Token | After |
Token ID | 3260 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
joke | +0.013 |
play | +0.012 |
chat | +0.012 |
eat | +0.012 |
sip | +0.011 |
Neg logit contributions | |
uster | -0.015 |
bars | -0.014 |
hole | -0.013 |
rier | -0.013 |
dollars | -0.013 |
Token | she |
Token ID | 673 |
Feature activation | -6.61e-03 |
Pos logit contributions | |
joke | +0.122 |
play | +0.109 |
sip | +0.104 |
laugh | +0.104 |
chat | +0.103 |
Neg logit contributions | |
uster | -0.127 |
dollars | -0.126 |
bars | -0.119 |
mith | -0.119 |
rier | -0.116 |
Token | prayed |
Token ID | 32168 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
joke | +0.010 |
play | +0.009 |
chat | +0.008 |
swamp | +0.008 |
eat | +0.008 |
Neg logit contributions | |
uster | -0.014 |
bars | -0.013 |
hole | -0.013 |
dollars | -0.013 |
isher | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +3.56e-03 |
Pos logit contributions | |
uster | +0.065 |
isher | +0.062 |
bars | +0.061 |
dollars | +0.060 |
hole | +0.060 |
Neg logit contributions | |
play | -0.031 |
chat | -0.028 |
joke | -0.026 |
eat | -0.025 |
dance | -0.024 |
Token | K |
Token ID | 509 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
uster | +0.008 |
rier | +0.008 |
isher | +0.007 |
bars | +0.007 |
dollars | +0.007 |
Neg logit contributions | |
play | -0.005 |
joke | -0.005 |
chat | -0.005 |
eat | -0.005 |
walk | -0.004 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
rier | +0.054 |
uster | +0.043 |
bars | +0.042 |
isher | +0.041 |
hole | +0.041 |
Neg logit contributions | |
walk | -0.101 |
play | -0.100 |
walks | -0.098 |
chat | -0.096 |
jog | -0.094 |
Token | lyn |
Token ID | 6213 |
Feature activation | -7.73e-03 |
Pos logit contributions | |
uster | +0.517 |
bars | +0.480 |
rier | +0.470 |
dollars | +0.462 |
hole | +0.455 |
Neg logit contributions | |
joke | -0.600 |
play | -0.594 |
chat | -0.564 |
eat | -0.553 |
sip | -0.533 |
Token | felt |
Token ID | 2936 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
joke | +0.011 |
play | +0.011 |
chat | +0.010 |
eat | +0.010 |
sip | +0.009 |
Neg logit contributions | |
uster | -0.017 |
bars | -0.016 |
rier | -0.016 |
dollars | -0.016 |
hole | -0.016 |
Token | much |
Token ID | 881 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
joke | +0.051 |
play | +0.051 |
chat | +0.047 |
eat | +0.045 |
sip | +0.043 |
Neg logit contributions | |
uster | -0.091 |
bars | -0.087 |
rier | -0.085 |
dollars | -0.084 |
hole | -0.084 |
Token | better |
Token ID | 1365 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
uster | +0.098 |
bars | +0.093 |
rier | +0.092 |
dollars | +0.091 |
hole | +0.090 |
Neg logit contributions | |
joke | -0.059 |
play | -0.057 |
chat | -0.054 |
eat | -0.051 |
sip | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +4.17e-03 |
Pos logit contributions | |
play | +0.040 |
joke | +0.039 |
chat | +0.036 |
eat | +0.035 |
laugh | +0.033 |
Neg logit contributions | |
uster | -0.068 |
bars | -0.064 |
rier | -0.062 |
isher | -0.061 |
dollars | -0.061 |
Token | so |
Token ID | 523 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
uster | +0.079 |
bars | +0.075 |
rier | +0.074 |
hole | +0.072 |
dollars | +0.072 |
Neg logit contributions | |
joke | -0.040 |
play | -0.040 |
chat | -0.037 |
eat | -0.036 |
laugh | -0.033 |
Token | much |
Token ID | 881 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
dollars | +0.040 |
bars | +0.037 |
uster | +0.035 |
rier | +0.032 |
ier | +0.032 |
Neg logit contributions | |
joke | -0.057 |
play | -0.054 |
swamp | -0.053 |
creek | -0.052 |
chase | -0.052 |
Token | fun |
Token ID | 1257 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
dollars | +0.072 |
uster | +0.065 |
ier | +0.065 |
bars | +0.064 |
iest | +0.062 |
Neg logit contributions | |
swamp | -0.065 |
joke | -0.063 |
chase | -0.061 |
crawl | -0.060 |
| | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
joke | +0.103 |
sip | +0.100 |
chat | +0.096 |
eat | +0.096 |
play | +0.096 |
Neg logit contributions | |
dollars | -0.105 |
hole | -0.103 |
uster | -0.102 |
bars | -0.101 |
rier | -0.100 |
Token | K |
Token ID | 509 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
uster | +0.004 |
rier | +0.004 |
bars | +0.004 |
dollars | +0.004 |
isher | +0.004 |
Neg logit contributions | |
play | -0.003 |
joke | -0.003 |
chat | -0.003 |
eat | -0.003 |
laugh | -0.003 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
rier | +0.053 |
uster | +0.045 |
bars | +0.044 |
hole | +0.043 |
isher | +0.043 |
Neg logit contributions | |
play | -0.101 |
walk | -0.099 |
chat | -0.097 |
walks | -0.096 |
eat | -0.096 |
Token | lyn |
Token ID | 6213 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
uster | +0.580 |
bars | +0.539 |
rier | +0.537 |
dollars | +0.529 |
hole | +0.513 |
Neg logit contributions | |
play | -0.524 |
joke | -0.520 |
chat | -0.493 |
eat | -0.479 |
laugh | -0.465 |
Token | was |
Token ID | 373 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
joke | +0.012 |
play | +0.011 |
chat | +0.011 |
eat | +0.010 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.022 |
bars | -0.021 |
rier | -0.021 |
dollars | -0.021 |
hole | -0.021 |
Token | so |
Token ID | 523 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
joke | +0.026 |
play | +0.026 |
chat | +0.024 |
eat | +0.024 |
sip | +0.023 |
Neg logit contributions | |
uster | -0.036 |
bars | -0.034 |
rier | -0.033 |
dollars | -0.033 |
hole | -0.032 |
Token | happy |
Token ID | 3772 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
uster | +0.064 |
bars | +0.061 |
rier | +0.060 |
dollars | +0.059 |
hole | +0.058 |
Neg logit contributions | |
joke | -0.039 |
play | -0.037 |
chat | -0.035 |
eat | -0.034 |
sip | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
joke | +0.085 |
play | +0.081 |
chat | +0.078 |
sip | +0.077 |
eat | +0.076 |
Neg logit contributions | |
uster | -0.083 |
bars | -0.079 |
rier | -0.079 |
hole | -0.077 |
dollars | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | +3.00e-04 |
Pos logit contributions | |
joke | +0.078 |
play | +0.073 |
chat | +0.071 |
eat | +0.069 |
sip | +0.069 |
Neg logit contributions | |
uster | -0.093 |
bars | -0.091 |
rier | -0.088 |
dollars | -0.088 |
hole | -0.088 |
Token | |
Token ID | 220 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
uster | +0.001 |
rier | +0.001 |
dollars | +0.001 |
isher | +0.001 |
bars | +0.001 |
Neg logit contributions | |
play | -0.000 |
joke | -0.000 |
chat | -0.000 |
eat | -0.000 |
laugh | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
uster | +0.162 |
bars | +0.154 |
rier | +0.152 |
dollars | +0.151 |
hole | +0.149 |
Neg logit contributions | |
joke | -0.072 |
play | -0.072 |
chat | -0.065 |
eat | -0.063 |
sip | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | -6.04e-03 |
Pos logit contributions | |
joke | +0.009 |
play | +0.008 |
chat | +0.008 |
sip | +0.008 |
eat | +0.008 |
Neg logit contributions | |
uster | -0.013 |
bars | -0.012 |
hole | -0.012 |
dollars | -0.011 |
rier | -0.011 |
Token | K |
Token ID | 42 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
joke | +0.010 |
play | +0.010 |
chat | +0.009 |
eat | +0.009 |
sip | +0.009 |
Neg logit contributions | |
uster | -0.012 |
bars | -0.011 |
hole | -0.011 |
dollars | -0.011 |
rier | -0.011 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
rier | +0.063 |
uster | +0.053 |
bars | +0.052 |
isher | +0.047 |
hole | +0.044 |
Neg logit contributions | |
play | -0.125 |
chat | -0.123 |
walk | -0.121 |
sip | -0.121 |
| | -0.119 |
Token | lyn |
Token ID | 6213 |
Feature activation | -8.72e-03 |
Pos logit contributions | |
uster | +0.557 |
bars | +0.516 |
rier | +0.512 |
dollars | +0.504 |
hole | +0.488 |
Neg logit contributions | |
play | -0.553 |
joke | -0.552 |
chat | -0.521 |
eat | -0.509 |
laugh | -0.492 |
Token | had |
Token ID | 550 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
joke | +0.011 |
play | +0.011 |
chat | +0.010 |
eat | +0.010 |
sip | +0.009 |
Neg logit contributions | |
uster | -0.021 |
bars | -0.020 |
rier | -0.020 |
dollars | -0.019 |
hole | -0.019 |
Token | so |
Token ID | 523 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
uster | +0.068 |
bars | +0.064 |
rier | +0.063 |
dollars | +0.062 |
hole | +0.062 |
Neg logit contributions | |
joke | -0.057 |
play | -0.056 |
chat | -0.052 |
eat | -0.051 |
sip | -0.049 |
Token | much |
Token ID | 881 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
dollars | +0.037 |
uster | +0.035 |
bars | +0.035 |
one | +0.032 |
hole | +0.031 |
Neg logit contributions | |
joke | -0.059 |
play | -0.056 |
chat | -0.054 |
swim | -0.053 |
sip | -0.053 |
Token | fun |
Token ID | 1257 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
dollars | +0.066 |
bars | +0.065 |
iest | +0.063 |
uster | +0.063 |
ier | +0.061 |
Neg logit contributions | |
joke | -0.063 |
sip | -0.061 |
| | -0.060 |
chat | -0.059 |
play | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
uster | +0.038 |
bars | +0.036 |
rier | +0.035 |
hole | +0.035 |
dollars | +0.035 |
Neg logit contributions | |
joke | -0.018 |
play | -0.018 |
chat | -0.017 |
eat | -0.016 |
sip | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
joke | +0.040 |
chat | +0.035 |
play | +0.035 |
sip | +0.034 |
laugh | +0.034 |
Neg logit contributions | |
uster | -0.040 |
ubby | -0.035 |
hole | -0.034 |
dollars | -0.034 |
bars | -0.033 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
joke | +0.024 |
play | +0.023 |
chat | +0.023 |
eat | +0.022 |
sip | +0.022 |
Neg logit contributions | |
uster | -0.015 |
rier | -0.014 |
dollars | -0.014 |
bars | -0.013 |
ubby | -0.013 |
Token | named |
Token ID | 3706 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
joke | +0.042 |
play | +0.040 |
chat | +0.038 |
eat | +0.037 |
sip | +0.035 |
Neg logit contributions | |
uster | -0.063 |
bars | -0.060 |
hole | -0.058 |
dollars | -0.058 |
rier | -0.058 |
Token | K |
Token ID | 509 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
uster | +0.140 |
bars | +0.130 |
hole | +0.127 |
rier | +0.126 |
dollars | +0.124 |
Neg logit contributions | |
joke | -0.112 |
play | -0.103 |
chat | -0.102 |
eat | -0.095 |
swim | -0.094 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
rier | +0.071 |
uster | +0.067 |
bars | +0.065 |
dollars | +0.064 |
isher | +0.060 |
Neg logit contributions | |
play | -0.070 |
joke | -0.065 |
chat | -0.065 |
walk | -0.064 |
eat | -0.063 |
Token | lyn |
Token ID | 6213 |
Feature activation | -9.13e-03 |
Pos logit contributions | |
uster | +0.498 |
bars | +0.463 |
rier | +0.453 |
hole | +0.446 |
dollars | +0.441 |
Neg logit contributions | |
joke | -0.610 |
play | -0.597 |
chat | -0.573 |
eat | -0.559 |
sip | -0.545 |
Token | . |
Token ID | 13 |
Feature activation | -9.67e-03 |
Pos logit contributions | |
joke | +0.014 |
play | +0.014 |
chat | +0.013 |
eat | +0.013 |
sip | +0.012 |
Neg logit contributions | |
uster | -0.019 |
bars | -0.018 |
hole | -0.018 |
dollars | -0.017 |
rier | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
play | +0.013 |
joke | +0.013 |
chat | +0.012 |
eat | +0.012 |
laugh | +0.011 |
Neg logit contributions | |
uster | -0.023 |
rier | -0.022 |
dollars | -0.021 |
bars | -0.021 |
isher | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
sip | +0.042 |
joke | +0.042 |
chat | +0.039 |
jokes | +0.038 |
eat | +0.038 |
Neg logit contributions | |
uster | -0.040 |
bars | -0.039 |
ubby | -0.036 |
hole | -0.036 |
iest | -0.036 |
Token | three |
Token ID | 1115 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
joke | +0.035 |
play | +0.034 |
chat | +0.032 |
eat | +0.031 |
sip | +0.031 |
Neg logit contributions | |
uster | -0.055 |
bars | -0.052 |
rier | -0.051 |
dollars | -0.050 |
hole | -0.050 |
Token | so |
Token ID | 523 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
joke | +0.031 |
play | +0.031 |
chat | +0.029 |
eat | +0.028 |
laugh | +0.027 |
Neg logit contributions | |
uster | -0.041 |
bars | -0.038 |
rier | -0.037 |
dollars | -0.037 |
hole | -0.037 |
Token | happy |
Token ID | 3772 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
uster | +0.057 |
bars | +0.055 |
rier | +0.055 |
dollars | +0.053 |
hole | +0.052 |
Neg logit contributions | |
joke | -0.037 |
play | -0.036 |
chat | -0.033 |
eat | -0.033 |
sip | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
joke | +0.087 |
play | +0.083 |
chat | +0.080 |
eat | +0.078 |
sip | +0.078 |
Neg logit contributions | |
uster | -0.093 |
bars | -0.088 |
rier | -0.087 |
hole | -0.087 |
dollars | -0.085 |
Token | see |
Token ID | 766 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
joke | +0.031 |
play | +0.029 |
chat | +0.028 |
sip | +0.026 |
eat | +0.026 |
Neg logit contributions | |
uster | -0.067 |
bars | -0.063 |
rier | -0.063 |
hole | -0.062 |
dollars | -0.061 |
Token | K |
Token ID | 509 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
uster | +0.041 |
rier | +0.039 |
bars | +0.038 |
isher | +0.038 |
dollars | +0.037 |
Neg logit contributions | |
play | -0.025 |
joke | -0.023 |
chat | -0.022 |
eat | -0.022 |
walk | -0.020 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
rier | +0.047 |
uster | +0.042 |
bars | +0.041 |
hole | +0.039 |
isher | +0.039 |
Neg logit contributions | |
play | -0.102 |
walk | -0.100 |
chat | -0.098 |
joke | -0.097 |
walks | -0.097 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
uster | +0.540 |
bars | +0.502 |
rier | +0.488 |
dollars | +0.487 |
hole | +0.473 |
Neg logit contributions | |
joke | -0.571 |
play | -0.568 |
chat | -0.535 |
eat | -0.527 |
laugh | -0.507 |
Token | with |
Token ID | 351 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
joke | +0.017 |
play | +0.015 |
chat | +0.015 |
sip | +0.014 |
swim | +0.014 |
Neg logit contributions | |
bars | -0.020 |
hole | -0.020 |
uster | -0.019 |
dollars | -0.019 |
rier | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
play | +0.027 |
joke | +0.026 |
chat | +0.025 |
eat | +0.023 |
laugh | +0.022 |
Neg logit contributions | |
uster | -0.057 |
rier | -0.054 |
bars | -0.054 |
hole | -0.053 |
isher | -0.052 |
Token | smile |
Token ID | 8212 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
joke | +0.009 |
play | +0.009 |
chat | +0.008 |
eat | +0.008 |
sip | +0.007 |
Neg logit contributions | |
uster | -0.014 |
bars | -0.013 |
rier | -0.013 |
dollars | -0.013 |
hole | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
joke | +0.005 |
play | +0.005 |
chat | +0.004 |
eat | +0.004 |
sip | +0.004 |
Neg logit contributions | |
uster | -0.008 |
bars | -0.007 |
rier | -0.007 |
dollars | -0.007 |
hole | -0.007 |
Token | than |
Token ID | 621 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
play | +0.040 |
joke | +0.040 |
chat | +0.037 |
eat | +0.036 |
swim | +0.034 |
Neg logit contributions | |
uster | -0.066 |
bars | -0.061 |
rier | -0.060 |
dollars | -0.059 |
isher | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
uster | +0.174 |
rier | +0.160 |
bars | +0.159 |
dollars | +0.157 |
isher | +0.156 |
Neg logit contributions | |
play | -0.123 |
joke | -0.120 |
chat | -0.113 |
eat | -0.112 |
laugh | -0.106 |
Token | park |
Token ID | 3952 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
uster | +0.029 |
bars | +0.027 |
rier | +0.027 |
dollars | +0.027 |
hole | +0.027 |
Neg logit contributions | |
joke | -0.015 |
play | -0.015 |
chat | -0.014 |
eat | -0.013 |
laugh | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
play | +0.071 |
joke | +0.070 |
chat | +0.065 |
eat | +0.063 |
dance | +0.059 |
Neg logit contributions | |
uster | -0.128 |
bars | -0.118 |
rier | -0.116 |
isher | -0.114 |
dollars | -0.114 |
Token | K |
Token ID | 509 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
play | +0.003 |
chat | +0.003 |
joke | +0.003 |
eat | +0.003 |
walk | +0.002 |
Neg logit contributions | |
uster | -0.005 |
rier | -0.005 |
isher | -0.005 |
dollars | -0.005 |
ier | -0.005 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
rier | +0.050 |
uster | +0.042 |
bars | +0.041 |
isher | +0.039 |
hole | +0.039 |
Neg logit contributions | |
play | -0.094 |
walk | -0.093 |
walks | -0.090 |
chat | -0.090 |
sip | -0.089 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
uster | +0.566 |
bars | +0.524 |
rier | +0.522 |
dollars | +0.515 |
hole | +0.496 |
Neg logit contributions | |
play | -0.535 |
joke | -0.532 |
chat | -0.503 |
eat | -0.490 |
laugh | -0.471 |
Token | ran |
Token ID | 4966 |
Feature activation | -6.97e-03 |
Pos logit contributions | |
joke | +0.014 |
play | +0.014 |
chat | +0.013 |
eat | +0.012 |
laugh | +0.012 |
Neg logit contributions | |
uster | -0.024 |
bars | -0.023 |
rier | -0.022 |
dollars | -0.022 |
hole | -0.022 |
Token | over |
Token ID | 625 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
