | -0.386 |
Token | very |
Token ID | 845 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
also | +0.406 |
known | +0.353 |
Acc | +0.352 |
Deal | +0.343 |
Do | +0.323 |
Neg logit contributions | |
ors | -0.887 |
badges | -0.845 |
affe | -0.829 |
cream | -0.808 |
ops | -0.801 |
Token | poor |
Token ID | 3595 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
also | +0.334 |
Deal | +0.265 |
known | +0.261 |
Acc | +0.259 |
welcome | +0.250 |
Neg logit contributions | |
ors | -0.836 |
badges | -0.828 |
ted | -0.795 |
cream | -0.794 |
affe | -0.790 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
also | +0.259 |
living | +0.256 |
welcome | +0.216 |
Do | +0.208 |
doing | +0.208 |
Neg logit contributions | |
ors | -0.394 |
ked | -0.388 |
badges | -0.379 |
affe | -0.375 |
cream | -0.374 |
Token | She |
Token ID | 1375 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Deal | +0.161 |
also | +0.159 |
Acc | +0.153 |
narrative | +0.143 |
Amen | +0.142 |
Neg logit contributions | |
ors | -0.334 |
badges | -0.329 |
cream | -0.319 |
affe | -0.318 |
ted | -0.309 |
Token | was |
Token ID | 373 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
also | +0.288 |
known | +0.191 |
narrative | +0.185 |
Always | +0.184 |
Amen | +0.173 |
Neg logit contributions | |
ors | -0.519 |
ados | -0.488 |
badges | -0.482 |
cream | -0.482 |
ries | -0.472 |
Token | a |
Token ID | 257 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
ops | +0.021 |
badges | +0.021 |
affe | +0.020 |
omes | +0.019 |
ors | +0.019 |
Neg logit contributions | |
also | -0.012 |
Do | -0.011 |
welcome | -0.010 |
first | -0.010 |
Amen | -0.009 |
Token | big |
Token ID | 1263 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
also | +0.391 |
Deal | +0.369 |
Acc | +0.356 |
Amen | +0.352 |
sch | +0.350 |
Neg logit contributions | |
ors | -0.656 |
cream | -0.614 |
badges | -0.607 |
ted | -0.594 |
affe | -0.582 |
Token | flashlight |
Token ID | 38371 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
welcome | +0.523 |
also | +0.476 |
Amen | +0.461 |
Do | +0.450 |
doing | +0.435 |
Neg logit contributions | |
ors | -0.685 |
cream | -0.671 |
ted | -0.609 |
ops | -0.598 |
ked | -0.593 |
Token | that |
Token ID | 326 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
also | +0.200 |
living | +0.167 |
doing | +0.162 |
going | +0.159 |
first | +0.157 |
Neg logit contributions | |
badges | -0.248 |
cream | -0.229 |
ors | -0.226 |
affe | -0.225 |
wo | -0.217 |
Token | they |
Token ID | 484 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
also | +0.309 |
known | +0.256 |
sch | +0.249 |
Do | +0.248 |
welcome | +0.242 |
Neg logit contributions | |
ors | -0.533 |
affe | -0.526 |
badges | -0.519 |
cream | -0.499 |
round | -0.491 |
Token | could |
Token ID | 714 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
also | +0.254 |
known | +0.160 |
sch | +0.128 |
welcome | +0.125 |
Always | +0.123 |
Neg logit contributions | |
ados | -0.613 |
ries | -0.612 |
ors | -0.608 |
eros | -0.603 |
cream | -0.591 |
Token | turn |
Token ID | 1210 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
also | +0.496 |
Amen | +0.390 |
Deal | +0.373 |
known | +0.361 |
sch | +0.355 |
Neg logit contributions | |
cream | -0.803 |
badges | -0.802 |
ors | -0.802 |
affe | -0.790 |
ted | -0.780 |
Token | on |
Token ID | 319 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
also | +0.212 |
very | +0.198 |
right | +0.191 |
late | +0.182 |
impossible | +0.181 |
Neg logit contributions | |
affe | -0.486 |
ops | -0.464 |
uddled | -0.439 |
eros | -0.437 |
omes | -0.435 |
Token | and |
Token ID | 290 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
also | +0.240 |
very | +0.199 |
first | +0.199 |
living | +0.195 |
right | +0.193 |
Neg logit contributions | |
affe | -0.481 |
cream | -0.456 |
wo | -0.454 |
ops | -0.452 |
round | -0.448 |
Token | off |
Token ID | 572 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
also | +0.187 |
Deal | +0.176 |
sch | +0.165 |
Acc | +0.165 |
known | +0.163 |
Neg logit contributions | |
ors | -0.283 |
badges | -0.272 |
affe | -0.272 |
cream | -0.267 |
ops | -0.259 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
also | +0.160 |
first | +0.139 |
very | +0.130 |
living | +0.124 |
right | +0.117 |
Neg logit contributions | |
affe | -0.363 |
cream | -0.349 |
wo | -0.347 |
ors | -0.338 |
ops | -0.336 |
Token | nos |
Token ID | 43630 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
badges | +0.178 |
cream | +0.175 |
ors | +0.172 |
affe | +0.166 |
bars | +0.161 |
Neg logit contributions | |
Deal | -0.223 |
Acc | -0.205 |
Amen | -0.199 |
narrative | -0.198 |
also | -0.193 |
Token | y |
Token ID | 88 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
also | +0.419 |
Do | +0.403 |
Always | +0.393 |
Acc | +0.391 |
narrative | +0.388 |
Neg logit contributions | |
badges | -0.556 |
cream | -0.479 |
phones | -0.479 |
ors | -0.475 |
stret | -0.474 |
Token | . |
Token ID | 13 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
also | +0.351 |
living | +0.333 |
welcome | +0.326 |
very | +0.304 |
Always | +0.303 |
Neg logit contributions | |
badges | -0.489 |
cream | -0.460 |
ors | -0.446 |
ops | -0.421 |
ted | -0.419 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Do | +0.208 |
Deal | +0.195 |
Always | +0.193 |
also | +0.192 |
Amen | +0.178 |
Neg logit contributions | |
badges | -0.544 |
ors | -0.541 |
les | -0.529 |
cream | -0.519 |
ops | -0.512 |
Token | Once |
Token ID | 7454 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Deal | +0.292 |
Acc | +0.284 |
also | +0.279 |
narrative | +0.264 |
Amen | +0.259 |
Neg logit contributions | |
ors | -0.447 |
badges | -0.434 |
cream | -0.429 |
affe | -0.429 |
ted | -0.423 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Deal | +0.333 |
Amen | +0.314 |
Acc | +0.299 |
narrative | +0.287 |
sch | +0.286 |
Neg logit contributions | |
ors | -0.618 |
les | -0.594 |
affe | -0.591 |
ops | -0.562 |
ed | -0.554 |
Token | a |
Token ID | 257 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Deal | +0.764 |
narrative | +0.733 |
Acc | +0.694 |
Amen | +0.683 |
sch | +0.675 |
Neg logit contributions | |
cream | -0.446 |
badges | -0.441 |
affe | -0.434 |
bars | -0.412 |
aw | -0.411 |
Token | time |
Token ID | 640 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Deal | +0.198 |
Acc | +0.191 |
also | +0.190 |
known | +0.188 |
Do | +0.187 |
Neg logit contributions | |
affe | -0.373 |
ors | -0.367 |
badges | -0.362 |
les | -0.347 |
ops | -0.346 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Deal | +0.491 |
Acc | +0.489 |
also | +0.480 |
narrative | +0.475 |
Amen | +0.473 |
Neg logit contributions | |
ors | -0.132 |
badges | -0.112 |
affe | -0.109 |
ops | -0.098 |
cream | -0.095 |
Token | a |
Token ID | 257 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Deal | +0.238 |
sch | +0.224 |
narrative | +0.219 |
Amen | +0.216 |
Acc | +0.216 |
Neg logit contributions | |
ors | -0.157 |
ed | -0.148 |
affe | -0.148 |
badges | -0.142 |
cream | -0.142 |
Token | little |
Token ID | 1310 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
also | +0.218 |
Deal | +0.212 |
Acc | +0.210 |
sch | +0.196 |
narrative | +0.196 |
Neg logit contributions | |
ors | -0.306 |
badges | -0.298 |
cream | -0.289 |
affe | -0.282 |
ted | -0.278 |
Token | if |
Token ID | 611 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
badges | +0.196 |
ors | +0.192 |
cream | +0.181 |
ted | +0.178 |
affe | +0.177 |
Neg logit contributions | |
Deal | -0.281 |
Acc | -0.275 |
narrative | -0.270 |
also | -0.263 |
sch | -0.261 |
Token | they |
Token ID | 484 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
also | +0.292 |
Do | +0.238 |
known | +0.226 |
welcome | +0.219 |
first | +0.214 |
Neg logit contributions | |
ors | -0.865 |
badges | -0.840 |
affe | -0.830 |
les | -0.810 |
cream | -0.799 |
Token | allowed |
Token ID | 3142 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
also | +0.316 |
known | +0.179 |
only | +0.172 |
'd | +0.170 |
first | +0.168 |
Neg logit contributions | |
ors | -0.793 |
badges | -0.783 |
eros | -0.778 |
ados | -0.763 |
ries | -0.748 |
Token | him |
Token ID | 683 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
first | +0.284 |
also | +0.267 |
Do | +0.247 |
welcome | +0.242 |
right | +0.225 |
Neg logit contributions | |
affe | -0.618 |
ors | -0.582 |
badges | -0.577 |
les | -0.573 |
cream | -0.571 |
Token | he |
Token ID | 339 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
also | +0.237 |
first | +0.203 |
welcome | +0.201 |
not | +0.193 |
right | +0.182 |
Neg logit contributions | |
badges | -0.465 |
ors | -0.455 |
affe | -0.454 |
ries | -0.436 |
eros | -0.435 |
Token | could |
Token ID | 714 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
also | +0.304 |
known | +0.208 |
first | +0.201 |
welcome | +0.197 |
Always | +0.183 |
Neg logit contributions | |
ors | -0.635 |
ados | -0.629 |
badges | -0.606 |
ries | -0.603 |
round | -0.590 |
Token | teach |
Token ID | 4545 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