joke | +0.011 |
play | +0.010 |
chat | +0.010 |
eat | +0.010 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.015 |
bars | -0.014 |
rier | -0.013 |
hole | -0.013 |
dollars | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
joke | +0.199 |
play | +0.194 |
chat | +0.183 |
eat | +0.178 |
sip | +0.170 |
Neg logit contributions | |
uster | -0.275 |
bars | -0.260 |
rier | -0.255 |
dollars | -0.251 |
hole | -0.251 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
joke | +0.043 |
chat | +0.038 |
play | +0.037 |
sip | +0.035 |
eat | +0.035 |
Neg logit contributions | |
uster | -0.058 |
bars | -0.056 |
hole | -0.054 |
rier | -0.052 |
mith | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -6.51e-04 |
Pos logit contributions | |
joke | +0.013 |
chat | +0.012 |
play | +0.012 |
sip | +0.012 |
eat | +0.011 |
Neg logit contributions | |
uster | -0.016 |
bars | -0.016 |
rier | -0.016 |
hole | -0.016 |
dollars | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
play | +0.001 |
joke | +0.001 |
chat | +0.001 |
eat | +0.001 |
sip | +0.001 |
Neg logit contributions | |
uster | -0.002 |
bars | -0.002 |
rier | -0.002 |
dollars | -0.002 |
hole | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
joke | +0.013 |
play | +0.013 |
chat | +0.012 |
eat | +0.012 |
sip | +0.011 |
Neg logit contributions | |
uster | -0.025 |
bars | -0.024 |
rier | -0.024 |
hole | -0.024 |
dollars | -0.023 |
Token | So |
Token ID | 2396 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
joke | +0.018 |
play | +0.017 |
chat | +0.016 |
eat | +0.016 |
sip | +0.015 |
Neg logit contributions | |
uster | -0.020 |
bars | -0.019 |
rier | -0.019 |
hole | -0.018 |
dollars | -0.018 |
Token | K |
Token ID | 509 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
play | +0.052 |
joke | +0.047 |
chat | +0.047 |
eat | +0.046 |
walk | +0.044 |
Neg logit contributions | |
uster | -0.085 |
rier | -0.081 |
bars | -0.078 |
isher | -0.078 |
dollars | -0.077 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
rier | +0.049 |
uster | +0.039 |
bars | +0.039 |
hole | +0.038 |
isher | +0.037 |
Neg logit contributions | |
play | -0.099 |
walk | -0.097 |
chat | -0.094 |
walks | -0.094 |
jog | -0.093 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
uster | +0.472 |
bars | +0.437 |
rier | +0.423 |
hole | +0.418 |
dollars | +0.413 |
Neg logit contributions | |
joke | -0.639 |
play | -0.627 |
chat | -0.602 |
eat | -0.589 |
sip | -0.572 |
Token | kne |
Token ID | 24813 |
Feature activation | +4.67e-03 |
Pos logit contributions | |
joke | +0.014 |
play | +0.013 |
chat | +0.012 |
eat | +0.012 |
sip | +0.011 |
Neg logit contributions | |
uster | -0.023 |
bars | -0.022 |
rier | -0.022 |
dollars | -0.021 |
hole | -0.021 |
Token | eled |
Token ID | 18449 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
uster | +0.007 |
bars | +0.007 |
rier | +0.007 |
dollars | +0.007 |
hole | +0.006 |
Neg logit contributions | |
play | -0.010 |
joke | -0.010 |
chat | -0.009 |
eat | -0.009 |
sip | -0.009 |
Token | down |
Token ID | 866 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
uster | +0.146 |
bars | +0.137 |
rier | +0.136 |
dollars | +0.135 |
hole | +0.133 |
Neg logit contributions | |
play | -0.078 |
joke | -0.076 |
chat | -0.071 |
eat | -0.069 |
sip | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -2.94e-04 |
Pos logit contributions | |
play | +0.151 |
joke | +0.143 |
chat | +0.138 |
eat | +0.133 |
sip | +0.125 |
Neg logit contributions | |
uster | -0.269 |
bars | -0.249 |
rier | -0.248 |
dollars | -0.246 |
isher | -0.242 |
Token | |
Token ID | 220 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
play | +0.013 |
joke | +0.013 |
chat | +0.013 |
eat | +0.012 |
sip | +0.011 |
Neg logit contributions | |
uster | -0.019 |
rier | -0.018 |
bars | -0.018 |
dollars | -0.018 |
isher | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
uster | +0.151 |
rier | +0.148 |
isher | +0.147 |
dollars | +0.146 |
bars | +0.145 |
Neg logit contributions | |
play | -0.045 |
joke | -0.038 |
eat | -0.034 |
chat | -0.034 |
sip | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
play | +0.015 |
joke | +0.014 |
chat | +0.013 |
eat | +0.012 |
laugh | +0.011 |
Neg logit contributions | |
uster | -0.039 |
rier | -0.038 |
bars | -0.037 |
isher | -0.037 |
dollars | -0.037 |
Token | So |
Token ID | 2396 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
joke | +0.024 |
play | +0.024 |
chat | +0.022 |
eat | +0.022 |
sip | +0.021 |
Neg logit contributions | |
uster | -0.029 |
bars | -0.028 |
rier | -0.027 |
dollars | -0.027 |
hole | -0.027 |
Token | K |
Token ID | 509 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
play | +0.055 |
chat | +0.050 |
joke | +0.048 |
eat | +0.048 |
walk | +0.046 |
Neg logit contributions | |
uster | -0.100 |
rier | -0.093 |
bars | -0.093 |
isher | -0.092 |
dollars | -0.090 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
rier | +0.043 |
bars | +0.037 |
uster | +0.037 |
hole | +0.035 |
isher | +0.034 |
Neg logit contributions | |
play | -0.089 |
walk | -0.088 |
chat | -0.085 |
eat | -0.084 |
walks | -0.084 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
uster | +0.498 |
bars | +0.462 |
rier | +0.452 |
dollars | +0.442 |
hole | +0.440 |
Neg logit contributions | |
joke | -0.611 |
play | -0.603 |
chat | -0.575 |
eat | -0.563 |
sip | -0.545 |
Token | put |
Token ID | 1234 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
play | +0.014 |
joke | +0.014 |
chat | +0.013 |
eat | +0.012 |
swim | +0.012 |
Neg logit contributions | |
uster | -0.029 |
rier | -0.028 |
bars | -0.027 |
dollars | -0.026 |
hole | -0.026 |
Token | on |
Token ID | 319 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
uster | +0.146 |
bars | +0.138 |
rier | +0.137 |
hole | +0.135 |
dollars | +0.134 |
Neg logit contributions | |
play | -0.066 |
joke | -0.064 |
chat | -0.060 |
eat | -0.058 |
sip | -0.054 |
Token | her |
Token ID | 607 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
joke | +0.103 |
play | +0.086 |
chat | +0.084 |
sip | +0.083 |
eat | +0.082 |
Neg logit contributions | |
bars | -0.144 |
uster | -0.142 |
dollars | -0.133 |
hole | -0.133 |
rier | -0.127 |
Token | shoes |
Token ID | 10012 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
joke | +0.019 |
play | +0.019 |
chat | +0.018 |
eat | +0.018 |
sip | +0.017 |
Neg logit contributions | |
uster | -0.022 |
bars | -0.021 |
rier | -0.021 |
dollars | -0.021 |
hole | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
play | +0.012 |
joke | +0.011 |
chat | +0.010 |
eat | +0.010 |
laugh | +0.009 |
Neg logit contributions | |
uster | -0.029 |
rier | -0.028 |
bars | -0.028 |
dollars | -0.027 |
isher | -0.027 |
Token | Just |
Token ID | 5703 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
joke | +0.017 |
play | +0.016 |
chat | +0.015 |
eat | +0.015 |
sip | +0.014 |
Neg logit contributions | |
uster | -0.022 |
bars | -0.021 |
rier | -0.020 |
dollars | -0.020 |
hole | -0.020 |
Token | then |
Token ID | 788 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
uster | +0.055 |
rier | +0.052 |
bars | +0.052 |
dollars | +0.051 |
isher | +0.049 |
Neg logit contributions | |
play | -0.032 |
joke | -0.030 |
eat | -0.029 |
chat | -0.029 |
walk | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.70e-03 |
Pos logit contributions | |
joke | +0.043 |
play | +0.041 |
chat | +0.039 |
eat | +0.039 |
sip | +0.038 |
Neg logit contributions | |
uster | -0.039 |
bars | -0.036 |
hole | -0.035 |
dollars | -0.035 |
rier | -0.035 |
Token | K |
Token ID | 509 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
play | +0.004 |
joke | +0.004 |
chat | +0.003 |
eat | +0.003 |
sip | +0.003 |
Neg logit contributions | |
uster | -0.006 |
bars | -0.006 |
rier | -0.006 |
dollars | -0.006 |
hole | -0.006 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
rier | +0.049 |
bars | +0.040 |
uster | +0.040 |
hole | +0.038 |
isher | +0.037 |
Neg logit contributions | |
play | -0.090 |
walk | -0.090 |
walks | -0.087 |
chat | -0.085 |
sip | -0.084 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
uster | +0.535 |
bars | +0.496 |
rier | +0.490 |
dollars | +0.481 |
hole | +0.468 |
Neg logit contributions | |
joke | -0.572 |
play | -0.570 |
chat | -0.539 |
eat | -0.527 |
sip | -0.507 |
Token | spotted |
Token ID | 13489 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
joke | +0.016 |
play | +0.015 |
chat | +0.014 |
eat | +0.014 |
sip | +0.013 |
Neg logit contributions | |
uster | -0.025 |
bars | -0.024 |
rier | -0.023 |
dollars | -0.023 |
hole | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -8.63e-03 |
Pos logit contributions | |
uster | +0.169 |
bars | +0.161 |
rier | +0.159 |
dollars | +0.156 |
hole | +0.156 |
Neg logit contributions | |
joke | -0.091 |
play | -0.089 |
chat | -0.082 |
eat | -0.080 |
sip | -0.075 |
Token | fun |
Token ID | 1257 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
joke | +0.014 |
play | +0.014 |
chat | +0.013 |
eat | +0.013 |
sip | +0.012 |
Neg logit contributions | |
uster | -0.017 |
rier | -0.016 |
bars | -0.016 |
dollars | -0.016 |
hole | -0.015 |
Token | playground |
Token ID | 24817 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
joke | +0.081 |
play | +0.080 |
eat | +0.079 |
enjoy | +0.078 |
chat | +0.076 |
Neg logit contributions | |
uster | -0.136 |
hole | -0.127 |
isher | -0.123 |
dollars | -0.122 |
bars | -0.122 |
Token | a |
Token ID | 257 |
Feature activation | -7.97e-03 |
Pos logit contributions | |
uster | +0.120 |
rier | +0.115 |
bars | +0.113 |
hole | +0.112 |
dollars | +0.110 |
Neg logit contributions | |
play | -0.058 |
joke | -0.057 |
chat | -0.054 |
eat | -0.051 |
sip | -0.049 |
Token | big |
Token ID | 1263 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
joke | +0.012 |
play | +0.012 |
chat | +0.011 |
eat | +0.010 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.018 |
bars | -0.017 |
rier | -0.017 |
hole | -0.016 |
dollars | -0.016 |
Token | smile |
Token ID | 8212 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
uster | +0.016 |
bars | +0.015 |
rier | +0.015 |
hole | +0.015 |
isher | +0.015 |
Neg logit contributions | |
joke | -0.005 |
play | -0.005 |
chat | -0.005 |
laugh | -0.005 |
eat | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -3.62e-04 |
Pos logit contributions | |
play | +0.007 |
joke | +0.007 |
chat | +0.006 |
eat | +0.006 |
dance | +0.006 |
Neg logit contributions | |
uster | -0.014 |
bars | -0.013 |
rier | -0.013 |
isher | -0.013 |
dollars | -0.013 |
Token | K |
Token ID | 509 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
play | +0.000 |
joke | +0.000 |
chat | +0.000 |
eat | +0.000 |
dance | +0.000 |
Neg logit contributions | |
uster | -0.001 |
rier | -0.001 |
isher | -0.001 |
bars | -0.001 |
dollars | -0.001 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
rier | +0.050 |
uster | +0.043 |
bars | +0.043 |
hole | +0.042 |
isher | +0.040 |
Neg logit contributions | |
play | -0.092 |
walk | -0.092 |
walks | -0.090 |
chat | -0.089 |
eat | -0.087 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
uster | +0.593 |
bars | +0.552 |
dollars | +0.547 |
rier | +0.542 |
hole | +0.519 |
Neg logit contributions | |
play | -0.507 |
joke | -0.497 |
chat | -0.470 |
eat | -0.463 |
laugh | -0.443 |
Token | started |
Token ID | 2067 |
Feature activation | -4.19e-04 |
Pos logit contributions | |
joke | +0.017 |
play | +0.016 |
chat | +0.015 |
eat | +0.015 |
sip | +0.014 |
Neg logit contributions | |
uster | -0.025 |
bars | -0.024 |
rier | -0.024 |
dollars | -0.023 |
hole | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
joke | +0.001 |
swamp | +0.001 |
sip | +0.001 |
play | +0.001 |
swim | +0.001 |
Neg logit contributions | |
bars | -0.001 |
uster | -0.001 |
dollars | -0.001 |
hole | -0.001 |
rier | -0.001 |
Token | read |
Token ID | 1100 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
swamp | +0.030 |
| | +0.028 |
fl | +0.027 |
sip | +0.026 |
< | +0.026 |
Neg logit contributions | |
bars | -0.054 |
uster | -0.051 |
hole | -0.050 |
ener | -0.046 |
rier | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +9.51e-03 |
Pos logit contributions | |
joke | +0.112 |
play | +0.109 |
chat | +0.102 |
eat | +0.099 |
sip | +0.094 |
Neg logit contributions | |
uster | -0.199 |
bars | -0.189 |
rier | -0.186 |
dollars | -0.184 |
hole | -0.183 |
Token | 't |
Token ID | 470 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
joke | +0.071 |
play | +0.071 |
chat | +0.065 |
eat | +0.065 |
sip | +0.062 |
Neg logit contributions | |
uster | -0.089 |
rier | -0.083 |
dollars | -0.083 |
bars | -0.082 |
isher | -0.082 |
Token | know |
Token ID | 760 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
uster | +0.226 |
bars | +0.216 |
rier | +0.214 |
dollars | +0.210 |
hole | +0.209 |
Neg logit contributions | |
joke | -0.099 |
play | -0.097 |
chat | -0.088 |
eat | -0.086 |
sip | -0.079 |
Token | how |
Token ID | 703 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
play | +0.054 |
joke | +0.051 |
eat | +0.047 |
chat | +0.043 |
sip | +0.042 |
Neg logit contributions | |
uster | -0.129 |
rier | -0.121 |
isher | -0.116 |
dollars | -0.113 |
bars | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e-03 |
Pos logit contributions | |
play | +0.030 |
joke | +0.029 |
eat | +0.026 |
chat | +0.026 |
sip | +0.024 |
Neg logit contributions | |
uster | -0.056 |
rier | -0.052 |
bars | -0.052 |
isher | -0.051 |
hole | -0.051 |
Token | K |
Token ID | 509 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
play | +0.002 |
joke | +0.002 |
chat | +0.002 |
eat | +0.002 |
walk | +0.002 |
Neg logit contributions | |
uster | -0.005 |
rier | -0.005 |
dollars | -0.005 |
bars | -0.005 |
isher | -0.005 |
Token | ait |
Token ID | 4548 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
rier | +0.049 |
uster | +0.039 |
bars | +0.037 |
hole | +0.036 |
isher | +0.036 |
Neg logit contributions | |
play | -0.097 |
walk | -0.095 |
chat | -0.093 |
walks | -0.093 |
jog | -0.091 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
uster | +0.474 |
bars | +0.440 |
rier | +0.425 |
hole | +0.421 |
dollars | +0.416 |
Neg logit contributions | |
joke | -0.632 |
play | -0.620 |
chat | -0.595 |
eat | -0.583 |
sip | -0.564 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
joke | +0.014 |
play | +0.014 |
chat | +0.013 |
eat | +0.013 |
sip | +0.012 |
Neg logit contributions | |
uster | -0.025 |
bars | -0.024 |
rier | -0.023 |
hole | -0.023 |
dollars | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
joke | +0.017 |
play | +0.017 |
chat | +0.016 |
eat | +0.015 |
sip | +0.014 |
Neg logit contributions | |
uster | -0.025 |
bars | -0.024 |
rier | -0.023 |
dollars | -0.023 |
hole | -0.023 |
Token | pray |
Token ID | 12472 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
joke | +0.040 |
play | +0.038 |
chat | +0.037 |
eat | +0.034 |
sip | +0.034 |
Neg logit contributions | |
uster | -0.067 |
bars | -0.063 |
rier | -0.062 |
hole | -0.061 |
dollars | -0.061 |
Token | but |
Token ID | 475 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
uster | +0.070 |
bars | +0.065 |
isher | +0.064 |
rier | +0.064 |
dollars | +0.063 |
Neg logit contributions | |
play | -0.043 |
joke | -0.041 |
chat | -0.038 |
eat | -0.038 |
laugh | -0.036 |
Token | pretty |
Token ID | 2495 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
joke | +0.005 |
play | +0.005 |
chat | +0.005 |
eat | +0.005 |
sip | +0.005 |
Neg logit contributions | |
bars | -0.007 |
uster | -0.007 |
hole | -0.007 |
rier | -0.007 |
dollars | -0.007 |
Token | flowers |
Token ID | 12734 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
joke | +0.062 |
play | +0.058 |
eat | +0.056 |
chat | +0.056 |
sip | +0.055 |
Neg logit contributions | |
bars | -0.070 |
rier | -0.069 |
uster | -0.069 |
hole | -0.068 |
dollars | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -4.47e-03 |
Pos logit contributions | |
joke | +0.179 |
play | +0.168 |
chat | +0.160 |
eat | +0.156 |
sip | +0.152 |
Neg logit contributions | |
uster | -0.205 |
bars | -0.203 |
hole | -0.199 |
rier | -0.192 |
dollars | -0.190 |
Token | but |
Token ID | 475 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
joke | +0.008 |
play | +0.008 |
chat | +0.007 |
eat | +0.007 |
laugh | +0.007 |
Neg logit contributions | |
uster | -0.009 |
bars | -0.008 |
rier | -0.008 |
dollars | -0.008 |
hole | -0.008 |
Token | K |
Token ID | 509 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
uster | +0.181 |
rier | +0.168 |
dollars | +0.163 |
bars | +0.163 |
isher | +0.162 |
Neg logit contributions | |
play | -0.098 |
joke | -0.091 |
chat | -0.089 |
eat | -0.086 |
walk | -0.080 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
rier | +0.046 |
uster | +0.039 |
bars | +0.037 |
hole | +0.035 |
isher | +0.035 |