also | +0.453 |
welcome | +0.354 |
Deal | +0.349 |
Amen | +0.339 |
known | +0.333 |
Neg logit contributions | |
badges | -0.868 |
ors | -0.862 |
cream | -0.857 |
ted | -0.854 |
affe | -0.839 |
Token | them |
Token ID | 606 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
also | +0.221 |
Do | +0.210 |
welcome | +0.196 |
first | +0.192 |
Deal | +0.190 |
Neg logit contributions | |
affe | -0.358 |
cream | -0.347 |
ors | -0.344 |
badges | -0.340 |
uddled | -0.339 |
Token | a |
Token ID | 257 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
also | +0.168 |
welcome | +0.137 |
living | +0.131 |
very | +0.128 |
winning | +0.127 |
Neg logit contributions | |
affe | -0.294 |
ors | -0.293 |
eros | -0.284 |
ops | -0.283 |
ted | -0.283 |
Token | special |
Token ID | 2041 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
also | +0.172 |
Deal | +0.160 |
Acc | +0.150 |
welcome | +0.148 |
known | +0.147 |
Neg logit contributions | |
ors | -0.442 |
ted | -0.418 |
badges | -0.413 |
cream | -0.410 |
als | -0.408 |
Token | game |
Token ID | 983 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
welcome | +0.250 |
Amen | +0.237 |
also | +0.229 |
Do | +0.219 |
living | +0.207 |
Neg logit contributions | |
ors | -0.518 |
ted | -0.480 |
als | -0.472 |
cream | -0.467 |
ops | -0.466 |
Token | not |
Token ID | 407 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
ors | +0.187 |
badges | +0.182 |
cream | +0.178 |
ted | +0.174 |
affe | +0.169 |
Neg logit contributions | |
also | -0.162 |
Deal | -0.157 |
Acc | -0.155 |
narrative | -0.148 |
known | -0.147 |
Token | see |
Token ID | 766 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
also | +0.522 |
known | +0.484 |
welcome | +0.478 |
Do | +0.445 |
Deal | +0.445 |
Neg logit contributions | |
ors | -0.935 |
ops | -0.878 |
als | -0.870 |
badges | -0.868 |
ted | -0.866 |
Token | anything |
Token ID | 1997 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Do | +0.338 |
also | +0.337 |
welcome | +0.305 |
living | +0.276 |
known | +0.267 |
Neg logit contributions | |
ops | -0.730 |
ors | -0.688 |
affe | -0.681 |
uddled | -0.679 |
badges | -0.677 |
Token | else |
Token ID | 2073 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
also | +0.306 |
Do | +0.265 |
welcome | +0.261 |
narrative | +0.252 |
possible | +0.250 |
Neg logit contributions | |
badges | -0.361 |
ors | -0.354 |
cream | -0.343 |
affe | -0.341 |
ted | -0.332 |
Token | he |
Token ID | 339 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
also | +0.386 |
Do | +0.331 |
welcome | +0.330 |
known | +0.314 |
Always | +0.308 |
Neg logit contributions | |
badges | -0.551 |
ors | -0.546 |
affe | -0.530 |
cream | -0.514 |
ted | -0.509 |
Token | could |
Token ID | 714 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
also | +0.352 |
known | +0.295 |
sch | +0.272 |
Always | +0.267 |
welcome | +0.267 |
Neg logit contributions | |
ors | -0.564 |
badges | -0.531 |
cream | -0.518 |
affe | -0.517 |
ados | -0.514 |
Token | use |
Token ID | 779 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
also | +0.397 |
known | +0.309 |
Deal | +0.302 |
welcome | +0.296 |
Always | +0.282 |
Neg logit contributions | |
badges | -0.902 |
ors | -0.886 |
cream | -0.885 |
ted | -0.862 |
affe | -0.848 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
also | +0.337 |
welcome | +0.310 |
Do | +0.299 |
first | +0.295 |
living | +0.293 |
Neg logit contributions | |
affe | -0.527 |
cream | -0.486 |
ops | -0.473 |
ors | -0.472 |
badges | -0.468 |
Token | He |
Token ID | 679 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Deal | +0.167 |
also | +0.165 |
Acc | +0.156 |
Do | +0.149 |
Amen | +0.147 |
Neg logit contributions | |
ors | -0.368 |
badges | -0.364 |
cream | -0.351 |
affe | -0.350 |
les | -0.344 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
also | +0.360 |
known | +0.265 |
narrative | +0.245 |
Always | +0.240 |
sch | +0.236 |
Neg logit contributions | |
ors | -0.481 |
cream | -0.452 |
ados | -0.449 |
round | -0.444 |
affe | -0.441 |
Token | sad |
Token ID | 6507 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
also | +0.187 |
Deal | +0.172 |
Acc | +0.169 |
known | +0.163 |
Do | +0.153 |
Neg logit contributions | |
ors | -0.459 |
badges | -0.446 |
affe | -0.440 |
cream | -0.435 |
ops | -0.429 |
Token | book |
Token ID | 1492 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
badges | +0.108 |
ors | +0.108 |
affe | +0.103 |
cream | +0.100 |
als | +0.100 |
Neg logit contributions | |
Deal | -0.112 |
Acc | -0.109 |
also | -0.108 |
known | -0.104 |
Amen | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
ors | +0.275 |
badges | +0.273 |
cream | +0.259 |
affe | +0.251 |
ted | +0.238 |
Neg logit contributions | |
also | -0.333 |
narrative | -0.305 |
Deal | -0.304 |
sch | -0.304 |
Acc | -0.294 |
Token | It |
Token ID | 632 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
ors | +0.178 |
badges | +0.178 |
ops | +0.170 |
cream | +0.169 |
ats | +0.169 |
Neg logit contributions | |
Do | -0.067 |
Deal | -0.057 |
welcome | -0.057 |
sch | -0.056 |
also | -0.056 |
Token | had |
Token ID | 550 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
ors | +0.067 |
badges | +0.065 |
cream | +0.064 |
affe | +0.063 |
ados | +0.060 |
Neg logit contributions | |
also | -0.041 |
sch | -0.032 |
known | -0.032 |
Do | -0.031 |
Amen | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
also | +0.082 |
Deal | +0.078 |
Acc | +0.075 |
sch | +0.075 |
known | +0.075 |
Neg logit contributions | |
ors | -0.115 |
badges | -0.110 |
cream | -0.109 |
affe | -0.108 |
ops | -0.104 |
Token | picture |
Token ID | 4286 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
badges | +0.096 |
ors | +0.094 |
affe | +0.093 |
cream | +0.089 |
les | +0.087 |
Neg logit contributions | |
Deal | -0.084 |
Acc | -0.084 |
also | -0.080 |
narrative | -0.078 |
known | -0.077 |
Token | of |
Token ID | 286 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
badges | +0.442 |
ors | +0.436 |
cream | +0.418 |
affe | +0.402 |
vered | +0.402 |
Neg logit contributions | |
also | -0.157 |
living | -0.119 |
Do | -0.119 |
sch | -0.118 |
welcome | -0.117 |
Token | a |
Token ID | 257 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
also | +0.081 |
Deal | +0.073 |
known | +0.071 |
Do | +0.070 |
sch | +0.069 |
Neg logit contributions | |
ors | -0.148 |
affe | -0.140 |
cream | -0.139 |
badges | -0.135 |
ops | -0.132 |
Token | star |
Token ID | 3491 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ors | +0.099 |
badges | +0.096 |
cream | +0.093 |
affe | +0.091 |
ted | +0.089 |
Neg logit contributions | |
also | -0.091 |
Deal | -0.090 |
Acc | -0.088 |
sch | -0.085 |
narrative | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
badges | +0.328 |
ors | +0.318 |
cream | +0.316 |
ted | +0.289 |
affe | +0.288 |
Neg logit contributions | |
also | -0.293 |
living | -0.245 |
Do | -0.239 |
doing | -0.239 |
performing | -0.234 |
Token | a |
Token ID | 257 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
ors | +0.215 |
affe | +0.201 |
badges | +0.197 |
cream | +0.196 |
ops | +0.193 |
Neg logit contributions | |
also | -0.132 |
Do | -0.114 |
known | -0.113 |
sch | -0.111 |
Deal | -0.106 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ors | +0.173 |
badges | +0.164 |
cream | +0.160 |
affe | +0.159 |
les | +0.156 |
Neg logit contributions | |
also | -0.118 |
Deal | -0.114 |
Acc | -0.110 |
known | -0.107 |
Do | -0.106 |
Token | said |
Token ID | 531 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
ors | +0.259 |
eros | +0.232 |
ados | +0.228 |
affe | +0.223 |
cream | +0.219 |
Neg logit contributions | |
also | -0.182 |
narrative | -0.123 |
sch | -0.120 |
known | -0.118 |
Acc | -0.114 |
Token | goodbye |
Token ID | 24829 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ors | +0.004 |
badges | +0.004 |
cream | +0.004 |
affe | +0.004 |
round | +0.004 |
Neg logit contributions | |
also | -0.006 |
Deal | -0.005 |
Acc | -0.005 |
welcome | -0.005 |
Amen | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
ors | +0.179 |
badges | +0.178 |
les | +0.175 |
ries | +0.175 |
affe | +0.170 |
Neg logit contributions | |
also | -0.111 |
not | -0.095 |
first | -0.094 |
Acc | -0.093 |
right | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
ors | +0.071 |
badges | +0.069 |
affe | +0.067 |
cream | +0.067 |
les | +0.064 |
Neg logit contributions | |
also | -0.050 |
Deal | -0.048 |
Acc | -0.047 |
sch | -0.044 |
known | -0.044 |
Token | bear |
Token ID | 6842 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ors | +0.107 |
cream | +0.101 |
badges | +0.098 |
affe | +0.095 |
als | +0.092 |
Neg logit contributions | |
also | -0.131 |
Deal | -0.125 |
Amen | -0.122 |
welcome | -0.121 |
Do | -0.120 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
badges | +0.323 |
ors | +0.316 |
cream | +0.292 |
affe | +0.278 |
les | +0.275 |
Neg logit contributions | |
also | -0.394 |
living | -0.329 |
Acc | -0.322 |
first | -0.321 |
Always | -0.318 |
Token | the |
Token ID | 262 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
ors | +0.177 |
affe | +0.157 |
ops | +0.152 |
les | +0.149 |
badges | +0.145 |
Neg logit contributions | |
also | -0.165 |
known | -0.144 |
sch | -0.137 |
Acc | -0.135 |
narrative | -0.132 |
Token | zo |
Token ID | 40565 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ors | +0.123 |
cream | +0.110 |
badges | +0.103 |
affe | +0.103 |
ops | +0.101 |
Neg logit contributions | |
also | -0.131 |
Deal | -0.127 |
welcome | -0.125 |
Do | -0.121 |
Amen | -0.121 |
Token | oke |
Token ID | 2088 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
badges | +0.213 |
ors | +0.205 |
cream | +0.202 |
ted | +0.192 |
affe | +0.191 |
Neg logit contributions | |
also | -0.099 |
Deal | -0.089 |
narrative | -0.087 |
welcome | -0.084 |
Do | -0.084 |
Token | ep |
Token ID | 538 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
also | +0.087 |
known | +0.079 |
narrative | +0.075 |
Amen | +0.072 |
Acc | +0.070 |
Neg logit contributions | |
badges | -0.077 |
ors | -0.076 |
als | -0.075 |
affe | -0.075 |
cream | -0.075 |
Token | bad |
Token ID | 2089 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
ors | +0.079 |
affe | +0.077 |
badges | +0.077 |
cream | +0.075 |
ops | +0.075 |
Neg logit contributions | |
also | -0.036 |
Deal | -0.030 |
Acc | -0.029 |
known | -0.028 |
Do | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ors | +0.097 |
badges | +0.097 |
cream | +0.094 |
affe | +0.091 |
stret | +0.091 |
Neg logit contributions | |
also | -0.068 |
Do | -0.066 |
narrative | -0.063 |
right | -0.063 |
living | -0.063 |
Token | He |
Token ID | 679 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
badges | +0.166 |
ors | +0.166 |
affe | +0.160 |
cream | +0.157 |
ted | +0.154 |
Neg logit contributions | |
Acc | -0.123 |
also | -0.122 |
Deal | -0.122 |
Amen | -0.118 |
sch | -0.115 |
Token | was |
Token ID | 373 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
ors | +0.027 |
ados | +0.024 |
affe | +0.024 |
als | +0.023 |
eros | +0.023 |
Neg logit contributions | |
also | -0.019 |
known | -0.014 |
Acc | -0.014 |
narrative | -0.013 |
sch | -0.013 |
Token | using |
Token ID | 1262 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
Deal | +0.036 |
narrative | +0.035 |
Acc | +0.034 |
Amen | +0.034 |
sch | +0.032 |
Neg logit contributions | |
badges | -0.062 |
cream | -0.058 |
ors | -0.057 |
bars | -0.055 |
affe | -0.055 |
Token | blocks |
Token ID | 7021 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
affe | +0.122 |
ors | +0.121 |
cream | +0.119 |
round | +0.117 |
ops | +0.115 |
Neg logit contributions | |
also | -0.057 |
welcome | -0.046 |
known | -0.045 |
Deal | -0.044 |
winning | -0.043 |
Token | that |
Token ID | 326 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
ors | +0.440 |
badges | +0.436 |
cream | +0.430 |
affe | +0.428 |
eros | +0.413 |
Neg logit contributions | |
also | -0.369 |
welcome | -0.304 |
known | -0.301 |
first | -0.300 |
narrative | -0.295 |
Token | did |
Token ID | 750 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
ors | +0.145 |
affe | +0.138 |
badges | +0.135 |
cream | +0.133 |
eros | +0.131 |
Neg logit contributions | |
also | -0.091 |
known | -0.074 |
narrative | -0.072 |
welcome | -0.071 |
Do | -0.069 |
Token | not |
Token ID | 407 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
also | +0.023 |
known | +0.006 |
Deal | +0.004 |
not | +0.002 |
Do | +0.001 |
Neg logit contributions | |
ors | -0.202 |
affe | -0.199 |
ted | -0.197 |
als | -0.195 |
cream | -0.195 |
Token | match |
Token ID | 2872 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
also | +0.067 |
known | +0.058 |
welcome | +0.058 |
Deal | +0.051 |
Do | +0.050 |
Neg logit contributions | |
ors | -0.137 |
ted | -0.135 |
eros | -0.131 |
affe | -0.130 |
als | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
affe | +0.294 |
cream | +0.287 |
badges | +0.280 |
stret | +0.277 |
wo | +0.275 |
Neg logit contributions | |
also | -0.231 |
welcome | -0.205 |
winning | -0.203 |
first | -0.200 |
Do | -0.200 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ors | +0.048 |
badges | +0.043 |
affe | +0.041 |
cream | +0.038 |
ops | +0.036 |
Neg logit contributions | |
Deal | -0.155 |
Acc | -0.153 |
also | -0.152 |
narrative | -0.149 |
sch | -0.148 |
Token | there |
Token ID | 612 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
ors | +0.159 |
ed | +0.154 |
affe | +0.153 |
cream | +0.152 |
ted | +0.150 |
Neg logit contributions | |
Deal | -0.252 |
sch | -0.240 |
Acc | -0.236 |
narrative | -0.233 |
known | -0.227 |
Token | was |
Token ID | 373 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ors | +0.095 |
badges | +0.093 |
affe | +0.090 |
cream | +0.090 |
ted | +0.087 |
Neg logit contributions | |
Deal | -0.087 |
Acc | -0.084 |
also | -0.083 |
narrative | -0.080 |
Amen | -0.079 |
Token | a |
Token ID | 257 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Deal | +0.023 |
narrative | +0.022 |
Acc | +0.022 |
Amen | +0.021 |
also | +0.021 |
Neg logit contributions | |
badges | -0.016 |
cream | -0.016 |
affe | -0.015 |
ors | -0.015 |
ted | -0.015 |
Token | little |
Token ID | 1310 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
ors | +0.157 |
badges | +0.155 |
affe | +0.151 |
cream | +0.149 |
les | +0.142 |
Neg logit contributions | |
Deal | -0.134 |
also | -0.130 |
Acc | -0.129 |
narrative | -0.124 |
sch | -0.123 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ors | +0.114 |
badges | +0.107 |
cream | +0.106 |
ops | +0.104 |
ted | +0.101 |
Neg logit contributions | |
also | -0.056 |
welcome | -0.053 |
Amen | -0.050 |
Do | -0.047 |
Acc | -0.045 |
Token | named |
Token ID | 3706 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ors | +0.165 |
badges | +0.149 |
affe | +0.148 |
cream | +0.145 |
ted | +0.140 |
Neg logit contributions | |
Deal | -0.318 |
narrative | -0.290 |
Acc | -0.288 |
known | -0.284 |
sch | -0.284 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ors | +0.148 |
als | +0.142 |
bars | +0.133 |
ted | +0.132 |
affe | +0.130 |
Neg logit contributions | |
narrative | -0.203 |
Deal | -0.196 |
Amen | -0.193 |
known | -0.191 |
Acc | -0.190 |
Token | who |
Token ID | 508 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ors | +0.122 |
cream | +0.105 |
affe | +0.099 |
badges | +0.096 |
les | +0.091 |
Neg logit contributions | |
Deal | -0.408 |
narrative | -0.372 |
known | -0.359 |
sch | -0.358 |
Acc | -0.352 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
cream | +0.118 |
badges | +0.114 |
ors | +0.113 |
affe | +0.111 |
ted | +0.106 |
Neg logit contributions | |
Deal | -0.170 |
narrative | -0.150 |
sch | -0.147 |
Acc | -0.146 |
also | -0.142 |
Token | to |
Token ID | 284 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
ors | +0.050 |
affe | +0.049 |
badges | +0.048 |
ops | +0.046 |
les | +0.046 |
Neg logit contributions | |
also | -0.036 |
Acc | -0.035 |
sch | -0.034 |
Deal | -0.033 |
Do | -0.033 |
Token | One |
Token ID | 1881 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
ors | +0.202 |
badges | +0.197 |
affe | +0.197 |
cream | +0.193 |
round | +0.181 |
Neg logit contributions | |
Acc | -0.164 |
Deal | -0.162 |
narrative | -0.159 |
Amen | -0.157 |
also | -0.155 |
Token | day |
Token ID | 1110 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ors | +0.163 |
badges | +0.161 |
affe | +0.155 |
cream | +0.154 |
ted | +0.151 |
Neg logit contributions | |
also | -0.040 |
Deal | -0.035 |
Acc | -0.035 |
sch | -0.033 |
known | -0.031 |
Token | he |
Token ID | 339 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
ors | +0.216 |
affe | +0.204 |
cream | +0.199 |
co | +0.198 |
badges | +0.197 |
Neg logit contributions | |
also | -0.203 |
Do | -0.203 |
known | -0.188 |
welcome | -0.188 |
upon | -0.182 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
ors | +0.094 |
affe | +0.090 |
badges | +0.089 |
cream | +0.087 |
ados | +0.086 |
Neg logit contributions | |
also | -0.071 |
known | -0.060 |
sch | -0.058 |
Always | -0.052 |
Acc | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ors | +0.131 |
ops | +0.124 |
affe | +0.123 |
badges | +0.117 |
lets | +0.117 |
Neg logit contributions | |
also | -0.056 |
known | -0.047 |
sch | -0.042 |
Acc | -0.041 |
living | -0.040 |
Token | boat |
Token ID | 8848 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
ors | +0.212 |
badges | +0.202 |
cream | +0.198 |
affe | +0.195 |
ted | +0.195 |
Neg logit contributions | |
also | -0.115 |
Deal | -0.103 |
Acc | -0.102 |
sch | -0.101 |
narrative | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ors | +0.396 |
badges | +0.394 |
affe | +0.382 |
cream | +0.375 |
ops | +0.360 |
Neg logit contributions | |
also | -0.318 |
sch | -0.280 |
Acc | -0.277 |
known | -0.276 |
Do | -0.271 |
Token | asked |
Token ID | 1965 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
ors | +0.348 |
ops | +0.341 |
affe | +0.325 |
co | +0.314 |
eros | +0.314 |
Neg logit contributions | |
also | -0.185 |
known | -0.133 |
Do | -0.130 |
sch | -0.118 |
Always | -0.117 |
Token | his |