Neg logit contributions | |
play | -0.095 |
walk | -0.093 |
walks | -0.091 |
chat | -0.091 |
eat | -0.088 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
uster | +0.529 |
bars | +0.489 |
rier | +0.484 |
dollars | +0.474 |
hole | +0.462 |
Neg logit contributions | |
joke | -0.576 |
play | -0.573 |
chat | -0.541 |
eat | -0.531 |
sip | -0.510 |
Token | wasn |
Token ID | 2492 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
joke | +0.016 |
play | +0.016 |
chat | +0.015 |
eat | +0.015 |
sip | +0.014 |
Neg logit contributions | |
uster | -0.027 |
bars | -0.025 |
rier | -0.025 |
dollars | -0.024 |
hole | -0.024 |
Token | 't |
Token ID | 470 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
uster | +0.056 |
isher | +0.054 |
rier | +0.054 |
bars | +0.053 |
dollars | +0.053 |
Neg logit contributions | |
play | -0.041 |
joke | -0.041 |
chat | -0.038 |
eat | -0.038 |
laugh | -0.036 |
Token | interested |
Token ID | 4609 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
uster | +0.198 |
bars | +0.193 |
isher | +0.184 |
rier | +0.184 |
dollars | +0.181 |
Neg logit contributions | |
play | -0.126 |
joke | -0.126 |
chat | -0.117 |
eat | -0.115 |
laugh | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
play | +0.035 |
joke | +0.035 |
chat | +0.031 |
eat | +0.031 |
dance | +0.029 |
Neg logit contributions | |
uster | -0.076 |
bars | -0.072 |
isher | -0.069 |
dollars | -0.069 |
hole | -0.069 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
joke | +0.045 |
chat | +0.040 |
play | +0.039 |
sip | +0.037 |
laugh | +0.037 |
Neg logit contributions | |
uster | -0.049 |
ubby | -0.044 |
hole | -0.044 |
dollars | -0.044 |
bars | -0.043 |
Token | little |
Token ID | 1310 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
joke | +0.025 |
chat | +0.024 |
play | +0.024 |
eat | +0.023 |
sip | +0.023 |
Neg logit contributions | |
uster | -0.016 |
dollars | -0.014 |
rier | -0.014 |
bars | -0.013 |
ubby | -0.013 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
uster | +0.025 |
bars | +0.024 |
rier | +0.023 |
hole | +0.023 |
dollars | +0.023 |
Neg logit contributions | |
joke | -0.027 |
play | -0.027 |
chat | -0.025 |
eat | -0.024 |
swim | -0.024 |
Token | named |
Token ID | 3706 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
joke | +0.042 |
play | +0.041 |
chat | +0.038 |
eat | +0.037 |
sip | +0.035 |
Neg logit contributions | |
uster | -0.070 |
bars | -0.066 |
rier | -0.065 |
dollars | -0.064 |
hole | -0.064 |
Token | K |
Token ID | 509 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
uster | +0.118 |
bars | +0.110 |
hole | +0.110 |
rier | +0.103 |
dollars | +0.102 |
Neg logit contributions | |
joke | -0.114 |
chat | -0.103 |
play | -0.099 |
swim | -0.096 |
jokes | -0.095 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
rier | +0.072 |
uster | +0.069 |
bars | +0.066 |
dollars | +0.066 |
isher | +0.063 |
Neg logit contributions | |
play | -0.066 |
joke | -0.060 |
chat | -0.060 |
walk | -0.059 |
eat | -0.058 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
uster | +0.490 |
bars | +0.455 |
rier | +0.445 |
hole | +0.440 |
dollars | +0.433 |
Neg logit contributions | |
joke | -0.608 |
play | -0.593 |
chat | -0.571 |
eat | -0.555 |
sip | -0.543 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
joke | +0.022 |
play | +0.020 |
chat | +0.020 |
eat | +0.019 |
sip | +0.019 |
Neg logit contributions | |
uster | -0.027 |
bars | -0.026 |
hole | -0.025 |
dollars | -0.025 |
rier | -0.025 |
Token | K |
Token ID | 509 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
play | +0.016 |
joke | +0.015 |
chat | +0.014 |
eat | +0.014 |
laugh | +0.013 |
Neg logit contributions | |
uster | -0.025 |
rier | -0.024 |
bars | -0.024 |
dollars | -0.024 |
isher | -0.023 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
rier | +0.042 |
uster | +0.035 |
bars | +0.034 |
dollars | +0.032 |
isher | +0.031 |
Neg logit contributions | |
play | -0.089 |
chat | -0.085 |
walk | -0.084 |
joke | -0.084 |
eat | -0.083 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
uster | +0.485 |
bars | +0.450 |
rier | +0.439 |
hole | +0.431 |
dollars | +0.429 |
Neg logit contributions | |
joke | -0.613 |
play | -0.603 |
chat | -0.577 |
eat | -0.564 |
sip | -0.548 |
Token | on |
Token ID | 319 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
joke | +0.029 |
play | +0.029 |
chat | +0.026 |
eat | +0.025 |
laugh | +0.024 |
Neg logit contributions | |
uster | -0.052 |
bars | -0.049 |
rier | -0.048 |
dollars | -0.048 |
hole | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
joke | +0.085 |
play | +0.084 |
chat | +0.077 |
eat | +0.075 |
sip | +0.071 |
Neg logit contributions | |
uster | -0.152 |
bars | -0.142 |
rier | -0.141 |
dollars | -0.139 |
hole | -0.138 |
Token | walls |
Token ID | 7714 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
uster | +0.024 |
bars | +0.022 |
rier | +0.022 |
dollars | +0.021 |
hole | +0.021 |
Neg logit contributions | |
play | -0.020 |
joke | -0.020 |
eat | -0.018 |
chat | -0.018 |
dance | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.24e-03 |
Pos logit contributions | |
uster | +0.107 |
dollars | +0.097 |
isher | +0.096 |
rier | +0.095 |
bars | +0.094 |
Neg logit contributions | |
play | -0.062 |
joke | -0.058 |
eat | -0.055 |
chat | -0.054 |
dance | -0.053 |
Token | K |
Token ID | 509 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
uster | +0.005 |
rier | +0.005 |
dollars | +0.005 |
isher | +0.005 |
bars | +0.005 |
Neg logit contributions | |
play | -0.003 |
joke | -0.003 |
chat | -0.002 |
eat | -0.002 |
laugh | -0.002 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
rier | +0.054 |
uster | +0.042 |
bars | +0.041 |
isher | +0.039 |
hole | +0.039 |
Neg logit contributions | |
play | -0.095 |
walk | -0.094 |
chat | -0.091 |
walks | -0.091 |
joke | -0.089 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
uster | +0.584 |
rier | +0.545 |
dollars | +0.539 |
bars | +0.533 |
hole | +0.507 |
Neg logit contributions | |
play | -0.507 |
joke | -0.502 |
chat | -0.471 |
eat | -0.459 |
laugh | -0.447 |
Token | made |
Token ID | 925 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
joke | +0.013 |
play | +0.013 |
chat | +0.012 |
eat | +0.012 |
laugh | +0.011 |
Neg logit contributions | |
uster | -0.026 |
bars | -0.024 |
rier | -0.024 |
dollars | -0.023 |
hole | -0.023 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
uster | +0.163 |
rier | +0.157 |
bars | +0.156 |
hole | +0.152 |
dollars | +0.150 |
Neg logit contributions | |
joke | -0.110 |
play | -0.106 |
chat | -0.102 |
eat | -0.099 |
sip | -0.098 |
Token | art |
Token ID | 1242 |
Feature activation | -9.03e-03 |
Pos logit contributions | |
joke | +0.078 |
sip | +0.074 |
play | +0.074 |
chat | +0.074 |
eat | +0.072 |
Neg logit contributions | |
rier | -0.081 |
uster | -0.081 |
bars | -0.080 |
hole | -0.080 |
dollars | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
joke | +0.013 |
play | +0.013 |
chat | +0.011 |
eat | +0.011 |
dance | +0.011 |
Neg logit contributions | |
uster | -0.021 |
bars | -0.020 |
rier | -0.019 |
dollars | -0.019 |
hole | -0.019 |
Token | lots |
Token ID | 6041 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
play | +0.003 |
joke | +0.003 |
chat | +0.003 |
eat | +0.003 |
dance | +0.003 |
Neg logit contributions | |
uster | -0.006 |
rier | -0.005 |
bars | -0.005 |
hole | -0.005 |
dollars | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
uster | +0.052 |
rier | +0.047 |
bars | +0.046 |
hole | +0.046 |
isher | +0.045 |
Neg logit contributions | |
play | -0.091 |
joke | -0.090 |
eat | -0.085 |
chat | -0.085 |
sip | -0.083 |
Token | poems |
Token ID | 31888 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
uster | +0.234 |
bars | +0.222 |
rier | +0.219 |
hole | +0.215 |
dollars | +0.214 |
Neg logit contributions | |
joke | -0.144 |
play | -0.141 |
chat | -0.131 |
eat | -0.127 |
sip | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | -4.86e-03 |
Pos logit contributions | |
joke | +0.058 |
play | +0.058 |
chat | +0.054 |
eat | +0.052 |
sip | +0.050 |
Neg logit contributions | |
uster | -0.094 |
bars | -0.089 |
rier | -0.087 |
dollars | -0.086 |
hole | -0.085 |
Token | K |
Token ID | 509 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
play | +0.007 |
joke | +0.007 |
chat | +0.006 |
eat | +0.006 |
chase | +0.006 |
Neg logit contributions | |
uster | -0.011 |
rier | -0.011 |
dollars | -0.010 |
isher | -0.010 |
bars | -0.010 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
rier | +0.047 |
uster | +0.040 |
bars | +0.038 |
hole | +0.037 |
isher | +0.035 |
Neg logit contributions | |
play | -0.095 |
walk | -0.093 |
chat | -0.091 |
walks | -0.091 |
joke | -0.090 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
uster | +0.531 |
bars | +0.490 |
rier | +0.487 |
dollars | +0.478 |
hole | +0.466 |
Neg logit contributions | |
joke | -0.569 |
play | -0.568 |
chat | -0.536 |
eat | -0.525 |
laugh | -0.505 |
Token | was |
Token ID | 373 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
joke | +0.019 |
play | +0.018 |
chat | +0.017 |
eat | +0.017 |
sip | +0.016 |
Neg logit contributions | |
uster | -0.028 |
bars | -0.028 |
dollars | -0.027 |
hole | -0.026 |
rier | -0.026 |
Token | so |
Token ID | 523 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
joke | +0.038 |
play | +0.037 |
chat | +0.035 |
eat | +0.034 |
sip | +0.034 |
Neg logit contributions | |
uster | -0.044 |
bars | -0.041 |
rier | -0.041 |
dollars | -0.040 |
hole | -0.040 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
uster | +0.046 |
rier | +0.046 |
bars | +0.046 |
dollars | +0.044 |
hole | +0.042 |
Neg logit contributions | |
joke | -0.035 |
play | -0.034 |
chat | -0.033 |
eat | -0.032 |
sip | -0.031 |
Token | ! |
Token ID | 0 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
joke | +0.022 |
play | +0.022 |
chat | +0.020 |
eat | +0.020 |
laugh | +0.019 |
Neg logit contributions | |
uster | -0.031 |
bars | -0.030 |
rier | -0.029 |
dollars | -0.029 |
hole | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
joke | +0.049 |
chat | +0.044 |
play | +0.042 |
sip | +0.041 |
eat | +0.041 |
Neg logit contributions | |
uster | -0.046 |
bars | -0.040 |
hole | -0.040 |
dollars | -0.040 |
ubby | -0.039 |
Token | little |
Token ID | 1310 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
joke | +0.027 |
chat | +0.026 |
play | +0.026 |
eat | +0.025 |
sip | +0.025 |
Neg logit contributions | |
uster | -0.017 |
rier | -0.015 |
dollars | -0.015 |
bars | -0.014 |
ubby | -0.014 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
uster | +0.037 |
bars | +0.035 |
rier | +0.034 |
hole | +0.033 |
dollars | +0.033 |
Neg logit contributions | |
joke | -0.038 |
play | -0.038 |
chat | -0.036 |
eat | -0.035 |
sip | -0.034 |
Token | named |
Token ID | 3706 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
joke | +0.038 |
play | +0.036 |
chat | +0.034 |
eat | +0.033 |
sip | +0.032 |
Neg logit contributions | |
uster | -0.057 |
bars | -0.054 |
hole | -0.052 |
dollars | -0.052 |
rier | -0.052 |
Token | K |
Token ID | 509 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
uster | +0.130 |
bars | +0.121 |
hole | +0.121 |
rier | +0.114 |
dollars | +0.114 |
Neg logit contributions | |
joke | -0.121 |
chat | -0.110 |
play | -0.108 |
swim | -0.105 |
jokes | -0.101 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
rier | +0.078 |
uster | +0.072 |
dollars | +0.070 |
bars | +0.069 |
isher | +0.066 |
Neg logit contributions | |
play | -0.070 |
joke | -0.063 |
chat | -0.063 |
walk | -0.062 |
eat | -0.060 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
uster | +0.481 |
bars | +0.444 |
hole | +0.436 |
rier | +0.432 |
dollars | +0.422 |
Neg logit contributions | |
joke | -0.612 |
play | -0.591 |
chat | -0.575 |
eat | -0.555 |
sip | -0.546 |
Token | who |
Token ID | 508 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
joke | +0.020 |
chat | +0.018 |
play | +0.018 |
eat | +0.018 |
sip | +0.017 |
Neg logit contributions | |
uster | -0.023 |
bars | -0.022 |
hole | -0.022 |
dollars | -0.021 |
rier | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
bars | +0.047 |
uster | +0.046 |
dollars | +0.045 |
iest | +0.044 |
hole | +0.043 |
Neg logit contributions | |
sip | -0.073 |
joke | -0.071 |
swim | -0.070 |
jokes | -0.069 |
swamp | -0.067 |
Token | very |
Token ID | 845 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
joke | +0.040 |
chat | +0.037 |
sip | +0.036 |
play | +0.036 |
eat | +0.035 |
Neg logit contributions | |
uster | -0.047 |
rier | -0.045 |
bars | -0.045 |
dollars | -0.043 |
ubby | -0.043 |
Token | sad |
Token ID | 6507 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
joke | +0.044 |
chat | +0.042 |
play | +0.042 |
sip | +0.039 |
eat | +0.038 |
Neg logit contributions | |
uster | -0.055 |
rier | -0.053 |
bars | -0.051 |
dollars | -0.050 |
ubby | -0.049 |
Token | K |
Token ID | 509 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
uster | +0.118 |
bars | +0.110 |
hole | +0.110 |
rier | +0.103 |
dollars | +0.102 |
Neg logit contributions | |
joke | -0.114 |
chat | -0.103 |
play | -0.099 |
swim | -0.096 |
jokes | -0.095 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
rier | +0.072 |
uster | +0.069 |
bars | +0.066 |
dollars | +0.066 |
isher | +0.063 |
Neg logit contributions | |
play | -0.066 |
joke | -0.060 |
chat | -0.060 |
walk | -0.059 |
eat | -0.058 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
uster | +0.490 |
bars | +0.455 |
rier | +0.445 |
hole | +0.440 |
dollars | +0.433 |
Neg logit contributions | |
joke | -0.608 |
play | -0.593 |
chat | -0.571 |
eat | -0.555 |
sip | -0.543 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
joke | +0.022 |
play | +0.020 |
chat | +0.020 |
eat | +0.019 |
sip | +0.019 |
Neg logit contributions | |
uster | -0.027 |
bars | -0.026 |
hole | -0.025 |
dollars | -0.025 |
rier | -0.025 |
Token | K |
Token ID | 509 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
play | +0.016 |
joke | +0.015 |
chat | +0.014 |
eat | +0.014 |
laugh | +0.013 |
Neg logit contributions | |
uster | -0.025 |
rier | -0.024 |
bars | -0.024 |
dollars | -0.024 |
isher | -0.023 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
rier | +0.042 |
uster | +0.035 |
bars | +0.034 |
dollars | +0.032 |
isher | +0.031 |
Neg logit contributions | |
play | -0.089 |
chat | -0.085 |
walk | -0.084 |
joke | -0.084 |
eat | -0.083 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
uster | +0.485 |
bars | +0.450 |
rier | +0.439 |
hole | +0.431 |
dollars | +0.429 |
Neg logit contributions | |
joke | -0.613 |
play | -0.603 |
chat | -0.577 |
eat | -0.564 |
sip | -0.548 |
Token | went |
Token ID | 1816 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
joke | +0.020 |
play | +0.018 |
chat | +0.018 |
sip | +0.017 |
eat | +0.017 |
Neg logit contributions | |
uster | -0.033 |
bars | -0.033 |
hole | -0.032 |
dollars | -0.032 |
rier | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
joke | +0.114 |
sip | +0.102 |
jokes | +0.100 |
chat | +0.100 |
laugh | +0.096 |
Neg logit contributions | |
uster | -0.090 |
bars | -0.082 |
hole | -0.080 |
dollars | -0.072 |
rier | -0.070 |
Token | school |
Token ID | 1524 |
Feature activation | -7.61e-04 |
Pos logit contributions | |
joke | +0.055 |
chat | +0.049 |
sip | +0.049 |
Boo | +0.048 |
jokes | +0.047 |
Neg logit contributions | |
uster | -0.048 |
bars | -0.046 |
hole | -0.045 |
mith | -0.040 |
one | -0.039 |
Token | every |
Token ID | 790 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
play | +0.001 |
joke | +0.001 |
chat | +0.001 |
eat | +0.001 |
laugh | +0.001 |
Neg logit contributions | |
uster | -0.002 |
rier | -0.002 |
bars | -0.002 |
dollars | -0.002 |
hole | -0.002 |
Token | In |
Token ID | 818 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
joke | +0.016 |
play | +0.016 |
chat | +0.015 |
eat | +0.014 |
sip | +0.014 |
Neg logit contributions | |
uster | -0.018 |
bars | -0.017 |
rier | -0.016 |
dollars | -0.016 |
hole | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +9.50e-03 |
Pos logit contributions | |
uster | +0.091 |
rier | +0.091 |
dollars | +0.084 |
bars | +0.083 |
ier | +0.082 |
Neg logit contributions | |
play | -0.021 |
chat | -0.016 |
walk | -0.015 |
dance | -0.013 |
sip | -0.013 |
Token | end |
Token ID | 886 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
uster | +0.022 |
rier | +0.021 |
bars | +0.021 |
hole | +0.020 |
dollars | +0.020 |
Neg logit contributions | |
play | -0.014 |
joke | -0.013 |
chat | -0.012 |
eat | -0.012 |
walk | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +8.05e-04 |
Pos logit contributions | |
play | +0.002 |
joke | +0.002 |
chat | +0.002 |
eat | +0.002 |
dance | +0.002 |
Neg logit contributions | |
uster | -0.004 |