Token ID | 465 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ops | +0.182 |
ors | +0.175 |
omes | +0.168 |
als | +0.168 |
badges | +0.166 |
Neg logit contributions | |
welcome | -0.044 |
also | -0.043 |
Do | -0.039 |
known | -0.038 |
very | -0.030 |
Token | dad |
Token ID | 9955 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ors | +0.192 |
les | +0.174 |
ops | +0.174 |
ted | +0.172 |
affe | +0.170 |
Neg logit contributions | |
also | -0.134 |
welcome | -0.120 |
Deal | -0.120 |
known | -0.116 |
Amen | -0.115 |
Token | if |
Token ID | 611 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ors | +0.396 |
badges | +0.390 |
affe | +0.377 |
cream | +0.375 |
ted | +0.361 |
Neg logit contributions | |
also | -0.316 |
Deal | -0.310 |
Acc | -0.302 |
known | -0.289 |
Do | -0.287 |
Token | their |
Token ID | 511 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
affe | +0.074 |
ors | +0.072 |
ops | +0.071 |
ages | +0.069 |
ache | +0.068 |
Neg logit contributions | |
also | -0.019 |
first | -0.016 |
right | -0.014 |
very | -0.014 |
Do | -0.013 |
Token | door |
Token ID | 3420 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ors | +0.032 |
affe | +0.031 |
ops | +0.029 |
cream | +0.029 |
badges | +0.029 |
Neg logit contributions | |
also | -0.021 |
Deal | -0.020 |
welcome | -0.020 |
sch | -0.020 |
living | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
affe | +0.145 |
badges | +0.143 |
ors | +0.142 |
cream | +0.137 |
wo | +0.132 |
Neg logit contributions | |
also | -0.150 |
first | -0.130 |
welcome | -0.128 |
sill | -0.125 |
upon | -0.125 |
Token | It |
Token ID | 632 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
ors | +0.132 |
badges | +0.128 |
affe | +0.125 |
les | +0.124 |
ops | +0.122 |
Neg logit contributions | |
Deal | -0.076 |
also | -0.073 |
Do | -0.072 |
Always | -0.070 |
sch | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
ors | +0.055 |
ados | +0.052 |
affe | +0.052 |
badges | +0.050 |
round | +0.050 |
Neg logit contributions | |
also | -0.023 |
known | -0.014 |
sch | -0.012 |
first | -0.012 |
very | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
also | +0.071 |
Deal | +0.061 |
known | +0.061 |
sch | +0.058 |
welcome | +0.058 |
Neg logit contributions | |
ors | -0.134 |
affe | -0.129 |
cream | -0.125 |
ops | -0.124 |
badges | -0.124 |
Token | wealthy |
Token ID | 11574 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
ors | +0.107 |
cream | +0.097 |
ted | +0.096 |
badges | +0.096 |
les | +0.095 |
Neg logit contributions | |
also | -0.051 |
Deal | -0.046 |
welcome | -0.045 |
Amen | -0.044 |
sch | -0.044 |
Token | businessman |
Token ID | 19834 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ors | +0.169 |
cream | +0.165 |
ted | +0.160 |
ked | +0.157 |
oos | +0.155 |
Neg logit contributions | |
welcome | -0.104 |
also | -0.099 |
living | -0.084 |
full | -0.082 |
glad | -0.081 |
Token | ! |
Token ID | 0 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
badges | +0.332 |
ors | +0.326 |
cream | +0.322 |
ted | +0.316 |
affe | +0.307 |
Neg logit contributions | |
also | -0.364 |
Amen | -0.329 |
welcome | -0.317 |
known | -0.316 |
Do | -0.312 |
Token | He |
Token ID | 679 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
ors | +0.137 |
badges | +0.135 |
affe | +0.128 |
cream | +0.128 |
les | +0.127 |
Neg logit contributions | |
Deal | -0.086 |
also | -0.084 |
Do | -0.080 |
Always | -0.079 |
Amen | -0.077 |
Token | said |
Token ID | 531 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
also | +0.015 |
known | +0.010 |
Always | +0.009 |
sch | +0.008 |
Amen | +0.008 |
Neg logit contributions | |
ors | -0.029 |
ados | -0.027 |
oos | -0.026 |
ops | -0.026 |
ales | -0.026 |
Token | little |
Token ID | 1310 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
ors | +0.181 |
round | +0.168 |
cream | +0.166 |
badges | +0.166 |
affe | +0.160 |
Neg logit contributions | |
also | -0.128 |
known | -0.116 |
narrative | -0.110 |
welcome | -0.106 |
Acc | -0.104 |
Token | green |
Token ID | 4077 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
ors | +0.031 |
round | +0.030 |
cream | +0.029 |
ops | +0.029 |
affe | +0.028 |
Neg logit contributions | |
also | -0.030 |
welcome | -0.028 |
known | -0.028 |
Do | -0.028 |
younger | -0.027 |
Token | spr |
Token ID | 7500 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
round | +0.092 |
ors | +0.089 |
stret | +0.087 |
cream | +0.084 |
badges | +0.084 |
Neg logit contributions | |
also | -0.074 |
upon | -0.065 |
living | -0.062 |
first | -0.061 |
known | -0.060 |
Token | outs |
Token ID | 5269 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Deal | +0.043 |
Amen | +0.042 |
sch | +0.042 |
also | +0.041 |
Do | +0.041 |
Neg logit contributions | |
ors | -0.018 |
les | -0.017 |
ted | -0.016 |
als | -0.016 |
cream | -0.016 |
Token | started |
Token ID | 2067 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
ors | +0.212 |
cream | +0.202 |
badges | +0.202 |
affe | +0.195 |
round | +0.191 |
Neg logit contributions | |
also | -0.158 |
impossible | -0.134 |
known | -0.130 |
living | -0.127 |
sill | -0.127 |
Token | appearing |
Token ID | 12655 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
affe | +0.004 |
cream | +0.004 |
round | +0.004 |
ors | +0.004 |
badges | +0.004 |
Neg logit contributions | |
also | -0.002 |
known | -0.002 |
impossible | -0.001 |
doing | -0.001 |
winning | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
badges | +0.216 |
affe | +0.213 |
ors | +0.211 |
ops | +0.200 |
wo | +0.198 |
Neg logit contributions | |
also | -0.145 |
impossible | -0.125 |
right | -0.125 |
very | -0.120 |
first | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
ors | +0.032 |
badges | +0.031 |
affe | +0.030 |
cream | +0.030 |
ted | +0.029 |
Neg logit contributions | |
also | -0.024 |
Deal | -0.024 |
Acc | -0.023 |
narrative | -0.022 |
known | -0.022 |
Token | garden |
Token ID | 11376 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ors | +0.140 |
badges | +0.137 |
cream | +0.132 |
affe | +0.132 |
ted | +0.125 |
Neg logit contributions | |
also | -0.122 |
Deal | -0.119 |
Acc | -0.118 |
narrative | -0.114 |
sch | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
badges | +0.225 |
ors | +0.222 |
cream | +0.214 |
affe | +0.212 |
ted | +0.196 |
Neg logit contributions | |
also | -0.220 |
sch | -0.191 |
living | -0.190 |
known | -0.190 |
sill | -0.189 |
Token | Sammy |
Token ID | 44067 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ors | +0.193 |
badges | +0.192 |
affe | +0.184 |
les | +0.182 |
cream | +0.182 |
Neg logit contributions | |
Deal | -0.097 |
also | -0.094 |
Acc | -0.090 |
Do | -0.089 |
sch | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ors | +0.260 |
ados | +0.240 |
badges | +0.237 |
ries | +0.236 |
phones | +0.231 |
Neg logit contributions | |
also | -0.206 |
first | -0.125 |
only | -0.124 |
still | -0.121 |
not | -0.121 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ors | +0.256 |
les | +0.245 |
affe | +0.243 |
cream | +0.236 |
badges | +0.235 |
Neg logit contributions | |
also | -0.127 |
first | -0.109 |
Deal | -0.107 |
sch | -0.104 |
welcome | -0.101 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ors | +0.409 |
ados | +0.373 |
eros | +0.362 |
ller | +0.356 |
ittens | +0.353 |
Neg logit contributions | |
also | -0.252 |
known | -0.152 |
only | -0.147 |
very | -0.140 |
right | -0.136 |
Token | to |
Token ID | 284 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
ors | +0.167 |
badges | +0.162 |
affe | +0.161 |
cream | +0.158 |
ops | +0.155 |
Neg logit contributions | |
also | -0.118 |
Deal | -0.105 |
welcome | -0.103 |
sch | -0.103 |
Acc | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
badges | +0.087 |
ors | +0.085 |
cream | +0.082 |
affe | +0.080 |
ted | +0.080 |
Neg logit contributions | |
Acc | -0.088 |
Deal | -0.087 |
narrative | -0.086 |
also | -0.083 |
sch | -0.082 |
Token | edge |
Token ID | 5743 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
badges | +0.104 |
cream | +0.093 |
affe | +0.092 |
ors | +0.091 |
les | +0.091 |
Neg logit contributions | |
Acc | -0.182 |
Deal | -0.182 |
Amen | -0.169 |
Always | -0.168 |
known | -0.168 |
Token | of |
Token ID | 286 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
ors | +0.170 |
badges | +0.167 |
affe | +0.162 |
cream | +0.161 |
ted | +0.156 |
Neg logit contributions | |
Deal | -0.129 |
also | -0.126 |
Acc | -0.125 |
narrative | -0.118 |
Amen | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Acc | +0.112 |
Deal | +0.110 |
narrative | +0.105 |
Always | +0.103 |
Amen | +0.102 |
Neg logit contributions | |
badges | -0.063 |
ted | -0.059 |
ries | -0.056 |
apples | -0.055 |
ors | -0.053 |
Token | water |
Token ID | 1660 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
badges | +0.114 |
les | +0.111 |
ors | +0.110 |
als | +0.103 |
cream | +0.103 |
Neg logit contributions | |
Deal | -0.184 |
Acc | -0.183 |
known | -0.166 |
Amen | -0.166 |
Always | -0.161 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ors | +0.204 |
badges | +0.203 |