bars | -0.003 |
rier | -0.003 |
isher | -0.003 |
hole | -0.003 |
Token | K |
Token ID | 509 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
uster | +0.002 |
rier | +0.002 |
bars | +0.002 |
dollars | +0.002 |
isher | +0.002 |
Neg logit contributions | |
play | -0.001 |
joke | -0.001 |
chat | -0.001 |
eat | -0.001 |
dance | -0.001 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
rier | +0.052 |
bars | +0.042 |
uster | +0.041 |
hole | +0.040 |
isher | +0.039 |
Neg logit contributions | |
play | -0.091 |
walk | -0.090 |
walks | -0.087 |
chat | -0.087 |
eat | -0.084 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
uster | +0.575 |
rier | +0.533 |
bars | +0.532 |
dollars | +0.525 |
hole | +0.503 |
Neg logit contributions | |
play | -0.517 |
joke | -0.510 |
chat | -0.483 |
eat | -0.473 |
laugh | -0.455 |
Token | picked |
Token ID | 6497 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
play | +0.015 |
joke | +0.015 |
chat | +0.014 |
eat | +0.013 |
laugh | +0.012 |
Neg logit contributions | |
uster | -0.032 |
rier | -0.030 |
bars | -0.029 |
hole | -0.029 |
dollars | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
uster | +0.004 |
bars | +0.003 |
rier | +0.003 |
dollars | +0.003 |
hole | +0.003 |
Neg logit contributions | |
play | -0.001 |
joke | -0.001 |
chat | -0.001 |
eat | -0.001 |
laugh | -0.001 |
Token | spark |
Token ID | 9009 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
play | +0.008 |
joke | +0.008 |
eat | +0.007 |
chat | +0.007 |
laugh | +0.007 |
Neg logit contributions | |
uster | -0.013 |
bars | -0.013 |
rier | -0.012 |
isher | -0.012 |
dollars | -0.012 |
Token | ly |
Token ID | 306 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
uster | +0.082 |
bars | +0.073 |
hole | +0.070 |
rier | +0.069 |
dollars | +0.068 |
Neg logit contributions | |
play | -0.097 |
joke | -0.096 |
eat | -0.090 |
chat | -0.089 |
sip | -0.089 |
Token | help |
Token ID | 1037 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
joke | +0.040 |
swamp | +0.040 |
chat | +0.039 |
sip | +0.036 |
play | +0.036 |
Neg logit contributions | |
uster | -0.062 |
bars | -0.056 |
rier | -0.056 |
hole | -0.055 |
mith | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
uster | +0.202 |
bars | +0.193 |
dollars | +0.191 |
rier | +0.190 |
isher | +0.189 |
Neg logit contributions | |
play | -0.085 |
joke | -0.079 |
eat | -0.073 |
chat | -0.071 |
laugh | -0.065 |
Token | She |
Token ID | 1375 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
play | +0.009 |
joke | +0.008 |
chat | +0.008 |
eat | +0.008 |
walk | +0.007 |
Neg logit contributions | |
uster | -0.016 |
rier | -0.015 |
dollars | -0.015 |
isher | -0.015 |
bars | -0.014 |
Token | gave |
Token ID | 2921 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
play | +0.034 |
joke | +0.033 |
chat | +0.032 |
eat | +0.030 |
sip | +0.028 |
Neg logit contributions | |
uster | -0.055 |
rier | -0.052 |
bars | -0.051 |
hole | -0.050 |
dollars | -0.049 |
Token | K |
Token ID | 509 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
uster | +0.194 |
rier | +0.188 |
bars | +0.186 |
dollars | +0.186 |
hole | +0.179 |
Neg logit contributions | |
play | -0.104 |
chat | -0.095 |
joke | -0.095 |
eat | -0.090 |
walk | -0.085 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
rier | +0.043 |
uster | +0.038 |
hole | +0.036 |
bars | +0.036 |
mith | +0.034 |
Neg logit contributions | |
play | -0.095 |
joke | -0.092 |
walk | -0.092 |
chat | -0.091 |
walks | -0.091 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
uster | +0.545 |
bars | +0.510 |
rier | +0.501 |
dollars | +0.494 |
hole | +0.483 |
Neg logit contributions | |
play | -0.548 |
joke | -0.548 |
chat | -0.511 |
eat | -0.505 |
laugh | -0.489 |
Token | an |
Token ID | 281 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
joke | +0.021 |
play | +0.019 |
chat | +0.019 |
eat | +0.018 |
swim | +0.017 |
Neg logit contributions | |
uster | -0.028 |
bars | -0.028 |
dollars | -0.027 |
rier | -0.026 |
hole | -0.026 |
Token | ugly |
Token ID | 13400 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
uster | +0.148 |
bars | +0.147 |
rier | +0.140 |
mith | +0.140 |
isher | +0.139 |
Neg logit contributions | |
joke | -0.115 |
play | -0.113 |
eat | -0.106 |
jokes | -0.101 |
laugh | -0.100 |
Token | book |
Token ID | 1492 |
Feature activation | +2.59e-04 |
Pos logit contributions | |
joke | +0.054 |
play | +0.052 |
chat | +0.048 |
eat | +0.046 |
laugh | +0.045 |
Neg logit contributions | |
uster | -0.090 |
bars | -0.085 |
hole | -0.083 |
rier | -0.083 |
isher | -0.082 |
Token | with |
Token ID | 351 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
uster | +0.001 |
rier | +0.001 |
isher | +0.001 |
dollars | +0.001 |
bars | +0.001 |
Neg logit contributions | |
play | -0.000 |
joke | -0.000 |
chat | -0.000 |
eat | -0.000 |
laugh | -0.000 |
Token | agreed |
Token ID | 4987 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
joke | +0.005 |
play | +0.005 |
chat | +0.004 |
sip | +0.004 |
eat | +0.004 |
Neg logit contributions | |
uster | -0.005 |
bars | -0.005 |
rier | -0.005 |
dollars | -0.004 |
hole | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
uster | +0.033 |
bars | +0.032 |
rier | +0.032 |
dollars | +0.031 |
hole | +0.030 |
Neg logit contributions | |
joke | -0.028 |
play | -0.027 |
chat | -0.026 |
eat | -0.025 |
sip | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
joke | +0.004 |
play | +0.004 |
chat | +0.004 |
eat | +0.004 |
sip | +0.004 |
Neg logit contributions | |
uster | -0.007 |
bars | -0.007 |
rier | -0.007 |
hole | -0.006 |
dollars | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
joke | +0.018 |
play | +0.016 |
chat | +0.016 |
eat | +0.016 |
sip | +0.016 |
Neg logit contributions | |
uster | -0.024 |
bars | -0.022 |
hole | -0.021 |
mith | -0.021 |
dollars | -0.020 |
Token | K |
Token ID | 42 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
joke | +0.019 |
play | +0.018 |
eat | +0.018 |
chat | +0.017 |
sip | +0.017 |
Neg logit contributions | |
uster | -0.022 |
bars | -0.020 |
hole | -0.019 |
dollars | -0.019 |
mith | -0.018 |
Token | ait |
Token ID | 4548 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
rier | +0.067 |
uster | +0.052 |
bars | +0.051 |
hole | +0.049 |
dollars | +0.048 |
Neg logit contributions | |
play | -0.097 |
walk | -0.094 |
chat | -0.093 |
walks | -0.092 |
| | -0.091 |
Token | lyn |
Token ID | 6213 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
uster | +0.519 |
bars | +0.480 |
rier | +0.475 |
dollars | +0.468 |
hole | +0.458 |
Neg logit contributions | |
joke | -0.576 |
play | -0.572 |
chat | -0.543 |
eat | -0.530 |
laugh | -0.514 |
Token | and |
Token ID | 290 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
joke | +0.021 |
play | +0.020 |
chat | +0.019 |
eat | +0.018 |
sip | +0.018 |
Neg logit contributions | |
uster | -0.031 |
bars | -0.030 |
dollars | -0.029 |
hole | -0.029 |
rier | -0.029 |
Token | Alex |
Token ID | 4422 |
Feature activation | -9.66e-03 |
Pos logit contributions | |
joke | +0.006 |
play | +0.005 |
chat | +0.005 |
eat | +0.005 |
sip | +0.005 |
Neg logit contributions | |
uster | -0.006 |
bars | -0.005 |
rier | -0.005 |
dollars | -0.005 |
hole | -0.005 |
Token | showed |
Token ID | 3751 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
joke | +0.013 |
play | +0.012 |
chat | +0.011 |
eat | +0.011 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.023 |
bars | -0.022 |
dollars | -0.021 |
hole | -0.021 |
rier | -0.021 |
Token | that |
Token ID | 326 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
uster | +0.149 |
bars | +0.141 |
rier | +0.138 |
dollars | +0.136 |
isher | +0.135 |
Neg logit contributions | |
joke | -0.093 |
play | -0.088 |
chat | -0.084 |
eat | -0.082 |
sip | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | -6.58e-03 |
Pos logit contributions | |
joke | +0.140 |
play | +0.133 |
chat | +0.128 |
eat | +0.123 |
sip | +0.121 |
Neg logit contributions | |
uster | -0.154 |
hole | -0.146 |
bars | -0.145 |
dollars | -0.143 |
rier | -0.142 |
Token | roses |
Token ID | 42152 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
joke | +0.010 |
play | +0.010 |
chat | +0.010 |
eat | +0.009 |
sip | +0.009 |
Neg logit contributions | |
uster | -0.013 |
bars | -0.013 |
dollars | -0.012 |
rier | -0.012 |
hole | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
joke | +0.097 |
play | +0.096 |
chat | +0.090 |
eat | +0.088 |
sip | +0.084 |
Neg logit contributions | |
uster | -0.131 |
bars | -0.123 |
rier | -0.121 |
dollars | -0.118 |
hole | -0.118 |
Token | and |
Token ID | 290 |
Feature activation | -4.34e-04 |
Pos logit contributions | |
joke | +0.010 |
play | +0.010 |
chat | +0.009 |
eat | +0.009 |
sip | +0.009 |
Neg logit contributions | |
uster | -0.012 |
bars | -0.012 |
rier | -0.012 |
dollars | -0.011 |
hole | -0.011 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
joke | +0.001 |
play | +0.001 |
chat | +0.001 |
eat | +0.001 |
sip | +0.001 |
Neg logit contributions | |
uster | -0.001 |
bars | -0.001 |
rier | -0.001 |
dollars | -0.001 |
hole | -0.001 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
joke | +0.041 |
play | +0.039 |
chat | +0.036 |
sip | +0.034 |
eat | +0.034 |
Neg logit contributions | |
uster | -0.076 |
bars | -0.075 |
rier | -0.074 |
hole | -0.073 |
dollars | -0.072 |
Token | owers |
Token ID | 3618 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
joke | +0.546 |
play | +0.532 |
chat | +0.497 |
eat | +0.487 |
sip | +0.468 |
Neg logit contributions | |
uster | -0.727 |
bars | -0.691 |
rier | -0.677 |
hole | -0.666 |
dollars | -0.665 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-03 |
Pos logit contributions | |
joke | +0.115 |
play | +0.108 |
chat | +0.105 |
sip | +0.098 |
eat | +0.098 |
Neg logit contributions | |
uster | -0.136 |
bars | -0.132 |
hole | -0.131 |
dollars | -0.131 |
rier | -0.130 |
Token | They |
Token ID | 1119 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
joke | +0.002 |
play | +0.002 |
chat | +0.002 |
eat | +0.002 |
sip | +0.002 |
Neg logit contributions | |
uster | -0.004 |
bars | -0.003 |
rier | -0.003 |
dollars | -0.003 |
hole | -0.003 |
Token | waved |
Token ID | 26834 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
joke | +0.117 |
play | +0.112 |
chat | +0.104 |
eat | +0.101 |
sip | +0.098 |
Neg logit contributions | |
uster | -0.181 |
bars | -0.174 |
dollars | -0.168 |
hole | -0.167 |
rier | -0.167 |
Token | to |
Token ID | 284 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
uster | +0.234 |
bars | +0.224 |
hole | +0.218 |
rier | +0.215 |
dollars | +0.213 |
Neg logit contributions | |
play | -0.143 |
joke | -0.140 |
chat | -0.133 |
eat | -0.127 |
laugh | -0.123 |
Token | ." |
Token ID | 526 |
Feature activation | +8.74e-03 |
Pos logit contributions | |
joke | +0.055 |
play | +0.054 |
chat | +0.051 |
eat | +0.049 |
sip | +0.048 |
Neg logit contributions | |
uster | -0.071 |
bars | -0.069 |
rier | -0.068 |
dollars | -0.066 |
hole | -0.066 |
Token | Sam |
Token ID | 3409 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
uster | +0.021 |
bars | +0.019 |
rier | +0.019 |
dollars | +0.019 |
hole | +0.019 |
Neg logit contributions | |
joke | -0.012 |
play | -0.011 |
chat | -0.010 |
eat | -0.010 |
sip | -0.010 |
Token | thought |
Token ID | 1807 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
bars | +0.017 |
uster | +0.017 |
dollars | +0.016 |
hole | +0.016 |
ener | +0.015 |
Neg logit contributions | |
joke | -0.020 |
play | -0.019 |
chat | -0.019 |
eat | -0.018 |
sip | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +2.90e-03 |
Pos logit contributions | |
joke | +0.111 |
play | +0.110 |
chat | +0.104 |
eat | +0.101 |
sip | +0.097 |
Neg logit contributions | |
uster | -0.135 |
bars | -0.127 |
rier | -0.124 |
dollars | -0.122 |
hole | -0.122 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
rier | +0.005 |
bars | +0.005 |
uster | +0.005 |
hole | +0.005 |
dollars | +0.005 |
Neg logit contributions | |
play | -0.005 |
joke | -0.005 |
chat | -0.005 |
eat | -0.004 |
sip | -0.004 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
joke | +0.051 |
play | +0.050 |
eat | +0.048 |
chat | +0.046 |
swamp | +0.045 |
Neg logit contributions | |
bars | -0.070 |
uster | -0.067 |
rier | -0.066 |
hole | -0.065 |
dollars | -0.064 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
joke | +0.627 |
play | +0.607 |
eat | +0.573 |
chat | +0.571 |
sip | +0.552 |
Neg logit contributions | |
uster | -0.594 |
bars | -0.592 |
rier | -0.587 |
isher | -0.577 |
hole | -0.561 |
Token | were |
Token ID | 547 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
joke | +0.104 |
play | +0.098 |
chat | +0.092 |
eat | +0.090 |
chase | +0.089 |
Neg logit contributions | |
bars | -0.131 |
dollars | -0.127 |
uster | -0.127 |
rier | -0.126 |
hole | -0.126 |
Token | incredible |
Token ID | 8082 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
joke | +0.025 |
play | +0.024 |
chat | +0.023 |
eat | +0.022 |
sip | +0.021 |
Neg logit contributions | |
uster | -0.037 |
bars | -0.035 |
rier | -0.035 |
dollars | -0.034 |
hole | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -5.28e-03 |
Pos logit contributions | |
joke | +0.084 |
play | +0.082 |
chat | +0.078 |
eat | +0.076 |
sip | +0.074 |
Neg logit contributions | |
uster | -0.101 |
rier | -0.098 |
bars | -0.097 |
dollars | -0.096 |
hole | -0.094 |
Token | He |
Token ID | 679 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
joke | +0.007 |
play | +0.007 |
chat | +0.007 |
eat | +0.007 |
sip | +0.006 |
Neg logit contributions | |
uster | -0.012 |
bars | -0.011 |
rier | -0.011 |
dollars | -0.011 |
hole | -0.011 |
Token | en |
Token ID | 551 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
joke | +0.028 |
play | +0.028 |
chat | +0.026 |
eat | +0.025 |
sip | +0.024 |
Neg logit contributions | |
uster | -0.050 |
bars | -0.047 |
rier | -0.047 |
dollars | -0.046 |
hole | -0.046 |
Token | vious |
Token ID | 1442 |
Feature activation | -5.29e-03 |
Pos logit contributions | |
uster | +0.016 |
bars | +0.014 |
rier | +0.014 |
hole | +0.014 |
mith | +0.014 |
Neg logit contributions | |
play | -0.016 |
joke | -0.016 |
eat | -0.014 |
chat | -0.014 |
laugh | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +9.64e-02 |
Pos logit contributions | |
play | +0.010 |
joke | +0.010 |
eat | +0.009 |
jokes | +0.008 |
dance | +0.008 |
Neg logit contributions | |
uster | -0.011 |
isher | -0.010 |
mith | -0.010 |
rier | -0.010 |
bars | -0.009 |
Token | your |
Token ID | 534 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
uster | +0.193 |
bars | +0.176 |
rier | +0.174 |
hole | +0.173 |
dollars | +0.170 |
Neg logit contributions | |
joke | -0.171 |
play | -0.171 |
eat | -0.156 |
chat | -0.156 |
swim | -0.148 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
uster | +0.156 |
bars | +0.149 |
rier | +0.147 |
dollars | +0.146 |
hole | +0.142 |
Neg logit contributions | |
joke | -0.127 |
play | -0.125 |
chat | -0.121 |
eat | -0.117 |
sip | -0.114 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
joke | +0.061 |
play | +0.060 |
chat | +0.056 |
eat | +0.055 |
sip | +0.053 |
Neg logit contributions | |
uster | -0.075 |
bars | -0.071 |
rier | -0.069 |
dollars | -0.068 |
hole | -0.068 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
joke | +0.539 |
play | +0.528 |
chat | +0.497 |
eat | +0.486 |
sip | +0.469 |
Neg logit contributions | |
uster | -0.715 |
bars | -0.685 |
rier | -0.673 |
hole | -0.658 |
dollars | -0.658 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
joke | +0.103 |
play | +0.103 |
chat | +0.095 |
eat | +0.094 |
laugh | +0.088 |
Neg logit contributions | |
uster | -0.156 |
bars | -0.146 |
rier | -0.143 |
hole | -0.140 |
dollars | -0.139 |
Token | I |
Token ID | 314 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
uster | +0.004 |
hole | +0.004 |
isher | +0.004 |
bars | +0.004 |
dollars | +0.004 |
Neg logit contributions | |
play | -0.004 |
joke | -0.004 |
eat | -0.003 |
swim | -0.003 |
chat | -0.003 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
uster | +0.139 |
bars | +0.131 |
dollars | +0.130 |
rier | +0.128 |
hole | +0.128 |
Neg logit contributions | |
joke | -0.095 |
play | -0.092 |
chat | -0.088 |
eat | -0.085 |
swim | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
joke | +0.029 |
play | +0.029 |
chat | +0.026 |
eat | +0.026 |
swim | +0.024 |
Neg logit contributions | |
uster | -0.047 |
rier | -0.043 |
bars | -0.043 |
hole | -0.043 |
dollars | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -6.26e-03 |
Pos logit contributions | |
joke | +0.119 |
chat | +0.112 |
play | +0.111 |
eat | +0.103 |
| | +0.102 |
Neg logit contributions | |
hole | -0.131 |
rier | -0.127 |
bars | -0.126 |
dollars | -0.126 |
uster | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
joke | +0.011 |
play | +0.011 |
chat | +0.011 |
eat | +0.010 |
laugh | +0.010 |
Neg logit contributions | |
uster | -0.011 |
bars | -0.011 |
rier | -0.010 |
hole | -0.010 |
dollars | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
joke | +0.022 |
play | +0.021 |
chat | +0.020 |
eat | +0.019 |
sip | +0.018 |
Neg logit contributions | |
uster | -0.037 |
bars | -0.035 |
hole | -0.034 |
rier | -0.033 |
dollars | -0.033 |
Token | " |
Token ID | 1 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
joke | +0.036 |
play | +0.034 |
chat | +0.034 |
eat | +0.033 |
sip | +0.032 |
Neg logit contributions | |
uster | -0.020 |
bars | -0.018 |
hole | -0.017 |
dollars | -0.017 |
rier | -0.017 |
Token | Sun |
Token ID | 16012 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
uster | +0.129 |
bars | +0.123 |
hole | +0.118 |
rier | +0.118 |
dollars | +0.117 |
Neg logit contributions | |
joke | -0.104 |
play | -0.101 |
chat | -0.095 |
eat | -0.094 |
laugh | -0.090 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
play | +0.004 |
joke | +0.004 |
chat | +0.003 |
eat | +0.003 |
sip | +0.003 |
Neg logit contributions | |
uster | -0.005 |
bars | -0.004 |
rier | -0.004 |
dollars | -0.004 |
hole | -0.004 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
joke | +0.595 |
play | +0.574 |
chat | +0.540 |
eat | +0.534 |
swim | +0.515 |
Neg logit contributions | |
uster | -0.668 |
bars | -0.637 |
hole | -0.625 |
dollars | -0.625 |
rier | -0.618 |
Token | are |
Token ID | 389 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
joke | +0.092 |
play | +0.091 |
chat | +0.084 |
eat | +0.082 |
sip | +0.077 |
Neg logit contributions | |
uster | -0.161 |
bars | -0.152 |
rier | -0.150 |
dollars | -0.147 |
hole | -0.146 |
Token | yellow |
Token ID | 7872 |
Feature activation | +6.79e-03 |
Pos logit contributions | |
joke | +0.040 |
play | +0.039 |
chat | +0.037 |
eat | +0.036 |
sip | +0.034 |
Neg logit contributions | |
uster | -0.057 |
bars | -0.054 |
rier | -0.053 |
dollars | -0.052 |
hole | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -7.39e-03 |
Pos logit contributions | |
uster | +0.015 |
bars | +0.014 |
rier | +0.014 |
isher | +0.013 |
hole | +0.013 |
Neg logit contributions | |
joke | -0.010 |
play | -0.010 |
eat | -0.009 |
chat | -0.009 |
laugh | -0.009 |
Token | grass |
Token ID | 8701 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
joke | +0.013 |
play | +0.012 |
chat | +0.012 |
eat | +0.011 |
sip | +0.011 |
Neg logit contributions | |
uster | -0.015 |
bars | -0.014 |
rier | -0.014 |
hole | -0.014 |
dollars | -0.013 |
Token | me |
Token ID | 502 |
Feature activation | +6.98e-03 |
Pos logit contributions | |
joke | +0.013 |
play | +0.013 |
chat | +0.012 |
eat | +0.012 |
sip | +0.011 |
Neg logit contributions | |
uster | -0.020 |
bars | -0.018 |
rier | -0.018 |
dollars | -0.018 |
hole | -0.018 |
Token | adow |
Token ID | 4584 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
uster | +0.015 |
bars | +0.015 |
rier | +0.015 |
dollars | +0.014 |
hole | +0.014 |
Neg logit contributions | |
joke | -0.010 |
play | -0.010 |
chat | -0.009 |
eat | -0.009 |
laugh | -0.009 |
Token | full |
Token ID | 1336 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
joke | +0.059 |
play | +0.058 |
chat | +0.055 |
eat | +0.053 |
laugh | +0.050 |
Neg logit contributions | |
uster | -0.089 |
bars | -0.083 |
rier | -0.081 |
dollars | -0.081 |
hole | -0.080 |
Token | of |
Token ID | 286 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
uster | +0.126 |
bars | +0.114 |
isher | +0.109 |
hole | +0.109 |
rier | +0.108 |
Neg logit contributions | |
play | -0.190 |
joke | -0.190 |
chat | -0.180 |
eat | -0.180 |
drink | -0.175 |
Token | wild |
Token ID | 4295 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
uster | +0.209 |
rier | +0.196 |
bars | +0.196 |
dollars | +0.195 |
hole | +0.188 |
Neg logit contributions | |
joke | -0.142 |
play | -0.138 |
chat | -0.129 |
eat | -0.126 |
sip | -0.122 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
joke | +0.035 |
play | +0.034 |
chat | +0.032 |
eat | +0.031 |
sip | +0.031 |
Neg logit contributions | |
uster | -0.054 |
rier | -0.051 |
bars | -0.050 |
dollars | -0.050 |
hole | -0.049 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
joke | +0.609 |
play | +0.586 |
eat | +0.545 |
chat | +0.545 |
sip | +0.534 |
Neg logit contributions | |
uster | -0.664 |
bars | -0.633 |
rier | -0.622 |
hole | -0.606 |
dollars | -0.598 |
Token | . |
Token ID | 13 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
joke | +0.112 |
play | +0.108 |
chat | +0.103 |
eat | +0.098 |
sip | +0.096 |
Neg logit contributions | |
uster | -0.142 |
bars | -0.135 |
rier | -0.133 |
hole | -0.133 |
dollars | -0.132 |
Token | He |
Token ID | 679 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
joke | +0.013 |
play | +0.012 |
chat | +0.012 |
eat | +0.011 |
sip | +0.011 |
Neg logit contributions | |
uster | -0.017 |
bars | -0.016 |
rier | -0.016 |
dollars | -0.016 |
hole | -0.016 |
Token | spun |
Token ID | 26843 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
uster | +0.046 |
bars | +0.044 |
dollars | +0.043 |
hole | +0.042 |
rier | +0.042 |
Neg logit contributions | |
joke | -0.032 |
play | -0.031 |
eat | -0.028 |
chat | -0.028 |
sip | -0.027 |
Token | around |
Token ID | 1088 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
joke | +0.054 |
play | +0.052 |
eat | +0.048 |
chat | +0.048 |
sip | +0.045 |
Neg logit contributions | |
uster | -0.082 |
rier | -0.077 |
bars | -0.076 |
hole | -0.074 |
dollars | -0.073 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
play | +0.013 |
joke | +0.013 |
chat | +0.012 |
eat | +0.011 |
sip | +0.011 |
Neg logit contributions | |
uster | -0.020 |
bars | -0.019 |
rier | -0.018 |
dollars | -0.018 |
hole | -0.018 |
Token | L |
Token ID | 43 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
joke | +0.108 |
chat | +0.097 |
play | +0.096 |
eat | +0.095 |
sip | +0.092 |
Neg logit contributions | |
uster | -0.123 |
hole | -0.117 |
bars | -0.114 |
mith | -0.109 |
dollars | -0.106 |
Token | ily |
Token ID | 813 |
Feature activation | +3.42e-03 |
Pos logit contributions | |
uster | +0.032 |
rier | +0.031 |
bars | +0.030 |
dollars | +0.029 |
hole | +0.029 |
Neg logit contributions | |
joke | -0.033 |
play | -0.033 |
eat | -0.031 |
chat | -0.030 |
sip | -0.029 |
Token | loved |
Token ID | 6151 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
uster | +0.007 |
bars | +0.007 |
hole | +0.006 |
rier | +0.006 |
dollars | +0.006 |
Neg logit contributions | |
joke | -0.006 |
play | -0.005 |
chat | -0.005 |
eat | -0.005 |
sip | -0.005 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
sip | +0.012 |
joke | +0.012 |
| | +0.011 |
laugh | +0.011 |
chat | +0.011 |
Neg logit contributions | |
bars | -0.012 |
uster | -0.011 |
isher | -0.010 |
rier | -0.010 |
dollars | -0.010 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
joke | +0.062 |
play | +0.059 |
chat | +0.057 |
eat | +0.055 |
sip | +0.054 |
Neg logit contributions | |
uster | -0.069 |
bars | -0.066 |
rier | -0.065 |
hole | -0.063 |
dollars | -0.062 |
Token | owers |
Token ID | 3618 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
joke | +0.580 |
play | +0.555 |
chat | +0.525 |
eat | +0.524 |
sip | +0.504 |
Neg logit contributions | |
uster | -0.673 |
bars | -0.655 |
rier | -0.631 |
hole | -0.625 |
dollars | -0.620 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
joke | +0.110 |
play | +0.106 |
chat | +0.101 |
eat | +0.097 |
sip | +0.094 |
Neg logit contributions | |
uster | -0.149 |
bars | -0.142 |
rier | -0.140 |
dollars | -0.138 |
hole | -0.138 |
Token | She |
Token ID | 1375 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
joke | +0.016 |
play | +0.016 |
chat | +0.015 |
eat | +0.015 |
sip | +0.014 |
Neg logit contributions | |
uster | -0.032 |
bars | -0.030 |
rier | -0.030 |
dollars | -0.030 |
hole | -0.029 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
play | +0.034 |
joke | +0.032 |
chat | +0.030 |
eat | +0.029 |
dance | +0.027 |
Neg logit contributions | |
uster | -0.079 |
rier | -0.075 |
bars | -0.073 |
hole | -0.072 |
dollars | -0.072 |
Token | to |
Token ID | 284 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
joke | +0.040 |
play | +0.038 |
sip | +0.037 |
chat | +0.036 |
laugh | +0.035 |
Neg logit contributions | |
bars | -0.037 |
uster | -0.036 |
rier | -0.035 |
dollars | -0.034 |
hole | -0.033 |
Token | da |
Token ID | 12379 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
joke | +0.011 |
play | +0.010 |
chat | +0.010 |
eat | +0.009 |
sip | +0.009 |
Neg logit contributions | |
uster | -0.015 |
bars | -0.014 |
rier | -0.014 |
dollars | -0.014 |
hole | -0.014 |
Token | is |
Token ID | 271 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
joke | +0.081 |
play | +0.081 |
chat | +0.076 |
eat | +0.075 |
sip | +0.073 |
Neg logit contributions | |
uster | -0.048 |
rier | -0.044 |
bars | -0.044 |
dollars | -0.043 |
hole | -0.042 |
Token | ies |
Token ID | 444 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
uster | +0.110 |
bars | +0.103 |
rier | +0.098 |
hole | +0.098 |
isher | +0.095 |
Neg logit contributions | |
joke | -0.103 |
play | -0.101 |
chat | -0.097 |
eat | -0.096 |
laugh | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
joke | +0.143 |
play | +0.141 |
chat | +0.133 |
eat | +0.130 |
sip | +0.124 |
Neg logit contributions | |
uster | -0.185 |
bars | -0.173 |
rier | -0.170 |
dollars | -0.167 |
hole | -0.166 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
joke | +0.016 |
play | +0.016 |
chat | +0.015 |
eat | +0.014 |
sip | +0.014 |
Neg logit contributions | |
uster | -0.023 |
bars | -0.022 |
rier | -0.022 |
dollars | -0.021 |
hole | -0.021 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
joke | +0.044 |
play | +0.042 |
chat | +0.039 |
eat | +0.038 |
sip | +0.036 |
Neg logit contributions | |
uster | -0.077 |
bars | -0.074 |
rier | -0.073 |
dollars | -0.072 |
hole | -0.072 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
joke | +0.564 |
play | +0.545 |
chat | +0.507 |
eat | +0.499 |
sip | +0.485 |
Neg logit contributions | |
uster | -0.685 |
bars | -0.659 |
rier | -0.650 |
dollars | -0.638 |
hole | -0.637 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
joke | +0.112 |
play | +0.108 |
chat | +0.103 |
eat | +0.098 |
sip | +0.096 |
Neg logit contributions | |
uster | -0.133 |
bars | -0.127 |
rier | -0.125 |
hole | -0.125 |
dollars | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | -4.83e-03 |
Pos logit contributions | |
joke | +0.017 |
play | +0.017 |
chat | +0.016 |
eat | +0.015 |
sip | +0.015 |
Neg logit contributions | |
uster | -0.022 |
bars | -0.021 |
rier | -0.021 |
dollars | -0.021 |
hole | -0.020 |
Token | tul |
Token ID | 48373 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
joke | +0.007 |
play | +0.006 |
chat | +0.006 |
eat | +0.006 |
sip | +0.006 |
Neg logit contributions | |
uster | -0.010 |
bars | -0.010 |
rier | -0.010 |
dollars | -0.010 |
hole | -0.010 |
Token | ips |
Token ID | 2419 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
joke | +0.096 |
play | +0.094 |
chat | +0.090 |
eat | +0.088 |
sip | +0.085 |
Neg logit contributions | |
uster | -0.075 |
bars | -0.070 |
rier | -0.068 |
dollars | -0.067 |
hole | -0.066 |
Token | book |
Token ID | 1492 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
uster | +0.011 |
bars | +0.011 |
rier | +0.011 |
dollars | +0.010 |
hole | +0.010 |
Neg logit contributions | |
joke | -0.009 |
play | -0.009 |
chat | -0.009 |
eat | -0.009 |
sip | -0.008 |
Token | also |
Token ID | 635 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
joke | +0.008 |
play | +0.008 |
chat | +0.007 |
eat | +0.007 |
laugh | +0.007 |
Neg logit contributions | |
uster | -0.014 |
rier | -0.012 |
isher | -0.012 |
bars | -0.012 |
dollars | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | +3.93e-03 |
Pos logit contributions | |
joke | +0.014 |
play | +0.014 |
chat | +0.013 |
eat | +0.012 |
laugh | +0.012 |
Neg logit contributions | |
uster | -0.019 |
bars | -0.018 |
rier | -0.017 |
hole | -0.017 |
dollars | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
uster | +0.008 |
bars | +0.007 |
hole | +0.007 |
rier | +0.007 |
isher | +0.007 |
Neg logit contributions | |
joke | -0.007 |
play | -0.007 |
chat | -0.006 |
eat | -0.006 |
laugh | -0.006 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
joke | +0.032 |
play | +0.032 |
chat | +0.029 |
eat | +0.029 |
dance | +0.027 |
Neg logit contributions | |
uster | -0.043 |
rier | -0.038 |
bars | -0.038 |
isher | -0.037 |
hole | -0.037 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
play | +0.054 |
joke | +0.054 |
chat | +0.049 |
eat | +0.049 |
dance | +0.046 |
Neg logit contributions | |
uster | -0.080 |
bars | -0.072 |
rier | -0.072 |
dollars | -0.070 |
hole | -0.070 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
joke | +0.501 |
play | +0.493 |
chat | +0.462 |
eat | +0.447 |
sip | +0.426 |
Neg logit contributions | |
uster | -0.754 |
bars | -0.709 |
rier | -0.699 |
dollars | -0.687 |
hole | -0.685 |
Token | grow |
Token ID | 1663 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
joke | +0.095 |
play | +0.094 |
chat | +0.087 |
eat | +0.085 |
sip | +0.080 |
Neg logit contributions | |
uster | -0.158 |
bars | -0.149 |
rier | -0.147 |
dollars | -0.144 |
hole | -0.144 |
Token | very |
Token ID | 845 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
joke | +0.123 |
play | +0.122 |
chat | +0.115 |
eat | +0.112 |
sip | +0.107 |
Neg logit contributions | |
uster | -0.179 |
bars | -0.170 |
rier | -0.162 |
hole | -0.162 |
dollars | -0.162 |
Token | tall |
Token ID | 7331 |
Feature activation | +9.79e-03 |
Pos logit contributions | |
joke | +0.041 |
play | +0.040 |
chat | +0.038 |
eat | +0.036 |
sip | +0.035 |
Neg logit contributions | |
rier | -0.053 |
uster | -0.053 |
bars | -0.051 |
dollars | -0.051 |
hole | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
uster | +0.024 |
bars | +0.022 |
rier | +0.021 |
isher | +0.021 |
hole | +0.021 |
Neg logit contributions | |
play | -0.013 |
joke | -0.013 |
eat | -0.012 |
chat | -0.012 |
swim | -0.011 |
Token | nodded |
Token ID | 14464 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
uster | +0.013 |
bars | +0.012 |
hole | +0.012 |
dollars | +0.012 |
isher | +0.012 |
Neg logit contributions | |
joke | -0.012 |
play | -0.011 |
eat | -0.011 |
chat | -0.011 |
swamp | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
joke | +0.011 |
play | +0.011 |
chat | +0.010 |
eat | +0.010 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.017 |
bars | -0.016 |
rier | -0.016 |
dollars | -0.015 |
hole | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
play | +0.009 |
joke | +0.008 |
eat | +0.008 |
chat | +0.008 |
sip | +0.007 |
Neg logit contributions | |
uster | -0.011 |
dollars | -0.011 |
bars | -0.011 |
hole | -0.011 |
isher | -0.011 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
uster | +0.044 |
bars | +0.041 |
rier | +0.041 |
dollars | +0.040 |
hole | +0.040 |
Neg logit contributions | |
joke | -0.027 |
play | -0.026 |
chat | -0.024 |
eat | -0.024 |
sip | -0.022 |
Token | sun |
Token ID | 4252 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
joke | +0.030 |
play | +0.028 |
chat | +0.028 |
eat | +0.027 |
sip | +0.026 |
Neg logit contributions | |
uster | -0.033 |
bars | -0.033 |
dollars | -0.031 |
isher | -0.031 |
rier | -0.030 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
joke | +0.047 |
play | +0.044 |
chat | +0.044 |
eat | +0.043 |
sip | +0.042 |
Neg logit contributions | |
bars | -0.044 |
uster | -0.044 |
rier | -0.044 |
hole | -0.042 |
isher | -0.041 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
joke | +0.616 |
play | +0.592 |
chat | +0.561 |
eat | +0.555 |
laugh | +0.526 |
Neg logit contributions | |
uster | -0.653 |
bars | -0.612 |
rier | -0.593 |
hole | -0.592 |
dollars | -0.585 |
Token | too |
Token ID | 1165 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
joke | +0.118 |
chat | +0.112 |
play | +0.111 |
eat | +0.104 |
sip | +0.103 |
Neg logit contributions | |
uster | -0.114 |
hole | -0.111 |
dollars | -0.110 |
bars | -0.110 |
rier | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -4.59e-03 |
Pos logit contributions | |
play | +0.025 |
joke | +0.023 |
eat | +0.022 |
swim | +0.020 |
chat | +0.020 |
Neg logit contributions | |
uster | -0.065 |
bars | -0.063 |
isher | -0.063 |
rier | -0.061 |
dollars | -0.060 |
Token | He |
Token ID | 679 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
play | +0.007 |
joke | +0.007 |
eat | +0.006 |
chat | +0.006 |
sip | +0.006 |
Neg logit contributions | |
uster | -0.010 |
bars | -0.010 |