affe | +0.194 |
cream | +0.191 |
ted | +0.176 |
Neg logit contributions | |
also | -0.289 |
Acc | -0.269 |
Deal | -0.268 |
sch | -0.266 |
narrative | -0.261 |
Token | They |
Token ID | 1119 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
ors | +0.215 |
badges | +0.211 |
affe | +0.207 |
cream | +0.203 |
les | +0.200 |
Neg logit contributions | |
also | -0.098 |
Deal | -0.095 |
Do | -0.090 |
Acc | -0.089 |
sch | -0.089 |
Token | bug |
Token ID | 5434 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
badges | +0.110 |
ors | +0.109 |
affe | +0.108 |
als | +0.106 |
cream | +0.103 |
Neg logit contributions | |
Deal | -0.182 |
Acc | -0.171 |
Amen | -0.170 |
known | -0.166 |
narrative | -0.164 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
badges | +0.356 |
cream | +0.323 |
ors | +0.314 |
affe | +0.305 |
ted | +0.296 |
Neg logit contributions | |
also | -0.385 |
living | -0.342 |
Acc | -0.317 |
Always | -0.312 |
sch | -0.310 |
Token | and |
Token ID | 290 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ors | +0.203 |
badges | +0.198 |
affe | +0.192 |
cream | +0.191 |
ted | +0.182 |
Neg logit contributions | |
also | -0.188 |
Deal | -0.185 |
Acc | -0.182 |
sch | -0.174 |
known | -0.173 |
Token | with |
Token ID | 351 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
ors | +0.249 |
affe | +0.244 |
badges | +0.235 |
ops | +0.228 |
les | +0.219 |
Neg logit contributions | |
also | -0.197 |
known | -0.162 |
Acc | -0.150 |
Always | -0.148 |
sch | -0.145 |
Token | one |
Token ID | 530 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
badges | +0.053 |
ors | +0.053 |
cream | +0.051 |
affe | +0.051 |
ted | +0.049 |
Neg logit contributions | |
Deal | -0.047 |
Acc | -0.046 |
also | -0.045 |
narrative | -0.044 |
sch | -0.043 |
Token | quick |
Token ID | 2068 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
affe | +0.239 |
badges | +0.237 |
ors | +0.233 |
les | +0.224 |
cream | +0.223 |
Neg logit contributions | |
Acc | -0.264 |
Deal | -0.260 |
Amen | -0.250 |
narrative | -0.249 |
also | -0.248 |
Token | slap |
Token ID | 23905 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
cream | +0.208 |
ors | +0.206 |
co | +0.191 |
round | +0.187 |
ries | +0.183 |
Neg logit contributions | |
welcome | -0.164 |
Deal | -0.145 |
Do | -0.142 |
also | -0.142 |
sch | -0.137 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ors | +0.393 |
badges | +0.391 |
omes | +0.390 |
affe | +0.384 |
round | +0.383 |
Neg logit contributions | |
Do | -0.163 |
right | -0.162 |
also | -0.161 |
welcome | -0.154 |
very | -0.145 |
Token | he |
Token ID | 339 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
ors | +0.276 |
affe | +0.259 |
badges | +0.258 |
cream | +0.251 |
ops | +0.249 |
Neg logit contributions | |
also | -0.164 |
Acc | -0.137 |
known | -0.136 |
Do | -0.135 |
Deal | -0.131 |
Token | caught |
Token ID | 4978 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ors | +0.070 |
ados | +0.069 |
round | +0.066 |
affe | +0.066 |
ries | +0.065 |
Neg logit contributions | |
also | -0.054 |
known | -0.040 |
not | -0.038 |
still | -0.036 |
only | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
badges | +0.225 |
ors | +0.225 |
affe | +0.224 |
ops | +0.212 |
round | +0.210 |
Neg logit contributions | |
also | -0.137 |
Do | -0.113 |
Acc | -0.113 |
known | -0.112 |
welcome | -0.112 |
Token | skull |
Token ID | 14511 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ors | +0.087 |
badges | +0.081 |
cream | +0.081 |
ted | +0.079 |
affe | +0.079 |
Neg logit contributions | |
also | -0.049 |
Deal | -0.044 |
Acc | -0.043 |
sch | -0.043 |
Do | -0.041 |
Token | lying |
Token ID | 9105 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
badges | +0.237 |
ors | +0.236 |
cream | +0.223 |
affe | +0.214 |
ted | +0.207 |
Neg logit contributions | |
also | -0.236 |
narrative | -0.197 |
Do | -0.196 |
sch | -0.195 |
Acc | -0.191 |
Token | on |
Token ID | 319 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ors | +0.061 |
badges | +0.061 |
affe | +0.058 |
cream | +0.058 |
ops | +0.055 |
Neg logit contributions | |
also | -0.052 |
Acc | -0.049 |
Deal | -0.049 |
narrative | -0.048 |
sch | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
ors | +0.059 |
badges | +0.056 |
affe | +0.056 |
cream | +0.056 |
ops | +0.055 |
Neg logit contributions | |
also | -0.034 |
Deal | -0.030 |
sch | -0.029 |
Acc | -0.029 |
Do | -0.029 |
Token | ground |
Token ID | 2323 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ors | +0.111 |
badges | +0.108 |
cream | +0.103 |
affe | +0.101 |
ted | +0.101 |
Neg logit contributions | |
also | -0.087 |
sch | -0.079 |
Deal | -0.079 |
Acc | -0.076 |
narrative | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
badges | +0.170 |
ors | +0.167 |
affe | +0.163 |
cream | +0.159 |
ted | +0.149 |
Neg logit contributions | |
also | -0.182 |
sch | -0.155 |
known | -0.151 |
Acc | -0.150 |
Do | -0.148 |
Token |
|
Token ID | 198 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
ors | +0.121 |
badges | +0.117 |
affe | +0.114 |
cream | +0.113 |
ted | +0.112 |
Neg logit contributions | |
Deal | -0.096 |
narrative | -0.095 |
Acc | -0.095 |
also | -0.092 |
known | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
narrative | +0.111 |
Deal | +0.106 |
Acc | +0.104 |
known | +0.102 |
rightful | +0.099 |
Neg logit contributions | |
ors | -0.097 |
affe | -0.092 |
les | -0.090 |
ted | -0.087 |
badges | -0.086 |
Token | " |
Token ID | 1 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
Deal | +0.112 |
narrative | +0.108 |
Acc | +0.107 |
known | +0.106 |
sch | +0.104 |
Neg logit contributions | |
ors | -0.095 |
badges | -0.091 |
affe | -0.089 |
cream | -0.086 |
ted | -0.084 |
Token | What |
Token ID | 2061 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
ors | +0.123 |
badges | +0.121 |
affe | +0.118 |
cream | +0.118 |
ted | +0.114 |
Neg logit contributions | |
Deal | -0.052 |
also | -0.052 |
Acc | -0.050 |
narrative | -0.046 |
sch | -0.046 |
Token | 's |
Token ID | 338 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
ors | +0.023 |
badges | +0.022 |
affe | +0.022 |
cream | +0.022 |
ted | +0.021 |
Neg logit contributions | |
Deal | -0.017 |
also | -0.017 |
Acc | -0.016 |
narrative | -0.015 |
sch | -0.015 |
Token | go |
Token ID | 467 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
also | +0.025 |
Deal | +0.022 |
welcome | +0.022 |
Amen | +0.022 |
known | +0.022 |
Neg logit contributions | |
ors | -0.046 |
badges | -0.044 |
cream | -0.044 |
affe | -0.044 |
ted | -0.043 |
Token | outside |
Token ID | 2354 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
Deal | +0.099 |
Acc | +0.096 |
also | +0.096 |
narrative | +0.093 |
sch | +0.091 |
Neg logit contributions | |
ors | -0.098 |
badges | -0.097 |
cream | -0.093 |
affe | -0.091 |
ted | -0.089 |
Token | and |
Token ID | 290 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
ors | +0.072 |
badges | +0.069 |
cream | +0.066 |
affe | +0.066 |
ted | +0.063 |
Neg logit contributions | |
Deal | -0.092 |
Acc | -0.089 |
also | -0.089 |
narrative | -0.087 |
known | -0.085 |
Token | play |
Token ID | 711 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
cream | +0.052 |
badges | +0.051 |
ors | +0.048 |
ted | +0.047 |
als | +0.047 |
Neg logit contributions | |
Deal | -0.085 |
narrative | -0.083 |
Acc | -0.078 |
acy | -0.075 |
known | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
affe | +0.066 |
ors | +0.066 |
cream | +0.064 |
badges | +0.064 |
ache | +0.060 |
Neg logit contributions | |
also | -0.044 |
Acc | -0.040 |
sch | -0.038 |
welcome | -0.038 |
narrative | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ors | +0.050 |
badges | +0.049 |
affe | +0.047 |
cream | +0.047 |
ted | +0.046 |
Neg logit contributions | |
Deal | -0.029 |
also | -0.028 |
Acc | -0.028 |
narrative | -0.027 |
sch | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Deal | +0.184 |
narrative | +0.182 |
Acc | +0.179 |
impossible | +0.163 |
sch | +0.158 |
Neg logit contributions | |
ors | -0.168 |
affe | -0.157 |
ops | -0.153 |
badges | -0.151 |
cream | -0.149 |
Token | The |
Token ID | 464 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
Deal | +0.129 |
also | +0.125 |
Acc | +0.124 |
narrative | +0.117 |
sch | +0.117 |
Neg logit contributions | |
ors | -0.216 |
badges | -0.214 |
affe | -0.208 |
cream | -0.206 |
ted | -0.199 |
Token | first |
Token ID | 717 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
Deal | +0.017 |
also | +0.017 |
Acc | +0.016 |
narrative | +0.016 |
sch | +0.016 |
Neg logit contributions | |
ors | -0.022 |
badges | -0.021 |
affe | -0.020 |
cream | -0.020 |
ted | -0.020 |
Token | friend |
Token ID | 1545 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
also | +0.081 |
welcome | +0.076 |
known | +0.072 |
Do | +0.067 |
weekend | +0.065 |
Neg logit contributions | |
ors | -0.134 |
cream | -0.123 |
badges | -0.121 |
ries | -0.116 |
ted | -0.113 |
Token | said |
Token ID | 531 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
badges | +0.373 |
ors | +0.370 |