hole | -0.009 |
isher | -0.009 |
dollars | -0.009 |
Token | gave |
Token ID | 2921 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
uster | +0.044 |
bars | +0.042 |
rier | +0.041 |
dollars | +0.041 |
hole | +0.041 |
Neg logit contributions | |
joke | -0.029 |
play | -0.028 |
chat | -0.026 |
eat | -0.026 |
sip | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.10e-03 |
Pos logit contributions | |
joke | +0.024 |
play | +0.024 |
chat | +0.022 |
eat | +0.022 |
laugh | +0.021 |
Neg logit contributions | |
uster | -0.037 |
bars | -0.034 |
rier | -0.034 |
dollars | -0.033 |
isher | -0.033 |
Token | look |
Token ID | 804 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
bars | +0.002 |
hole | +0.002 |
uster | +0.002 |
rier | +0.002 |
dollars | +0.002 |
Neg logit contributions | |
joke | -0.001 |
chat | -0.001 |
play | -0.001 |
swamp | -0.001 |
eat | -0.001 |
Token | at |
Token ID | 379 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
joke | +0.020 |
play | +0.020 |
chat | +0.019 |
eat | +0.018 |
sip | +0.018 |
Neg logit contributions | |
uster | -0.028 |
bars | -0.027 |
rier | -0.026 |
hole | -0.026 |
dollars | -0.026 |
Token | their |
Token ID | 511 |
Feature activation | -7.51e-04 |
Pos logit contributions | |
joke | +0.062 |
play | +0.062 |
chat | +0.056 |
eat | +0.055 |
sip | +0.052 |
Neg logit contributions | |
uster | -0.123 |
bars | -0.115 |
rier | -0.114 |
dollars | -0.113 |
hole | -0.112 |
Token | snow |
Token ID | 6729 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
chat | +0.001 |
| | +0.001 |
joke | +0.001 |
eat | +0.001 |
play | +0.001 |
Neg logit contributions | |
rier | -0.001 |
bars | -0.001 |
dollars | -0.001 |
hole | -0.001 |
isher | -0.001 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
joke | +0.125 |
play | +0.124 |
chat | +0.122 |
eat | +0.118 |
sip | +0.117 |
Neg logit contributions | |
rier | -0.113 |
bars | -0.108 |
uster | -0.104 |
hole | -0.104 |
isher | -0.101 |
Token | akes |
Token ID | 1124 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
joke | +0.636 |
play | +0.622 |
chat | +0.601 |
eat | +0.586 |
sip | +0.571 |
Neg logit contributions | |
uster | -0.604 |
bars | -0.595 |
rier | -0.568 |
hole | -0.562 |
isher | -0.549 |
Token | . |
Token ID | 13 |
Feature activation | +3.40e-03 |
Pos logit contributions | |
joke | +0.101 |
play | +0.098 |
chat | +0.093 |
eat | +0.089 |
sip | +0.085 |
Neg logit contributions | |
uster | -0.138 |
bars | -0.133 |
rier | -0.132 |
hole | -0.129 |
dollars | -0.128 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
uster | +0.008 |
bars | +0.007 |
rier | +0.007 |
dollars | +0.007 |
hole | +0.007 |
Neg logit contributions | |
joke | -0.005 |
play | -0.005 |
chat | -0.005 |
eat | -0.004 |
laugh | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
joke | +0.017 |
play | +0.016 |
chat | +0.016 |
eat | +0.015 |
sip | +0.014 |
Neg logit contributions | |
uster | -0.029 |
bars | -0.028 |
hole | -0.027 |
rier | -0.026 |
dollars | -0.026 |
Token | S |
Token ID | 50 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
joke | +0.021 |
play | +0.021 |
chat | +0.020 |
eat | +0.019 |
laugh | +0.019 |
Neg logit contributions | |
uster | -0.020 |
bars | -0.019 |
rier | -0.018 |
dollars | -0.018 |
hole | -0.018 |
Token | chains |
Token ID | 14659 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
uster | +0.220 |
bars | +0.205 |
rier | +0.201 |
hole | +0.198 |
dollars | +0.196 |
Neg logit contributions | |
play | -0.145 |
joke | -0.141 |
chat | -0.130 |
eat | -0.127 |
swim | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | -5.06e-03 |
Pos logit contributions | |
play | +0.053 |
chat | +0.047 |
joke | +0.047 |
eat | +0.046 |
laugh | +0.044 |
Neg logit contributions | |
uster | -0.080 |
rier | -0.076 |
isher | -0.074 |
dollars | -0.073 |
bars | -0.072 |
Token | glitter |
Token ID | 31133 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
joke | +0.009 |
play | +0.009 |
chat | +0.008 |
eat | +0.008 |
laugh | +0.008 |
Neg logit contributions | |
uster | -0.010 |
rier | -0.010 |
bars | -0.010 |
hole | -0.009 |
isher | -0.009 |
Token | y |
Token ID | 88 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
uster | +0.164 |
bars | +0.150 |
rier | +0.148 |
dollars | +0.146 |
mith | +0.145 |
Neg logit contributions | |
play | -0.070 |
swim | -0.060 |
joke | -0.060 |
eat | -0.059 |
drink | -0.057 |
Token | snow |
Token ID | 6729 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
joke | +0.082 |
play | +0.080 |
chat | +0.076 |
eat | +0.073 |
sip | +0.070 |
Neg logit contributions | |
uster | -0.104 |
bars | -0.099 |
rier | -0.097 |
dollars | -0.097 |
hole | -0.096 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
joke | +0.099 |
play | +0.098 |
chat | +0.091 |
eat | +0.088 |
sip | +0.083 |
Neg logit contributions | |
uster | -0.164 |
bars | -0.155 |
rier | -0.151 |
dollars | -0.150 |
hole | -0.149 |
Token | akes |
Token ID | 1124 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
play | +0.508 |
joke | +0.506 |
chat | +0.473 |
eat | +0.460 |
sip | +0.438 |
Neg logit contributions | |
uster | -0.730 |
bars | -0.681 |
rier | -0.679 |
dollars | -0.670 |
hole | -0.663 |
Token | , |
Token ID | 11 |
Feature activation | -4.36e-03 |
Pos logit contributions | |
play | +0.098 |
joke | +0.096 |
eat | +0.091 |
chat | +0.089 |
swim | +0.085 |
Neg logit contributions | |
uster | -0.156 |
bars | -0.145 |
rier | -0.142 |
dollars | -0.140 |
isher | -0.140 |
Token | and |
Token ID | 290 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
play | +0.006 |
joke | +0.006 |
eat | +0.006 |
chat | +0.006 |
laugh | +0.006 |
Neg logit contributions | |
uster | -0.010 |
bars | -0.009 |
rier | -0.009 |
isher | -0.009 |
hole | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -6.51e-03 |
Pos logit contributions | |
joke | +0.003 |
play | +0.003 |
chat | +0.003 |
eat | +0.003 |
sip | +0.002 |
Neg logit contributions | |
uster | -0.004 |
bars | -0.004 |
rier | -0.004 |
dollars | -0.004 |
hole | -0.004 |
Token | picture |
Token ID | 4286 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
joke | +0.011 |
play | +0.010 |
chat | +0.010 |
eat | +0.010 |
sip | +0.009 |
Neg logit contributions | |
uster | -0.013 |
bars | -0.012 |
rier | -0.012 |
dollars | -0.012 |
hole | -0.012 |
Token | no |
Token ID | 645 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
uster | +0.001 |
hole | +0.001 |
bars | +0.001 |
isher | +0.001 |
rier | +0.001 |
Neg logit contributions | |
joke | -0.001 |
play | -0.001 |
eat | -0.001 |
chat | -0.001 |
swim | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -3.61e-03 |
Pos logit contributions | |
uster | +0.367 |
bars | +0.345 |
rier | +0.341 |
dollars | +0.333 |
hole | +0.332 |
Neg logit contributions | |
joke | -0.256 |
play | -0.253 |
chat | -0.234 |
eat | -0.230 |
sip | -0.219 |
Token | He |
Token ID | 679 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
joke | +0.005 |
play | +0.005 |
chat | +0.005 |
eat | +0.005 |
sip | +0.005 |
Neg logit contributions | |
uster | -0.008 |
bars | -0.008 |
rier | -0.007 |
hole | -0.007 |
dollars | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
uster | +0.054 |
rier | +0.052 |
bars | +0.051 |
hole | +0.049 |
dollars | +0.048 |
Neg logit contributions | |
joke | -0.029 |
play | -0.029 |
chat | -0.027 |
eat | -0.026 |
swim | -0.025 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
uster | +0.002 |
hole | +0.002 |
bars | +0.002 |
isher | +0.002 |
rier | +0.002 |
Neg logit contributions | |
joke | -0.002 |
play | -0.002 |
eat | -0.002 |
chat | -0.002 |
swim | -0.002 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
joke | +0.048 |
play | +0.048 |
chat | +0.044 |
eat | +0.043 |
sip | +0.041 |
Neg logit contributions | |
uster | -0.073 |
bars | -0.069 |
rier | -0.068 |
dollars | -0.067 |
hole | -0.066 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
joke | +0.504 |
play | +0.498 |
chat | +0.468 |
eat | +0.452 |
sip | +0.434 |
Neg logit contributions | |
uster | -0.748 |
bars | -0.704 |
rier | -0.694 |
dollars | -0.682 |
hole | -0.679 |
Token | were |
Token ID | 547 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
joke | +0.093 |
play | +0.092 |
chat | +0.085 |
eat | +0.083 |
sip | +0.078 |
Neg logit contributions | |
uster | -0.156 |
bars | -0.147 |
rier | -0.145 |
dollars | -0.142 |
hole | -0.142 |
Token | not |
Token ID | 407 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
joke | +0.019 |
play | +0.019 |
eat | +0.017 |
chat | +0.017 |
swim | +0.016 |
Neg logit contributions | |
uster | -0.032 |
bars | -0.031 |
hole | -0.029 |
isher | -0.029 |
rier | -0.028 |
Token | for |
Token ID | 329 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
uster | +0.087 |
bars | +0.084 |
hole | +0.078 |
rier | +0.077 |
isher | +0.077 |
Neg logit contributions | |
joke | -0.057 |
play | -0.057 |
eat | -0.054 |
chat | -0.052 |
swim | -0.050 |
Token | picking |
Token ID | 10868 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
uster | +0.078 |
bars | +0.074 |
rier | +0.074 |
dollars | +0.073 |
hole | +0.072 |
Neg logit contributions | |
joke | -0.046 |
play | -0.044 |
chat | -0.041 |
eat | -0.039 |
sip | -0.038 |
Token | window |
Token ID | 4324 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
uster | +0.014 |
rier | +0.013 |
bars | +0.013 |
dollars | +0.013 |
hole | +0.012 |
Neg logit contributions | |
joke | -0.012 |
play | -0.012 |
chat | -0.011 |
eat | -0.011 |
sip | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
uster | +0.199 |
bars | +0.184 |
rier | +0.181 |
dollars | +0.180 |
hole | +0.178 |
Neg logit contributions | |
joke | -0.138 |
play | -0.137 |
chat | -0.128 |
eat | -0.124 |
laugh | -0.119 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
joke | +0.005 |
play | +0.004 |
chat | +0.004 |
eat | +0.004 |
sip | +0.004 |
Neg logit contributions | |
uster | -0.006 |
bars | -0.005 |
hole | -0.005 |
rier | -0.005 |
dollars | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +7.78e-03 |
Pos logit contributions | |
uster | +0.078 |
bars | +0.074 |
rier | +0.073 |
dollars | +0.072 |
hole | +0.071 |
Neg logit contributions | |
joke | -0.049 |
play | -0.048 |
chat | -0.045 |
eat | -0.044 |
sip | -0.042 |
Token | snow |
Token ID | 6729 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
uster | +0.014 |
rier | +0.014 |
bars | +0.014 |
hole | +0.013 |
dollars | +0.013 |
Neg logit contributions | |
joke | -0.013 |
play | -0.013 |
chat | -0.013 |
eat | -0.012 |
sip | -0.012 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
joke | +0.146 |
play | +0.145 |
chat | +0.140 |
eat | +0.135 |
sip | +0.133 |
Neg logit contributions | |
rier | -0.102 |
bars | -0.099 |
uster | -0.099 |
hole | -0.094 |
dollars | -0.090 |
Token | akes |
Token ID | 1124 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
joke | +0.647 |
play | +0.631 |
chat | +0.606 |
eat | +0.590 |
sip | +0.578 |
Neg logit contributions | |
uster | -0.597 |
bars | -0.582 |
rier | -0.567 |
hole | -0.554 |
isher | -0.543 |
Token | falling |
Token ID | 7463 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
joke | +0.103 |
play | +0.099 |
chat | +0.096 |
eat | +0.089 |
sip | +0.086 |
Neg logit contributions | |
uster | -0.135 |
bars | -0.133 |
rier | -0.131 |
hole | -0.128 |
dollars | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-03 |
Pos logit contributions | |
uster | +0.036 |
bars | +0.034 |
dollars | +0.034 |
rier | +0.033 |
hole | +0.033 |
Neg logit contributions | |
play | -0.020 |
joke | -0.020 |
chat | -0.018 |
eat | -0.018 |
sip | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
joke | +0.002 |
play | +0.002 |
chat | +0.002 |
eat | +0.002 |
laugh | +0.001 |
Neg logit contributions | |
uster | -0.002 |
bars | -0.002 |
rier | -0.002 |
hole | -0.002 |
dollars | -0.002 |
Token | thought |
Token ID | 1807 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
joke | +0.032 |
play | +0.031 |
chat | +0.029 |
eat | +0.028 |
sip | +0.027 |
Neg logit contributions | |
uster | -0.050 |
bars | -0.048 |
rier | -0.047 |
dollars | -0.046 |
hole | -0.046 |
Token | angry |
Token ID | 7954 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
joke | +0.041 |
play | +0.040 |
chat | +0.038 |
eat | +0.037 |
sip | +0.036 |
Neg logit contributions | |
uster | -0.043 |
rier | -0.043 |
dollars | -0.041 |
hole | -0.039 |
bars | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e-03 |
Pos logit contributions | |
play | +0.142 |
joke | +0.140 |
eat | +0.123 |
chat | +0.117 |
swim | +0.117 |
Neg logit contributions | |
uster | -0.301 |
bars | -0.283 |
isher | -0.274 |
rier | -0.273 |
dollars | -0.270 |
Token | She |
Token ID | 1375 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
joke | +0.002 |
play | +0.002 |
chat | +0.002 |
eat | +0.002 |
laugh | +0.002 |
Neg logit contributions | |
uster | -0.003 |
bars | -0.003 |
rier | -0.003 |
hole | -0.003 |
dollars | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | +2.23e-03 |
Pos logit contributions | |
joke | +0.035 |
play | +0.034 |
chat | +0.032 |
eat | +0.031 |
sip | +0.030 |
Neg logit contributions | |
uster | -0.047 |
bars | -0.045 |
dollars | -0.044 |
rier | -0.043 |
hole | -0.043 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
uster | +0.005 |
bars | +0.004 |
rier | +0.004 |
dollars | +0.004 |
hole | +0.004 |
Neg logit contributions | |
joke | -0.004 |
play | -0.004 |
chat | -0.003 |
eat | -0.003 |
sip | -0.003 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
joke | +0.045 |
play | +0.044 |
chat | +0.041 |
eat | +0.040 |
sip | +0.039 |
Neg logit contributions | |
uster | -0.065 |
bars | -0.062 |
rier | -0.061 |
hole | -0.060 |
dollars | -0.059 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
joke | +0.521 |
play | +0.511 |
chat | +0.480 |
eat | +0.466 |
sip | +0.445 |
Neg logit contributions | |
uster | -0.735 |
bars | -0.694 |
rier | -0.683 |
dollars | -0.671 |
hole | -0.670 |
Token | were |
Token ID | 547 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
joke | +0.092 |
play | +0.090 |
chat | +0.084 |
eat | +0.080 |
sip | +0.077 |
Neg logit contributions | |
uster | -0.151 |
bars | -0.144 |
rier | -0.142 |
dollars | -0.141 |
hole | -0.140 |
Token | for |
Token ID | 329 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
joke | +0.018 |
play | +0.018 |
chat | +0.017 |
eat | +0.017 |
sip | +0.015 |
Neg logit contributions | |
uster | -0.030 |
bars | -0.029 |
hole | -0.028 |
rier | -0.027 |
dollars | -0.027 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
uster | +0.076 |
rier | +0.072 |
dollars | +0.071 |
bars | +0.071 |
hole | +0.069 |
Neg logit contributions | |
joke | -0.049 |
play | -0.046 |
chat | -0.044 |
sip | -0.041 |
eat | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -5.25e-04 |
Pos logit contributions | |
joke | +0.017 |
play | +0.016 |
chat | +0.016 |
eat | +0.015 |
sip | +0.014 |
Neg logit contributions | |
uster | -0.021 |
bars | -0.021 |
dollars | -0.021 |
rier | -0.020 |
hole | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
play | +0.023 |
joke | +0.021 |
eat | +0.020 |
chat | +0.020 |
walk | +0.018 |
Neg logit contributions | |
uster | -0.049 |
bars | -0.047 |
rier | -0.046 |
dollars | -0.046 |
hole | -0.045 |
Token | look |
Token ID | 804 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
joke | +0.033 |
chat | +0.029 |
play | +0.028 |
sip | +0.027 |
laugh | +0.026 |
Neg logit contributions | |
uster | -0.075 |
bars | -0.070 |
hole | -0.070 |
rier | -0.069 |
dollars | -0.068 |
Token | in |
Token ID | 287 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
play | +0.019 |
joke | +0.017 |
eat | +0.017 |
chat | +0.016 |
swim | +0.016 |
Neg logit contributions | |
uster | -0.028 |
bars | -0.027 |
rier | -0.026 |
hole | -0.025 |
isher | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
play | +0.046 |
enjoy | +0.037 |
eat | +0.037 |
catch | +0.035 |
walks | +0.034 |
Neg logit contributions | |
uster | -0.113 |
bars | -0.112 |
rier | -0.107 |
isher | -0.100 |
one | -0.098 |
Token | wild |
Token ID | 4295 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
uster | +0.013 |
bars | +0.013 |
rier | +0.012 |
hole | +0.012 |
dollars | +0.012 |
Neg logit contributions | |
play | -0.010 |
joke | -0.010 |
chat | -0.009 |
eat | -0.009 |
sip | -0.009 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
play | +0.034 |
joke | +0.031 |
eat | +0.030 |
chat | +0.030 |
drink | +0.029 |
Neg logit contributions | |
uster | -0.065 |
bars | -0.061 |
rier | -0.060 |
dollars | -0.057 |
hole | -0.057 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
joke | +0.553 |
play | +0.539 |
chat | +0.505 |
eat | +0.493 |
laugh | +0.479 |
Neg logit contributions | |
uster | -0.705 |
bars | -0.673 |
rier | -0.659 |
hole | -0.651 |
dollars | -0.649 |