ados | +0.368 |
phones | +0.364 |
stret | +0.362 |
Neg logit contributions | |
also | -0.160 |
always | -0.100 |
only | -0.088 |
� | -0.083 |
Always | -0.080 |
Token | hope |
Token ID | 2911 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
also | +0.168 |
known | +0.130 |
narrative | +0.128 |
Deal | +0.127 |
welcome | +0.121 |
Neg logit contributions | |
ors | -0.337 |
cream | -0.324 |
badges | -0.308 |
affe | -0.304 |
ted | -0.301 |
Token | the |
Token ID | 262 |
Feature activation | -8.52e-02 |
Pos logit contributions | |
also | +0.131 |
Do | +0.111 |
known | +0.111 |
sch | +0.105 |
Acc | +0.102 |
Neg logit contributions | |
ors | -0.217 |
affe | -0.214 |
cream | -0.209 |
badges | -0.209 |
ops | -0.204 |
Token | par |
Token ID | 1582 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
also | +0.121 |
narrative | +0.114 |
Acc | +0.109 |
Deal | +0.107 |
known | +0.106 |
Neg logit contributions | |
ors | -0.121 |
cream | -0.110 |
badges | -0.107 |
ted | -0.105 |
ops | -0.104 |
Token | rot |
Token ID | 10599 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
also | +0.083 |
Deal | +0.079 |
known | +0.079 |
Amen | +0.079 |
narrative | +0.079 |
Neg logit contributions | |
badges | -0.042 |
ors | -0.042 |
cream | -0.042 |
ted | -0.039 |
als | -0.035 |
Token | will |
Token ID | 481 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
ors | +0.132 |
badges | +0.130 |
cream | +0.126 |
ados | +0.120 |
affe | +0.119 |
Neg logit contributions | |
also | -0.049 |
known | -0.030 |
Always | -0.029 |
welcome | -0.028 |
Acc | -0.027 |
Token | not |
Token ID | 407 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
also | +0.263 |
Deal | +0.251 |
Acc | +0.240 |
known | +0.236 |
Amen | +0.230 |
Neg logit contributions | |
ors | -0.450 |
badges | -0.438 |
cream | -0.432 |
affe | -0.425 |
ted | -0.414 |
Token | come |
Token ID | 1282 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
also | +0.269 |
known | +0.226 |
Deal | +0.219 |
welcome | +0.213 |
Do | +0.212 |
Neg logit contributions | |
ors | -0.460 |
badges | -0.460 |
cream | -0.458 |
ted | -0.438 |
affe | -0.427 |
Token | back |
Token ID | 736 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
also | +0.264 |
Deal | +0.251 |
Do | +0.241 |
Acc | +0.240 |
Amen | +0.237 |
Neg logit contributions | |
ors | -0.309 |
badges | -0.306 |
cream | -0.302 |
affe | -0.297 |
ops | -0.292 |
Token | . |
Token ID | 13 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
also | +0.091 |
Do | +0.082 |
known | +0.082 |
Acc | +0.080 |
Deal | +0.079 |
Neg logit contributions | |
ors | -0.103 |
badges | -0.102 |
affe | -0.100 |
cream | -0.099 |
ops | -0.096 |
Token | They |
Token ID | 1119 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Acc | +0.096 |
narrative | +0.091 |
sch | +0.088 |
also | +0.088 |
known | +0.088 |
Neg logit contributions | |
badges | -0.090 |
ors | -0.083 |
affe | -0.082 |
cream | -0.082 |
ted | -0.080 |
Token | like |
Token ID | 588 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
also | +0.141 |
Deal | +0.117 |
narrative | +0.112 |
known | +0.111 |
welcome | +0.106 |
Neg logit contributions | |
ors | -0.266 |
cream | -0.249 |
badges | -0.246 |
affe | -0.238 |
ted | -0.236 |
Token | ap |
Token ID | 499 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
also | +0.202 |
Deal | +0.202 |
Acc | +0.200 |
narrative | +0.189 |
known | +0.188 |
Neg logit contributions | |
ors | -0.278 |
badges | -0.271 |
affe | -0.262 |
cream | -0.260 |
als | -0.252 |
Token | their |
Token ID | 511 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
also | +0.117 |
welcome | +0.108 |
Deal | +0.105 |
Do | +0.104 |
upon | +0.097 |
Neg logit contributions | |
cream | -0.183 |
ors | -0.174 |
affe | -0.165 |
ops | -0.161 |
badges | -0.160 |
Token | hands |
Token ID | 2832 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
Deal | +0.242 |
welcome | +0.225 |
also | +0.223 |
sch | +0.211 |
narrative | +0.211 |
Neg logit contributions | |
cream | -0.248 |
ors | -0.247 |
ted | -0.214 |
affe | -0.209 |
round | -0.208 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
also | +0.074 |
Deal | +0.062 |
first | +0.060 |
right | +0.060 |
welcome | +0.060 |
Neg logit contributions | |
ors | -0.086 |
badges | -0.086 |
cream | -0.084 |
affe | -0.082 |
eros | -0.079 |
Token | They |
Token ID | 1119 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Deal | +0.110 |
also | +0.109 |
Acc | +0.109 |
narrative | +0.103 |
sch | +0.101 |
Neg logit contributions | |
ors | -0.206 |
badges | -0.204 |
affe | -0.197 |
cream | -0.196 |
ted | -0.192 |
Token | pick |
Token ID | 2298 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
also | +0.180 |
welcome | +0.123 |
Deal | +0.120 |
known | +0.113 |
narrative | +0.110 |
Neg logit contributions | |
ors | -0.396 |
cream | -0.377 |
eros | -0.360 |
ados | -0.359 |
ries | -0.353 |
Token | up |
Token ID | 510 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
also | +0.108 |
welcome | +0.090 |
Do | +0.090 |
Deal | +0.086 |
sch | +0.084 |
Neg logit contributions | |
ors | -0.256 |
affe | -0.253 |
badges | -0.247 |
cream | -0.237 |
ops | -0.234 |
Token | the |
Token ID | 262 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
also | +0.115 |
first | +0.089 |
right | +0.083 |
very | +0.078 |
living | +0.069 |
Neg logit contributions | |
affe | -0.401 |
ors | -0.398 |
round | -0.369 |
opter | -0.364 |
int | -0.362 |
Token | ball |
Token ID | 2613 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
also | +0.125 |
living | +0.123 |
narrative | +0.122 |
Deal | +0.120 |
welcome | +0.119 |
Neg logit contributions | |
ors | -0.137 |
cream | -0.124 |
ops | -0.112 |
affe | -0.112 |
badges | -0.112 |
Token | and |
Token ID | 290 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
badges | +0.051 |
cream | +0.048 |
ors | +0.047 |
affe | +0.044 |
ted | +0.041 |
Neg logit contributions | |
also | -0.064 |
first | -0.054 |
living | -0.052 |
Do | -0.051 |
sch | -0.051 |
Token | throw |
Token ID | 3714 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
also | +0.077 |
Deal | +0.065 |
welcome | +0.060 |
sch | +0.059 |
Do | +0.058 |
Neg logit contributions | |
ors | -0.128 |
affe | -0.121 |
cream | -0.116 |
ops | -0.112 |
badges | -0.111 |
Token | them |
Token ID | 606 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
also | +0.139 |
Do | +0.128 |
welcome | +0.125 |
known | +0.121 |
Deal | +0.121 |
Neg logit contributions | |
ops | -0.222 |
ors | -0.221 |
affe | -0.220 |
cream | -0.215 |
ages | -0.210 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
also | +0.042 |
living | +0.031 |
not | +0.028 |
first | +0.024 |
very | +0.024 |
Neg logit contributions | |
affe | -0.112 |
ors | -0.107 |
ops | -0.107 |
plets | -0.104 |
omes | -0.103 |
Token | big |
Token ID | 1263 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
also | +0.122 |
welcome | +0.117 |
Deal | +0.114 |
Do | +0.113 |
sch | +0.109 |
Neg logit contributions | |
ors | -0.175 |
ted | -0.155 |
cream | -0.154 |
ops | -0.150 |
les | -0.148 |
Token | basket |
Token ID | 7988 |
Feature activation | +4.36e-03 |
Pos logit contributions | |
welcome | +0.199 |
Do | +0.175 |
Amen | +0.169 |
also | +0.167 |
sch | +0.159 |
Neg logit contributions | |
ors | -0.309 |
cream | -0.292 |
ted | -0.269 |
ops | -0.265 |
uddled | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
ors | +0.004 |
badges | +0.004 |
affe | +0.004 |
cream | +0.004 |
als | +0.004 |
Neg logit contributions | |
Deal | -0.008 |
Acc | -0.007 |
known | -0.007 |
narrative | -0.007 |
Amen | -0.007 |
Token | It |
Token ID | 632 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Acc | +0.086 |
Deal | +0.084 |
also | +0.082 |
narrative | +0.081 |
known | +0.079 |
Neg logit contributions | |
badges | -0.124 |
ors | -0.120 |
affe | -0.118 |
cream | -0.118 |
ted | -0.113 |
Token | is |
Token ID | 318 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Deal | +0.110 |
also | +0.107 |
Acc | +0.107 |
narrative | +0.100 |
sch | +0.099 |
Neg logit contributions | |
ors | -0.196 |
badges | -0.193 |
affe | -0.187 |
cream | -0.187 |
ted | -0.181 |
Token | full |
Token ID | 1336 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
also | +0.236 |
Deal | +0.236 |
Acc | +0.227 |
narrative | +0.215 |
sch | +0.214 |
Neg logit contributions | |
ors | -0.423 |
badges | -0.413 |
affe | -0.403 |
cream | -0.402 |
ted | -0.388 |
Token | of |
Token ID | 286 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
also | +0.158 |
welcome | +0.153 |
living | +0.149 |
Do | +0.140 |
sill | +0.127 |
Neg logit contributions | |
ors | -0.445 |
badges | -0.414 |
cream | -0.402 |
ops | -0.402 |
vered | -0.396 |
Token | cookies |
Token ID | 14746 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
also | +0.329 |
welcome | +0.319 |
living | +0.300 |
Do | +0.287 |
inviting | +0.278 |
Neg logit contributions | |
ors | -0.368 |
ops | -0.331 |
affe | -0.321 |
ar | -0.311 |
cream | -0.310 |
Token | , |
Token ID | 11 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
ors | +0.166 |
badges | +0.163 |
affe | +0.162 |
cream | +0.157 |
ted | +0.153 |
Neg logit contributions | |
also | -0.157 |
doing | -0.131 |
welcome | -0.130 |
living | -0.129 |
Do | -0.126 |
Token | funny |
Token ID | 8258 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
also | +0.024 |
Deal | +0.021 |
welcome | +0.020 |
Amen | +0.020 |
known | +0.020 |
Neg logit contributions | |
ors | -0.050 |
badges | -0.048 |
ted | -0.047 |
cream | -0.046 |
les | -0.045 |
Token | looking |
Token ID | 2045 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
welcome | +0.080 |
also | +0.074 |
doing | +0.069 |
Do | +0.067 |
winning | +0.065 |
Neg logit contributions | |
ors | -0.151 |
ted | -0.147 |
badges | -0.145 |
cream | -0.143 |
ishes | -0.136 |
Token | point |
Token ID | 966 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
welcome | +0.109 |
right | +0.087 |
also | +0.086 |
impossible | +0.084 |
Do | +0.084 |
Neg logit contributions | |
badges | -0.137 |
ors | -0.133 |
ted | -0.128 |
cream | -0.126 |
ops | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
also | +0.042 |
Do | +0.036 |
welcome | +0.035 |
first | +0.035 |
upon | +0.034 |
Neg logit contributions | |
badges | -0.051 |
stret | -0.045 |
cream | -0.044 |
ors | -0.042 |
ted | -0.042 |
Token | but |
Token ID | 475 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
ors | +0.059 |
badges | +0.056 |
cream | +0.055 |
ops | +0.055 |
ted | +0.054 |
Neg logit contributions | |
also | -0.042 |
Do | -0.038 |
Deal | -0.037 |
welcome | -0.036 |
Always | -0.034 |
Token | I |
Token ID | 314 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Deal | +0.047 |
Acc | +0.046 |
sch | +0.043 |
Amen | +0.043 |
narrative | +0.043 |
Neg logit contributions | |
ors | -0.054 |
badges | -0.052 |
cream | -0.051 |
affe | -0.050 |
als | -0.049 |
Token | don |
Token ID | 836 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
also | +0.122 |
Deal | +0.103 |
known | +0.103 |
Acc | +0.099 |
Always | +0.092 |
Neg logit contributions | |
ors | -0.246 |
badges | -0.240 |
cream | -0.233 |
affe | -0.231 |
ted | -0.227 |
Token | 't |
Token ID | 470 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Deal | +0.102 |
Acc | +0.099 |
also | +0.098 |
narrative | +0.087 |
sch | +0.087 |
Neg logit contributions | |
ors | -0.397 |
badges | -0.388 |
affe | -0.381 |
cream | -0.380 |
ted | -0.369 |
Token | know |
Token ID | 760 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
also | +0.178 |
known | +0.154 |
welcome | +0.151 |
Deal | +0.145 |
Do | +0.141 |
Neg logit contributions | |
badges | -0.345 |
ors | -0.344 |
cream | -0.332 |
ted | -0.329 |
uddled | -0.321 |
Token | what |
Token ID | 644 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
also | +0.041 |
Do | +0.037 |
winning | +0.033 |
possible | +0.032 |
living | +0.032 |
Neg logit contributions | |
badges | -0.059 |
ops | -0.055 |
stret | -0.054 |
affe | -0.054 |
ages | -0.054 |
Token | it |
Token ID | 340 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
also | +0.039 |
Do | +0.037 |
welcome | +0.031 |
living | +0.030 |
Always | +0.029 |
Neg logit contributions | |
badges | -0.076 |
ors | -0.076 |
ked | -0.073 |
ted | -0.073 |
cream | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
also | +0.356 |
Do | +0.331 |
doing | +0.318 |
Deal | +0.317 |
Acc | +0.313 |
Neg logit contributions | |
badges | -0.409 |
affe | -0.406 |
ors | -0.392 |
cream | -0.390 |
wo | -0.370 |
Token | Tim |
Token ID | 5045 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
Deal | +0.180 |
Do | +0.173 |
also | +0.169 |
Always | +0.168 |
Amen | +0.159 |
Neg logit contributions | |
badges | -0.356 |
ors | -0.356 |
les | -0.347 |
ops | -0.332 |
affe | -0.331 |
Token | was |
Token ID | 373 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
also | +0.069 |
Always | +0.043 |
Acc | +0.042 |
known | +0.040 |
sch | +0.040 |
Neg logit contributions | |
badges | -0.191 |
ors | -0.185 |
cream | -0.179 |
aro | -0.177 |
ados | -0.176 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
also | +0.228 |
Acc | +0.186 |
Deal | +0.186 |
known | +0.181 |
sch | +0.176 |
Neg logit contributions | |
ors | -0.652 |
badges | -0.639 |
affe | -0.629 |
cream | -0.618 |
ops | -0.616 |
Token | and |
Token ID | 290 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
also | +0.253 |
Acc | +0.226 |
Deal | +0.222 |
Always | +0.220 |
welcome | +0.218 |
Neg logit contributions | |
badges | -0.177 |
cream | -0.163 |
ors | -0.162 |
affe | -0.161 |
als | -0.157 |
Token | could |
Token ID | 714 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
Deal | +0.159 |
also | +0.153 |
Acc | +0.153 |
narrative | +0.147 |
sch | +0.145 |
Neg logit contributions | |
ors | -0.190 |
badges | -0.186 |
cream | -0.181 |
affe | -0.179 |
ted | -0.173 |
Token | not |
Token ID | 407 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Acc | +0.293 |
Deal | +0.292 |
narrative | +0.285 |
sch | +0.273 |
Do | +0.257 |
Neg logit contributions | |
ors | -0.677 |
badges | -0.672 |
cream | -0.656 |
affe | -0.653 |
ops | -0.634 |
Token | play |
Token ID | 711 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
also | +0.303 |
welcome | +0.224 |
Amen | +0.224 |
not | +0.199 |
first | +0.183 |
Neg logit contributions | |
badges | -0.709 |
ted | -0.702 |
ors | -0.697 |
ries | -0.683 |
uddled | -0.664 |
Token | with |
Token ID | 351 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
also | +0.147 |
Do | +0.140 |
welcome | +0.134 |
Acc | +0.133 |
winning | +0.133 |
Neg logit contributions | |
badges | -0.206 |
affe | -0.198 |
cream | -0.193 |
als | -0.193 |
ors | -0.192 |
Token | his |
Token ID | 465 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
also | +0.182 |
welcome | +0.156 |
not | +0.153 |
first | +0.147 |
wrong | +0.141 |
Neg logit contributions | |
affe | -0.425 |
omes | -0.419 |
round | -0.416 |
ops | -0.411 |
badges | -0.402 |
Token | friends |
Token ID | 2460 |
Feature activation | -5.15e-03 |
Pos logit contributions | |
also | +0.172 |
first | +0.166 |
living | +0.159 |
winning | +0.157 |
best | +0.151 |
Neg logit contributions | |
ors | -0.253 |
round | -0.248 |
ted | -0.248 |
cream | -0.247 |
les | -0.246 |
Token | the |
Token ID | 262 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
also | +0.328 |
Deal | +0.301 |
Acc | +0.295 |
known | +0.290 |
Do | +0.286 |
Neg logit contributions | |
ors | -0.460 |
badges | -0.455 |
affe | -0.438 |
cream | -0.431 |
les | -0.420 |
Token | family |
Token ID | 1641 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
also | +0.278 |
Deal | +0.249 |
welcome | +0.248 |
sch | +0.244 |
Amen | +0.244 |
Neg logit contributions | |
ors | -0.352 |
cream | -0.305 |
badges | -0.303 |
ops | -0.299 |
affe | -0.294 |
Token | was |
Token ID | 373 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
also | +0.067 |
always | +0.039 |
only | +0.036 |
known | +0.036 |
often | +0.035 |
Neg logit contributions | |
badges | -0.112 |
ors | -0.110 |
ados | -0.107 |
affe | -0.106 |
cream | -0.105 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
also | +0.247 |
Deal | +0.216 |
Acc | +0.210 |
known | +0.205 |
sch | +0.194 |
Neg logit contributions | |
ors | -0.717 |
badges | -0.701 |
affe | -0.693 |
cream | -0.687 |
als | -0.672 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
also | +0.294 |
living | +0.268 |
doing | +0.253 |
Do | +0.242 |
Always | +0.241 |
Neg logit contributions | |
badges | -0.553 |
affe | -0.544 |
ors | -0.528 |
cream | -0.511 |
ops | -0.498 |
Token | |
Token ID | 220 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Deal | +0.161 |
also | +0.160 |
Acc | +0.150 |
Do | +0.148 |
Always | +0.145 |
Neg logit contributions | |
ors | -0.326 |
badges | -0.323 |
cream | -0.311 |
affe | -0.311 |
les | -0.305 |
Token |
|
Token ID | 198 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Deal | +0.249 |
also | +0.249 |
Acc | +0.231 |
sch | +0.211 |
Do | +0.209 |
Neg logit contributions | |
ors | -0.747 |
badges | -0.743 |
affe | -0.722 |
cream | -0.719 |
ted | -0.701 |
Token |
|
Token ID | 198 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Deal | +0.269 |
Acc | +0.256 |
also | +0.252 |
narrative | +0.247 |
sch | +0.238 |
Neg logit contributions | |
ors | -0.577 |
badges | -0.566 |
affe | -0.556 |
cream | -0.551 |
les | -0.532 |
Token | Now |
Token ID | 3844 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
also | +0.269 |
Deal | +0.257 |
Acc | +0.253 |
known | +0.233 |
sch | +0.230 |
Neg logit contributions | |
ors | -0.583 |
badges | -0.571 |
cream | -0.555 |
affe | -0.550 |
ted | -0.540 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
also | +0.128 |
welcome | +0.109 |
Do | +0.108 |
doing | +0.102 |
going | +0.101 |
Neg logit contributions | |
affe | -0.217 |
cream | -0.217 |
badges | -0.215 |
wo | -0.213 |
co | -0.206 |
Token | family |
Token ID | 1641 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
also | +0.154 |
narrative | +0.141 |
Deal | +0.141 |
Amen | +0.140 |
welcome | +0.138 |
Neg logit contributions | |
ors | -0.242 |
badges | -0.218 |
cream | -0.217 |