Token | ." |
Token ID | 526 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
play | +0.103 |
eat | +0.094 |
joke | +0.093 |
chat | +0.089 |
swim | +0.088 |
Neg logit contributions | |
uster | -0.147 |
bars | -0.137 |
rier | -0.133 |
isher | -0.131 |
dollars | -0.126 |
Token |
|
Token ID | 198 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
uster | +0.029 |
bars | +0.027 |
hole | +0.026 |
rier | +0.025 |
dollars | +0.025 |
Neg logit contributions | |
joke | -0.023 |
play | -0.020 |
chat | -0.020 |
eat | -0.019 |
laugh | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
joke | +0.022 |
play | +0.020 |
chat | +0.020 |
eat | +0.019 |
sip | +0.019 |
Neg logit contributions | |
uster | -0.034 |
bars | -0.031 |
hole | -0.031 |
rier | -0.030 |
dollars | -0.030 |
Token | They |
Token ID | 2990 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
joke | +0.023 |
play | +0.022 |
chat | +0.021 |
eat | +0.021 |
sip | +0.020 |
Neg logit contributions | |
uster | -0.030 |
bars | -0.027 |
dollars | -0.027 |
hole | -0.026 |
rier | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -6.54e-03 |
Pos logit contributions | |
joke | +0.032 |
play | +0.032 |
chat | +0.029 |
eat | +0.029 |
sip | +0.027 |
Neg logit contributions | |
uster | -0.054 |
bars | -0.051 |
rier | -0.050 |
hole | -0.049 |
dollars | -0.049 |
Token | delicious |
Token ID | 12625 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
joke | +0.010 |
play | +0.010 |
chat | +0.010 |
eat | +0.009 |
sip | +0.009 |
Neg logit contributions | |
uster | -0.013 |
rier | -0.012 |
dollars | -0.012 |
bars | -0.012 |
hole | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -7.78e-03 |
Pos logit contributions | |
joke | +0.070 |
play | +0.070 |
chat | +0.065 |
| | +0.060 |
laugh | +0.060 |
Neg logit contributions | |
uster | -0.127 |
dollars | -0.124 |
rier | -0.123 |
isher | -0.118 |
bars | -0.116 |
Token | mild |
Token ID | 11607 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
joke | +0.012 |
play | +0.011 |
chat | +0.011 |
eat | +0.010 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.017 |
bars | -0.016 |
rier | -0.016 |
hole | -0.016 |
dollars | -0.016 |
Token | - |
Token ID | 12 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
uster | +0.048 |
bars | +0.045 |
rier | +0.044 |
dollars | +0.044 |
hole | +0.044 |
Neg logit contributions | |
joke | -0.028 |
play | -0.027 |
chat | -0.025 |
eat | -0.024 |
sip | -0.023 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
uster | +0.035 |
bars | +0.033 |
rier | +0.033 |
dollars | +0.032 |
hole | +0.032 |
Neg logit contributions | |
joke | -0.031 |
play | -0.030 |
chat | -0.029 |
eat | -0.028 |
sip | -0.027 |
Token | av |
Token ID | 615 |
Feature activation | -9.11e-03 |
Pos logit contributions | |
joke | +0.543 |
play | +0.535 |
chat | +0.505 |
eat | +0.490 |
sip | +0.469 |
Neg logit contributions | |
uster | -0.707 |
bars | -0.664 |
rier | -0.653 |
dollars | -0.642 |
hole | -0.639 |
Token | oured |
Token ID | 8167 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
joke | +0.017 |
play | +0.017 |
chat | +0.016 |
eat | +0.016 |
sip | +0.015 |
Neg logit contributions | |
uster | -0.017 |
bars | -0.016 |
rier | -0.015 |
hole | -0.015 |
dollars | -0.015 |
Token | cake |
Token ID | 12187 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
uster | +0.164 |
bars | +0.155 |
rier | +0.152 |
hole | +0.150 |
dollars | +0.149 |
Neg logit contributions | |
joke | -0.100 |
play | -0.098 |
chat | -0.091 |
eat | -0.089 |
sip | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -7.14e-03 |
Pos logit contributions | |
joke | +0.047 |
play | +0.046 |
chat | +0.043 |
eat | +0.042 |
sip | +0.040 |
Neg logit contributions | |
uster | -0.063 |
bars | -0.060 |
rier | -0.059 |
dollars | -0.058 |
hole | -0.057 |
Token | The |
Token ID | 383 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
play | +0.009 |
joke | +0.009 |
chat | +0.008 |
eat | +0.008 |
sip | +0.007 |
Neg logit contributions | |
uster | -0.017 |
rier | -0.017 |
bars | -0.017 |
isher | -0.016 |
dollars | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
joke | +0.024 |
play | +0.024 |
chat | +0.023 |
eat | +0.023 |
sip | +0.022 |
Neg logit contributions | |
uster | -0.016 |
bars | -0.014 |
rier | -0.014 |
dollars | -0.014 |
hole | -0.014 |
Token | Hello |
Token ID | 15496 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
uster | +0.148 |
bars | +0.141 |
rier | +0.137 |
dollars | +0.136 |
hole | +0.135 |
Neg logit contributions | |
joke | -0.105 |
play | -0.102 |
chat | -0.095 |
eat | -0.093 |
laugh | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-03 |
Pos logit contributions | |
play | +0.163 |
joke | +0.162 |
eat | +0.147 |
chat | +0.147 |
swim | +0.141 |
Neg logit contributions | |
uster | -0.246 |
bars | -0.233 |
rier | -0.225 |
hole | -0.219 |
isher | -0.217 |
Token | my |
Token ID | 616 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
uster | +0.003 |
bars | +0.003 |
rier | +0.003 |
hole | +0.003 |
isher | +0.003 |
Neg logit contributions | |
joke | -0.002 |
play | -0.002 |
eat | -0.002 |
laugh | -0.002 |
chat | -0.002 |
Token | snow |
Token ID | 6729 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
uster | +0.180 |
bars | +0.168 |
rier | +0.166 |
dollars | +0.163 |
hole | +0.162 |
Neg logit contributions | |
joke | -0.155 |
play | -0.152 |
chat | -0.144 |
eat | -0.140 |
sip | -0.135 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
joke | +0.151 |
play | +0.150 |
chat | +0.145 |
eat | +0.142 |
sip | +0.139 |
Neg logit contributions | |
uster | -0.079 |
bars | -0.073 |
rier | -0.073 |
dollars | -0.069 |
hole | -0.069 |
Token | akes |
Token ID | 1124 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
joke | +0.613 |
play | +0.604 |
chat | +0.573 |
eat | +0.561 |
sip | +0.541 |
Neg logit contributions | |
uster | -0.634 |
bars | -0.597 |
rier | -0.587 |
hole | -0.576 |
dollars | -0.574 |
Token | ! |
Token ID | 0 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
joke | +0.115 |
play | +0.113 |
chat | +0.107 |
eat | +0.104 |
sip | +0.101 |
Neg logit contributions | |
uster | -0.122 |
bars | -0.115 |
rier | -0.113 |
dollars | -0.111 |
hole | -0.111 |
Token | You |
Token ID | 921 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
uster | +0.040 |
bars | +0.037 |
rier | +0.037 |
hole | +0.036 |
dollars | +0.036 |
Neg logit contributions | |
play | -0.043 |
joke | -0.043 |
eat | -0.040 |
chat | -0.039 |
sip | -0.038 |
Token | look |
Token ID | 804 |
Feature activation | -8.89e-03 |
Pos logit contributions | |
joke | +0.020 |
play | +0.019 |
chat | +0.018 |
eat | +0.017 |
sip | +0.016 |
Neg logit contributions | |
uster | -0.032 |
bars | -0.030 |
dollars | -0.029 |
rier | -0.029 |
hole | -0.029 |
Token | very |
Token ID | 845 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
joke | +0.014 |
play | +0.013 |
chat | +0.013 |
eat | +0.012 |
sip | +0.012 |
Neg logit contributions | |
uster | -0.018 |
rier | -0.017 |
dollars | -0.017 |
hole | -0.017 |
bars | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +9.06e-03 |
Pos logit contributions | |
joke | +0.003 |
play | +0.003 |
chat | +0.003 |
eat | +0.003 |
sip | +0.003 |
Neg logit contributions | |
uster | -0.004 |
bars | -0.004 |
rier | -0.004 |
dollars | -0.004 |
hole | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
uster | +0.015 |
rier | +0.014 |
bars | +0.014 |
dollars | +0.014 |
hole | +0.014 |
Neg logit contributions | |
joke | -0.017 |
play | -0.017 |
chat | -0.016 |
eat | -0.016 |
sip | -0.016 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
uster | +0.035 |
bars | +0.032 |
rier | +0.031 |
dollars | +0.031 |
hole | +0.031 |
Neg logit contributions | |
play | -0.041 |
joke | -0.040 |
chat | -0.038 |
eat | -0.038 |
sip | -0.036 |
Token | collected |
Token ID | 7723 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
joke | +0.038 |
play | +0.037 |
chat | +0.034 |
eat | +0.033 |
sip | +0.032 |
Neg logit contributions | |
uster | -0.064 |
bars | -0.061 |
rier | -0.060 |
dollars | -0.059 |
hole | -0.059 |
Token | snow |
Token ID | 6729 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
uster | +0.186 |
bars | +0.174 |
hole | +0.169 |
rier | +0.164 |
isher | +0.162 |
Neg logit contributions | |
play | -0.082 |
joke | -0.078 |
eat | -0.075 |
chat | -0.074 |
sip | -0.069 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
joke | +0.090 |
play | +0.087 |
chat | +0.081 |
eat | +0.078 |
sip | +0.076 |
Neg logit contributions | |
uster | -0.154 |
bars | -0.148 |
rier | -0.148 |
dollars | -0.143 |
hole | -0.143 |
Token | akes |
Token ID | 1124 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
joke | +0.551 |
play | +0.538 |
chat | +0.506 |
eat | +0.493 |
sip | +0.473 |
Neg logit contributions | |
uster | -0.703 |
bars | -0.665 |
rier | -0.652 |
dollars | -0.643 |
hole | -0.639 |
Token | . |
Token ID | 13 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
joke | +0.093 |
play | +0.093 |
chat | +0.086 |
eat | +0.084 |
sip | +0.080 |
Neg logit contributions | |
uster | -0.140 |
bars | -0.131 |
rier | -0.129 |
dollars | -0.127 |
hole | -0.126 |
Token | She |
Token ID | 1375 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
play | +0.004 |
joke | +0.004 |
chat | +0.004 |
eat | +0.004 |
sip | +0.003 |
Neg logit contributions | |
uster | -0.007 |
bars | -0.007 |
rier | -0.007 |
dollars | -0.007 |
hole | -0.007 |
Token | would |
Token ID | 561 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
joke | +0.029 |
play | +0.028 |
chat | +0.026 |
eat | +0.025 |
sip | +0.025 |
Neg logit contributions | |
uster | -0.049 |
bars | -0.048 |
dollars | -0.046 |
hole | -0.046 |
rier | -0.045 |
Token | catch |
Token ID | 4929 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
uster | +0.075 |
bars | +0.073 |
rier | +0.071 |
dollars | +0.071 |
hole | +0.070 |
Neg logit contributions | |
joke | -0.030 |
play | -0.028 |
chat | -0.026 |
sip | -0.024 |
eat | -0.023 |
Token | me |
Token ID | 502 |
Feature activation | +7.89e-03 |
Pos logit contributions | |
joke | +0.012 |
play | +0.011 |
chat | +0.011 |
eat | +0.011 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.018 |
bars | -0.017 |
dollars | -0.017 |
rier | -0.017 |
hole | -0.017 |
Token | adow |
Token ID | 4584 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
uster | +0.019 |
rier | +0.018 |
bars | +0.018 |
dollars | +0.017 |
isher | +0.017 |
Neg logit contributions | |
play | -0.010 |
joke | -0.010 |
chat | -0.009 |
eat | -0.009 |
laugh | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -7.98e-03 |
Pos logit contributions | |
play | +0.048 |
joke | +0.048 |
chat | +0.045 |
eat | +0.043 |
laugh | +0.041 |
Neg logit contributions | |
uster | -0.082 |
bars | -0.077 |
dollars | -0.075 |
rier | -0.075 |
isher | -0.074 |
Token | picked |
Token ID | 6497 |
Feature activation | -3.65e-03 |
Pos logit contributions | |
joke | +0.011 |
play | +0.010 |
sip | +0.010 |
chat | +0.010 |
eat | +0.009 |
Neg logit contributions | |
uster | -0.016 |
bars | -0.016 |
hole | -0.015 |
rier | -0.014 |
dollars | -0.014 |
Token | wild |
Token ID | 4295 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
joke | +0.006 |
play | +0.005 |
chat | +0.005 |
eat | +0.005 |
sip | +0.005 |
Neg logit contributions | |
rier | -0.007 |
uster | -0.007 |
dollars | -0.007 |
bars | -0.007 |
hole | -0.007 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
joke | +0.031 |
sip | +0.029 |
chat | +0.029 |
play | +0.029 |
eat | +0.028 |
Neg logit contributions | |
uster | -0.043 |
rier | -0.042 |
bars | -0.042 |
dollars | -0.041 |
isher | -0.041 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
joke | +0.616 |
play | +0.587 |
chat | +0.558 |
eat | +0.558 |
sip | +0.548 |
Neg logit contributions | |
uster | -0.631 |
bars | -0.624 |
hole | -0.597 |
rier | -0.592 |
isher | -0.579 |
Token | . |
Token ID | 13 |
Feature activation | -9.24e-03 |
Pos logit contributions | |
joke | +0.114 |
play | +0.105 |
chat | +0.104 |
eat | +0.097 |
sip | +0.096 |
Neg logit contributions | |
uster | -0.126 |
bars | -0.122 |
rier | -0.121 |
hole | -0.121 |
dollars | -0.120 |
Token | Later |
Token ID | 11450 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
joke | +0.012 |
play | +0.012 |
chat | +0.011 |
eat | +0.011 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.022 |
bars | -0.021 |
rier | -0.020 |
dollars | -0.020 |
hole | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -9.54e-03 |
Pos logit contributions | |
play | +0.067 |
joke | +0.066 |
chat | +0.062 |
eat | +0.060 |
swim | +0.057 |
Neg logit contributions | |
uster | -0.098 |
bars | -0.092 |
rier | -0.091 |
dollars | -0.089 |
hole | -0.089 |
Token | they |
Token ID | 484 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
joke | +0.015 |
play | +0.014 |
chat | +0.014 |
eat | +0.014 |
sip | +0.013 |
Neg logit contributions | |
uster | -0.019 |
rier | -0.018 |
bars | -0.018 |
hole | -0.017 |
dollars | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
uster | +0.187 |
rier | +0.183 |
bars | +0.178 |
dollars | +0.176 |
hole | +0.173 |
Neg logit contributions | |
joke | -0.159 |
play | -0.152 |
chat | -0.149 |
eat | -0.140 |
laugh | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e-04 |
Pos logit contributions | |
uster | +0.023 |
rier | +0.022 |
bars | +0.022 |
dollars | +0.022 |
hole | +0.022 |
Neg logit contributions | |
joke | -0.017 |
play | -0.017 |
chat | -0.016 |
eat | -0.015 |
sip | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
play | +0.000 |
joke | +0.000 |
eat | +0.000 |
chat | +0.000 |
sip | +0.000 |
Neg logit contributions | |
uster | -0.001 |
bars | -0.001 |
hole | -0.001 |
rier | -0.001 |
dollars | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | +3.63e-03 |
Pos logit contributions | |
uster | +0.046 |
bars | +0.044 |
rier | +0.043 |
dollars | +0.042 |
hole | +0.042 |
Neg logit contributions | |
joke | -0.036 |
play | -0.035 |
chat | -0.033 |
eat | -0.032 |
sip | -0.031 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
uster | +0.008 |
bars | +0.008 |
hole | +0.008 |
rier | +0.008 |
dollars | +0.008 |
Neg logit contributions | |
joke | -0.005 |
play | -0.005 |
chat | -0.005 |
eat | -0.005 |
swim | -0.004 |
Token | fl |
Token ID | 2704 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
joke | +0.051 |
play | +0.049 |
chat | +0.047 |
eat | +0.046 |
sip | +0.044 |
Neg logit contributions | |
uster | -0.060 |
bars | -0.057 |
rier | -0.056 |
hole | -0.055 |
dollars | -0.054 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
joke | +0.569 |
play | +0.551 |
chat | +0.517 |
eat | +0.509 |
laugh | +0.487 |
Neg logit contributions | |
uster | -0.683 |
bars | -0.649 |
rier | -0.641 |
dollars | -0.629 |
hole | -0.628 |
Token | were |
Token ID | 547 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
joke | +0.097 |
play | +0.095 |
chat | +0.089 |
eat | +0.086 |
sip | +0.082 |
Neg logit contributions | |
uster | -0.148 |
bars | -0.141 |
rier | -0.139 |
dollars | -0.137 |
hole | -0.137 |
Token | easy |
Token ID | 2562 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
joke | +0.019 |
play | +0.019 |
eat | +0.017 |
chat | +0.017 |
swim | +0.016 |
Neg logit contributions | |
uster | -0.034 |
bars | -0.032 |
hole | -0.031 |
isher | -0.030 |
rier | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
uster | +0.145 |
bars | +0.136 |
rier | +0.133 |
isher | +0.128 |
hole | +0.128 |
Neg logit contributions | |
play | -0.079 |
joke | -0.078 |
eat | -0.071 |
chat | -0.071 |
swim | -0.065 |
Token | grow |
Token ID | 1663 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
joke | +0.039 |
chat | +0.035 |
| | +0.035 |
jokes | +0.033 |
play | +0.033 |
Neg logit contributions | |
uster | -0.070 |
rier | -0.069 |
hole | -0.069 |
dollars | -0.067 |
bars | -0.066 |
Token | handed |
Token ID | 10158 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
play | +0.025 |
joke | +0.025 |
chat | +0.024 |
eat | +0.022 |
walk | +0.021 |
Neg logit contributions | |
uster | -0.045 |
rier | -0.043 |
bars | -0.042 |
hole | -0.041 |
dollars | -0.040 |
Token | him |
Token ID | 683 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
uster | +0.307 |
rier | +0.297 |
dollars | +0.293 |
bars | +0.292 |
hole | +0.285 |
Neg logit contributions | |
play | -0.116 |
eat | -0.096 |
chat | -0.093 |
joke | -0.093 |
catch | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | -5.37e-03 |
Pos logit contributions | |
uster | +0.069 |
bars | +0.065 |
rier | +0.064 |
dollars | +0.063 |
hole | +0.063 |
Neg logit contributions | |
joke | -0.038 |
play | -0.037 |
chat | -0.034 |
eat | -0.033 |
sip | -0.031 |
Token | tiny |
Token ID | 7009 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
joke | +0.011 |
play | +0.011 |
eat | +0.011 |