affe | -0.217 |
ops | -0.212 |
Token | it |
Token ID | 340 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
also | +0.216 |
not | +0.196 |
Do | +0.193 |
living | +0.187 |
very | +0.183 |
Neg logit contributions | |
int | -0.574 |
badges | -0.568 |
ors | -0.553 |
affe | -0.549 |
cream | -0.548 |
Token | was |
Token ID | 373 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
also | +0.192 |
very | +0.125 |
known | +0.112 |
Do | +0.112 |
first | +0.112 |
Neg logit contributions | |
badges | -0.514 |
stret | -0.495 |
ors | -0.484 |
affe | -0.481 |
eros | -0.478 |
Token | a |
Token ID | 257 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
also | +0.339 |
known | +0.305 |
welcome | +0.293 |
Do | +0.280 |
winning | +0.274 |
Neg logit contributions | |
ors | -0.784 |
affe | -0.753 |
cream | -0.750 |
round | -0.734 |
badges | -0.729 |
Token | sword |
Token ID | 8429 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
also | +0.254 |
Deal | +0.234 |
Acc | +0.231 |
known | +0.225 |
Do | +0.222 |
Neg logit contributions | |
ors | -0.454 |
badges | -0.433 |
cream | -0.429 |
ted | -0.416 |
affe | -0.414 |
Token | he |
Token ID | 339 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
also | +0.075 |
doing | +0.063 |
first | +0.062 |
not | +0.060 |
known | +0.060 |
Neg logit contributions | |
cream | -0.089 |
badges | -0.089 |
ors | -0.088 |
oos | -0.085 |
ries | -0.085 |
Token | could |
Token ID | 714 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
also | +0.260 |
known | +0.216 |
sch | +0.171 |
Always | +0.170 |
Do | +0.169 |
Neg logit contributions | |
ors | -0.558 |
badges | -0.543 |
ados | -0.541 |
ries | -0.538 |
stret | -0.521 |
Token | use |
Token ID | 779 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
also | +0.439 |
known | +0.343 |
Amen | +0.328 |
welcome | +0.324 |
Deal | +0.324 |
Neg logit contributions | |
badges | -0.775 |
ors | -0.764 |
cream | -0.762 |
ted | -0.742 |
ries | -0.717 |
Token | to |
Token ID | 284 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
also | +0.302 |
Do | +0.290 |
doing | +0.274 |
living | +0.272 |
winning | +0.272 |
Neg logit contributions | |
affe | -0.447 |
cream | -0.443 |
uddled | -0.435 |
badges | -0.430 |
round | -0.429 |
Token | fight |
Token ID | 1907 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
also | +0.223 |
known | +0.192 |
welcome | +0.187 |
Do | +0.176 |
Deal | +0.176 |
Neg logit contributions | |
ors | -0.434 |
cream | -0.418 |
ted | -0.415 |
affe | -0.405 |
als | -0.401 |
Token | bad |
Token ID | 2089 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
also | +0.113 |
winning | +0.104 |
Do | +0.102 |
very | +0.101 |
right | +0.096 |
Neg logit contributions | |
cream | -0.191 |
uddled | -0.189 |
badges | -0.186 |
ted | -0.186 |
eros | -0.184 |
Token | guys |
Token ID | 3730 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
welcome | +0.270 |
Do | +0.261 |
narrative | +0.246 |
same | +0.237 |
doing | +0.235 |
Neg logit contributions | |
cream | -0.301 |
uddled | -0.292 |
round | -0.286 |
ors | -0.274 |
ted | -0.260 |
Token | so |
Token ID | 523 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
also | +0.464 |
Deal | +0.447 |
Acc | +0.435 |
known | +0.413 |
sch | +0.412 |
Neg logit contributions | |
ors | -0.943 |
badges | -0.920 |
affe | -0.903 |
cream | -0.897 |
ted | -0.866 |
Token | y |
Token ID | 331 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
Deal | +0.410 |
Acc | +0.394 |
also | +0.376 |
narrative | +0.370 |
Amen | +0.362 |
Neg logit contributions | |
ors | -0.854 |
badges | -0.851 |
cream | -0.832 |
affe | -0.822 |
les | -0.795 |
Token | ummy |
Token ID | 13513 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
Deal | +0.449 |
also | +0.445 |
Acc | +0.437 |
narrative | +0.415 |
sch | +0.414 |
Neg logit contributions | |
ors | -0.618 |
badges | -0.603 |
cream | -0.585 |
affe | -0.585 |
ted | -0.562 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
also | +0.314 |
welcome | +0.288 |
doing | +0.288 |
living | +0.285 |
going | +0.275 |
Neg logit contributions | |
badges | -0.377 |
ked | -0.372 |
ors | -0.363 |
vered | -0.347 |
anged | -0.338 |
Token |
|
Token ID | 198 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Deal | +0.186 |
also | +0.184 |
Do | +0.182 |
Always | +0.177 |
Acc | +0.165 |
Neg logit contributions | |
badges | -0.459 |
ors | -0.456 |
les | -0.437 |
cream | -0.434 |
affe | -0.431 |
Token |
|
Token ID | 198 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Deal | +0.290 |
also | +0.286 |
Acc | +0.278 |
narrative | +0.259 |
sch | +0.257 |
Neg logit contributions | |
ors | -0.705 |
badges | -0.694 |
affe | -0.677 |
cream | -0.675 |
ted | -0.654 |
Token | One |
Token ID | 3198 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
also | +0.349 |
Deal | +0.344 |
Acc | +0.333 |
known | +0.309 |
Amen | +0.307 |
Neg logit contributions | |
ors | -0.640 |
badges | -0.627 |
cream | -0.608 |
affe | -0.598 |
ted | -0.591 |
Token | day |
Token ID | 1110 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
also | +0.118 |
welcome | +0.067 |
Amen | +0.043 |
narrative | +0.040 |
known | +0.039 |
Neg logit contributions | |
ors | -0.714 |
badges | -0.703 |
ked | -0.649 |
cream | -0.647 |
ted | -0.645 |
Token | a |
Token ID | 257 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
welcome | +0.157 |
Do | +0.147 |
also | +0.145 |
upon | +0.137 |
known | +0.133 |
Neg logit contributions | |
ors | -0.322 |
cream | -0.300 |
affe | -0.295 |
ales | -0.290 |
ans | -0.282 |
Token | boss |
Token ID | 6478 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
also | +0.189 |
welcome | +0.170 |
Deal | +0.168 |
Amen | +0.163 |
known | +0.163 |
Neg logit contributions | |
ors | -0.382 |
cream | -0.340 |
badges | -0.337 |
ops | -0.333 |
ted | -0.331 |
Token | y |
Token ID | 88 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
also | +0.117 |
acy | +0.082 |
known | +0.082 |
narrative | +0.081 |
year | +0.079 |
Neg logit contributions | |
badges | -0.226 |
stret | -0.218 |
ors | -0.211 |
phones | -0.211 |
ados | -0.207 |
Token | part |
Token ID | 636 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
badges | +0.065 |
ors | +0.064 |
affe | +0.063 |
cream | +0.063 |
ops | +0.057 |
Neg logit contributions | |
also | -0.080 |
Deal | -0.079 |
Acc | -0.079 |
Do | -0.075 |
sch | -0.073 |
Token | of |
Token ID | 286 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
also | +0.261 |
welcome | +0.229 |
Always | +0.217 |
living | +0.216 |
first | +0.209 |
Neg logit contributions | |
badges | -0.425 |
ors | -0.395 |
affe | -0.389 |
ked | -0.381 |
cream | -0.374 |
Token | the |
Token ID | 262 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
also | +0.473 |
welcome | +0.424 |
known | +0.395 |
Always | +0.383 |
Deal | +0.381 |
Neg logit contributions | |
affe | -0.889 |
ors | -0.888 |
cream | -0.854 |
badges | -0.852 |
ops | -0.830 |
Token | stick |
Token ID | 4859 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
also | +0.315 |
narrative | +0.297 |
welcome | +0.291 |
living | +0.286 |
Deal | +0.273 |
Neg logit contributions | |
ors | -0.484 |
cream | -0.446 |
badges | -0.442 |
ted | -0.436 |
ked | -0.429 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
also | +0.210 |
first | +0.178 |
living | +0.177 |
right | +0.166 |
doing | +0.163 |
Neg logit contributions | |
badges | -0.270 |
wo | -0.240 |
affe | -0.239 |
cream | -0.239 |
ors | -0.238 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Do | +0.190 |
Deal | +0.189 |
also | +0.186 |
Always | +0.182 |
Amen | +0.168 |
Neg logit contributions | |
badges | -0.458 |
ors | -0.456 |
les | -0.437 |
cream | -0.431 |
affe | -0.426 |
Token |
|
Token ID | 198 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
Deal | +0.346 |
Acc | +0.335 |
also | +0.334 |
narrative | +0.320 |
sch | +0.313 |
Neg logit contributions | |
ors | -0.650 |
badges | -0.640 |
affe | -0.631 |
cream | -0.621 |
ted | -0.599 |
Token | " |
Token ID | 1 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Deal | +0.382 |
also | +0.381 |
Acc | +0.370 |
narrative | +0.349 |
sch | +0.346 |
Neg logit contributions | |
ors | -0.604 |
badges | -0.592 |
cream | -0.573 |
affe | -0.570 |
ted | -0.553 |
Token | It |
Token ID | 1026 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
also | +0.155 |
Deal | +0.151 |
Acc | +0.143 |
narrative | +0.138 |
known | +0.136 |
Neg logit contributions | |
ors | -0.437 |
badges | -0.403 |
affe | -0.393 |
cream | -0.391 |
les | -0.389 |
Token | is |
Token ID | 318 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
also | +0.243 |
welcome | +0.153 |
right | +0.150 |
� | +0.149 |
first | +0.147 |
Neg logit contributions | |
badges | -0.635 |
ors | -0.601 |
ted | -0.594 |
round | -0.594 |
ged | -0.573 |
Token | this |
Token ID | 428 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
also | +0.293 |
welcome | +0.241 |
impossible | +0.228 |
Deal | +0.223 |
known | +0.219 |
Neg logit contributions | |
ors | -0.775 |
ted | -0.759 |
ops | -0.750 |
als | -0.747 |
les | -0.747 |