chat | +0.011 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.009 |
bars | -0.008 |
rier | -0.008 |
isher | -0.008 |
dollars | -0.008 |
Token | golden |
Token ID | 10861 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
uster | +0.057 |
bars | +0.055 |
rier | +0.052 |
isher | +0.050 |
mith | +0.049 |
Neg logit contributions | |
play | -0.052 |
joke | -0.052 |
eat | -0.049 |
chat | -0.048 |
sip | -0.048 |
Token | key |
Token ID | 1994 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
uster | +0.211 |
bars | +0.202 |
rier | +0.178 |
isher | +0.176 |
dollars | +0.176 |
Neg logit contributions | |
play | -0.215 |
joke | -0.214 |
eat | -0.203 |
chat | -0.199 |
drink | -0.197 |
Token | and |
Token ID | 290 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
uster | +0.625 |
rier | +0.585 |
isher | +0.583 |
ubby | +0.579 |
chie | +0.559 |
Neg logit contributions | |
play | -0.186 |
eat | -0.151 |
walk | -0.143 |
swim | -0.123 |
laugh | -0.118 |
Token | asked |
Token ID | 1965 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
uster | +0.009 |
rier | +0.009 |
bars | +0.008 |
ubby | +0.008 |
isher | +0.008 |
Neg logit contributions | |
play | -0.005 |
eat | -0.004 |
chat | -0.004 |
joke | -0.004 |
walk | -0.004 |
Token | him |
Token ID | 683 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
uster | +0.209 |
bars | +0.198 |
hole | +0.196 |
rier | +0.193 |
dollars | +0.193 |
Neg logit contributions | |
play | -0.071 |
joke | -0.067 |
eat | -0.060 |
chat | -0.058 |
swim | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
uster | +0.060 |
bars | +0.057 |
rier | +0.056 |
dollars | +0.056 |
hole | +0.055 |
Neg logit contributions | |
joke | -0.048 |
play | -0.047 |
chat | -0.045 |
eat | -0.043 |
sip | -0.042 |
Token | be |
Token ID | 307 |
Feature activation | -8.89e-03 |
Pos logit contributions | |
play | +0.035 |
eat | +0.031 |
joke | +0.030 |
walk | +0.029 |
chat | +0.029 |
Neg logit contributions | |
uster | -0.069 |
rier | -0.065 |
dollars | -0.064 |
bars | -0.064 |
isher | -0.062 |
Token | man |
Token ID | 582 |
Feature activation | -5.79e-03 |
Pos logit contributions | |
uster | +0.017 |
bars | +0.016 |
rier | +0.015 |
dollars | +0.015 |
hole | +0.015 |
Neg logit contributions | |
joke | -0.015 |
play | -0.015 |
chat | -0.014 |
eat | -0.014 |
sip | -0.013 |
Token | went |
Token ID | 1816 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
joke | +0.008 |
play | +0.008 |
chat | +0.007 |
eat | +0.007 |
swim | +0.007 |
Neg logit contributions | |
uster | -0.014 |
bars | -0.013 |
rier | -0.013 |
dollars | -0.012 |
hole | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
joke | +0.080 |
play | +0.076 |
chat | +0.073 |
eat | +0.070 |
sip | +0.068 |
Neg logit contributions | |
uster | -0.111 |
bars | -0.104 |
rier | -0.102 |
dollars | -0.100 |
hole | -0.100 |
Token | check |
Token ID | 2198 |
Feature activation | +9.12e-02 |
Pos logit contributions | |
joke | +0.050 |
chat | +0.045 |
play | +0.043 |
sip | +0.043 |
jokes | +0.041 |
Neg logit contributions | |
uster | -0.066 |
hole | -0.060 |
bars | -0.060 |
rier | -0.059 |
mith | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | +7.93e-03 |
Pos logit contributions | |
uster | +0.244 |
rier | +0.232 |
bars | +0.229 |
hole | +0.227 |
isher | +0.223 |
Neg logit contributions | |
play | -0.093 |
eat | -0.079 |
joke | -0.069 |
swim | -0.068 |
drink | -0.068 |
Token | tool |
Token ID | 2891 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
uster | +0.016 |
bars | +0.015 |
rier | +0.015 |
dollars | +0.014 |
hole | +0.014 |
Neg logit contributions | |
joke | -0.013 |
play | -0.013 |
chat | -0.013 |
eat | -0.012 |
sip | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
uster | +0.360 |
rier | +0.329 |
dollars | +0.321 |
bars | +0.318 |
isher | +0.315 |
Neg logit contributions | |
play | -0.219 |
joke | -0.206 |
eat | -0.192 |
chat | -0.191 |
swim | -0.178 |
Token | It |
Token ID | 632 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
play | +0.017 |
joke | +0.016 |
eat | +0.015 |
chat | +0.015 |
sip | +0.014 |
Neg logit contributions | |
uster | -0.024 |
rier | -0.023 |
dollars | -0.023 |
isher | -0.023 |
bars | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
uster | +0.034 |
rier | +0.032 |
bars | +0.031 |
dollars | +0.031 |
hole | +0.031 |
Neg logit contributions | |
joke | -0.015 |
play | -0.014 |
chat | -0.013 |
eat | -0.013 |
laugh | -0.012 |
Token | still |
Token ID | 991 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
play | +0.030 |
joke | +0.029 |
eat | +0.027 |
chat | +0.027 |
laugh | +0.024 |
Neg logit contributions | |
uster | -0.064 |
bars | -0.061 |
isher | -0.059 |
dollars | -0.058 |
rier | -0.058 |
Token | hot |
Token ID | 3024 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
uster | +0.101 |
bars | +0.095 |
rier | +0.091 |
dollars | +0.090 |
hole | +0.090 |
Neg logit contributions | |
play | -0.056 |
joke | -0.056 |
chat | -0.052 |
eat | -0.050 |
laugh | -0.048 |
Token | went |
Token ID | 1816 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
uster | +0.039 |
bars | +0.037 |
rier | +0.036 |
dollars | +0.036 |
hole | +0.035 |
Neg logit contributions | |
joke | -0.019 |
play | -0.019 |
chat | -0.018 |
eat | -0.016 |
sip | -0.016 |
Token | so |
Token ID | 523 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
play | +0.062 |
joke | +0.058 |
chat | +0.056 |
eat | +0.053 |
dance | +0.051 |
Neg logit contributions | |
uster | -0.113 |
bars | -0.107 |
dollars | -0.107 |
isher | -0.104 |
rier | -0.104 |
Token | far |
Token ID | 1290 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
uster | +0.046 |
bars | +0.045 |
rier | +0.044 |
dollars | +0.042 |
hole | +0.042 |
Neg logit contributions | |
joke | -0.034 |
play | -0.032 |
chat | -0.030 |
eat | -0.030 |
sip | -0.029 |
Token | she |
Token ID | 673 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
uster | +0.314 |
bars | +0.311 |
dollars | +0.306 |
isher | +0.291 |
iers | +0.285 |
Neg logit contributions | |
play | -0.130 |
eat | -0.111 |
walk | -0.104 |
catch | -0.104 |
chat | -0.102 |
Token | could |
Token ID | 714 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
play | +0.017 |
joke | +0.016 |
chat | +0.015 |
swim | +0.014 |
eat | +0.014 |
Neg logit contributions | |
uster | -0.026 |
rier | -0.024 |
dollars | -0.024 |
isher | -0.023 |
bars | -0.023 |
Token | no |
Token ID | 645 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
uster | +0.203 |
bars | +0.193 |
rier | +0.191 |
dollars | +0.189 |
hole | +0.187 |
Neg logit contributions | |
joke | -0.081 |
play | -0.080 |
chat | -0.072 |
eat | -0.069 |
laugh | -0.064 |
Token | longer |
Token ID | 2392 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
uster | +0.366 |
rier | +0.322 |
bars | +0.319 |
dollars | +0.318 |
isher | +0.314 |
Neg logit contributions | |
play | -0.305 |
joke | -0.293 |
chat | -0.273 |
dance | -0.268 |
eat | -0.266 |
Token | see |
Token ID | 766 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
uster | +0.254 |
bars | +0.240 |
rier | +0.236 |
dollars | +0.232 |
hole | +0.231 |
Neg logit contributions | |
joke | -0.151 |
play | -0.149 |
chat | -0.138 |
eat | -0.134 |
sip | -0.126 |
Token | it |
Token ID | 340 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
uster | +0.034 |
dollars | +0.031 |
rier | +0.031 |
isher | +0.030 |
bars | +0.030 |
Neg logit contributions | |
play | -0.017 |
joke | -0.015 |
chat | -0.014 |
eat | -0.014 |
dance | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
uster | +0.036 |
bars | +0.034 |
rier | +0.033 |
hole | +0.033 |
dollars | +0.033 |
Neg logit contributions | |
joke | -0.024 |
play | -0.023 |
chat | -0.022 |
eat | -0.021 |
sip | -0.020 |
Token | The |
Token ID | 383 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
uster | +0.010 |
bars | +0.010 |
hole | +0.010 |
rier | +0.009 |
dollars | +0.009 |
Neg logit contributions | |
joke | -0.009 |
play | -0.008 |
chat | -0.008 |
eat | -0.008 |
swim | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
uster | +0.003 |
bars | +0.003 |
hole | +0.003 |
rier | +0.002 |
dollars | +0.002 |
Neg logit contributions | |
joke | -0.002 |
play | -0.002 |
chat | -0.002 |
eat | -0.001 |
swim | -0.001 |
Token | carefully |
Token ID | 7773 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
play | +0.023 |
joke | +0.022 |
chat | +0.021 |
eat | +0.020 |
swim | +0.019 |
Neg logit contributions | |
uster | -0.047 |
rier | -0.046 |
hole | -0.044 |
bars | -0.044 |
dollars | -0.043 |
Token | buck |
Token ID | 10230 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
uster | +0.102 |
rier | +0.099 |
bars | +0.095 |
dollars | +0.094 |
hole | +0.094 |
Neg logit contributions | |
play | -0.060 |
joke | -0.058 |
chat | -0.055 |
eat | -0.054 |
swim | -0.050 |
Token | led |
Token ID | 992 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
uster | +0.204 |
dollars | +0.190 |
rier | +0.189 |
bars | +0.181 |
hole | +0.181 |
Neg logit contributions | |
play | -0.122 |
joke | -0.113 |
chat | -0.110 |
eat | -0.104 |
walks | -0.101 |
Token | the |
Token ID | 262 |
Feature activation | +9.35e-03 |
Pos logit contributions | |
joke | +0.061 |
play | +0.056 |
chat | +0.054 |
eat | +0.052 |
sip | +0.049 |
Neg logit contributions | |
uster | -0.112 |
bars | -0.109 |
rier | -0.105 |
hole | -0.103 |
dollars | -0.103 |
Token | straps |
Token ID | 29552 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
uster | +0.020 |
isher | +0.019 |
mith | +0.019 |
rier | +0.019 |
dollars | +0.018 |
Neg logit contributions | |
play | -0.015 |
joke | -0.014 |
walk | -0.014 |
jog | -0.013 |
dance | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
dollars | +0.539 |
uster | +0.534 |
isher | +0.515 |
ubby | +0.510 |
rier | +0.503 |
Neg logit contributions | |
play | -0.199 |
chat | -0.161 |
laugh | -0.153 |
walk | -0.148 |
dance | -0.146 |
Token | each |
Token ID | 1123 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
play | +0.049 |
joke | +0.040 |
eat | +0.036 |
chat | +0.034 |
dance | +0.034 |
Neg logit contributions | |
uster | -0.189 |
dollars | -0.183 |
rier | -0.183 |
isher | -0.181 |
bars | -0.178 |
Token | shoe |
Token ID | 17292 |
Feature activation | -5.92e-03 |
Pos logit contributions | |
play | +0.014 |
walk | +0.012 |
jog | +0.012 |
joke | +0.012 |
dance | +0.011 |
Neg logit contributions | |
rier | -0.026 |
uster | -0.025 |
dollars | -0.024 |
isher | -0.024 |
hole | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +2.80e-03 |
Pos logit contributions | |
play | +0.008 |
joke | +0.007 |
chat | +0.007 |
eat | +0.007 |
dance | +0.006 |
Neg logit contributions | |
uster | -0.015 |
rier | -0.014 |
isher | -0.014 |
dollars | -0.014 |
ubby | -0.014 |
Token | jumped |
Token ID | 11687 |
Feature activation | -3.51e-03 |
Pos logit contributions | |
uster | +0.007 |
rier | +0.007 |
dollars | +0.006 |
bars | +0.006 |
hole | +0.006 |
Neg logit contributions | |
play | -0.004 |
joke | -0.004 |
chat | -0.003 |
eat | -0.003 |
laugh | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
uster | +0.038 |
bars | +0.036 |
hole | +0.036 |
rier | +0.036 |
dollars | +0.035 |
Neg logit contributions | |
joke | -0.028 |
play | -0.027 |
chat | -0.025 |
eat | -0.025 |
sip | -0.024 |
Token | : |
Token ID | 25 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
uster | +0.007 |
bars | +0.007 |
rier | +0.006 |
dollars | +0.006 |
hole | +0.006 |
Neg logit contributions | |
joke | -0.006 |
play | -0.006 |
chat | -0.006 |
eat | -0.005 |
sip | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
joke | +0.209 |
play | +0.206 |
chat | +0.198 |
eat | +0.194 |
sip | +0.191 |
Neg logit contributions | |
uster | -0.148 |
rier | -0.138 |
bars | -0.136 |
hole | -0.131 |
dollars | -0.128 |
Token | Take |
Token ID | 12322 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
uster | +0.134 |
rier | +0.129 |
dollars | +0.127 |
bars | +0.127 |
hole | +0.124 |
Neg logit contributions | |
play | -0.066 |
joke | -0.066 |
chat | -0.061 |
eat | -0.056 |
walk | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
uster | +0.084 |
bars | +0.082 |
rier | +0.079 |
hole | +0.078 |
dollars | +0.077 |
Neg logit contributions | |
joke | -0.063 |
play | -0.062 |
chat | -0.058 |
eat | -0.057 |
laugh | -0.053 |
Token | scissors |
Token ID | 41786 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
uster | +0.017 |
bars | +0.016 |
rier | +0.016 |
mith | +0.015 |
isher | +0.015 |
Neg logit contributions | |
joke | -0.020 |
play | -0.019 |
eat | -0.018 |
walk | -0.018 |
laugh | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-03 |
Pos logit contributions | |
uster | +0.356 |
bars | +0.331 |
isher | +0.330 |
rier | +0.328 |
dollars | +0.322 |
Neg logit contributions | |
play | -0.221 |
eat | -0.199 |
joke | -0.196 |
laugh | -0.185 |
dance | -0.183 |
Token | use |
Token ID | 779 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
play | +0.002 |
joke | +0.002 |
eat | +0.002 |
chat | +0.002 |
dance | +0.002 |
Neg logit contributions | |
uster | -0.004 |
rier | -0.003 |
bars | -0.003 |
dollars | -0.003 |
hole | -0.003 |
Token | them |
Token ID | 606 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
uster | +0.279 |
rier | +0.279 |
bars | +0.269 |
hole | +0.255 |
dollars | +0.254 |
Neg logit contributions | |
play | -0.128 |
eat | -0.103 |
joke | -0.100 |
catch | -0.099 |
swim | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | -5.24e-04 |
Pos logit contributions | |
uster | +0.101 |
bars | +0.095 |
rier | +0.094 |
isher | +0.091 |
dollars | +0.090 |
Neg logit contributions | |
play | -0.061 |
joke | -0.056 |
eat | -0.053 |
chat | -0.052 |
dance | -0.049 |
Token | That |
Token ID | 1320 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
play | +0.001 |
joke | +0.001 |
eat | +0.001 |
swim | +0.001 |
enjoy | +0.001 |
Neg logit contributions | |
uster | -0.001 |
rier | -0.001 |
isher | -0.001 |
bars | -0.001 |
dollars | -0.001 |
Token | am |
Token ID | 716 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
uster | +0.172 |
bars | +0.162 |
rier | +0.159 |
dollars | +0.158 |
hole | +0.157 |
Neg logit contributions | |
joke | -0.111 |
play | -0.108 |
chat | -0.102 |
eat | -0.098 |
sip | -0.094 |
Token | a |
Token ID | 257 |
Feature activation | -7.13e-03 |
Pos logit contributions | |
play | +0.123 |
joke | +0.119 |
eat | +0.111 |
chat | +0.109 |
laugh | +0.105 |
Neg logit contributions | |
uster | -0.246 |
bars | -0.237 |
isher | -0.235 |
rier | -0.228 |
hole | -0.227 |
Token | little |
Token ID | 1310 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
joke | +0.012 |
play | +0.011 |
chat | +0.011 |
eat | +0.011 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.014 |
rier | -0.013 |
bars | -0.013 |
dollars | -0.013 |
isher | -0.012 |
Token | scared |
Token ID | 12008 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
uster | +0.068 |
bars | +0.063 |
hole | +0.061 |
rier | +0.061 |
dollars | +0.060 |
Neg logit contributions | |
play | -0.049 |
joke | -0.048 |
chat | -0.044 |
eat | -0.043 |
swim | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
joke | +0.101 |
play | +0.100 |
eat | +0.093 |
swim | +0.092 |
chat | +0.089 |
Neg logit contributions | |
uster | -0.107 |
bars | -0.106 |
hole | -0.102 |
isher | -0.100 |
rier | -0.094 |
Token | The |
Token ID | 383 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
uster | +0.013 |
rier | +0.012 |
bars | +0.012 |
isher | +0.012 |
dollars | +0.012 |
Neg logit contributions | |
play | -0.014 |
joke | -0.014 |
eat | -0.013 |
chat | -0.012 |
swim | -0.012 |
Token | slide |
Token ID | 10649 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
uster | +0.057 |
bars | +0.056 |
rier | +0.055 |
dollars | +0.054 |
hole | +0.054 |
Neg logit contributions | |
joke | -0.016 |
play | -0.015 |
chat | -0.014 |
eat | -0.013 |
sip | -0.012 |
Token | is |
Token ID | 318 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
play | +0.158 |
joke | +0.150 |
eat | +0.137 |
chat | +0.135 |
swim | +0.130 |
Neg logit contributions | |
uster | -0.301 |
rier | -0.267 |
isher | -0.255 |
hole | -0.250 |
bars | -0.250 |
Token | very |
Token ID | 845 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
play | +0.024 |
joke | +0.024 |
eat | +0.021 |
chat | +0.021 |
laugh | +0.020 |
Neg logit contributions | |
uster | -0.041 |
bars | -0.038 |
rier | -0.038 |
isher | -0.037 |
hole | -0.036 |
Token | high |
Token ID | 1029 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
play | +0.030 |
joke | +0.030 |
chat | +0.027 |
eat | +0.027 |
swim | +0.026 |
Neg logit contributions | |
uster | -0.052 |
bars | -0.048 |
rier | -0.048 |
hole | -0.048 |
dollars | -0.047 |
Token | ." |
Token ID | 526 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
uster | +0.036 |
bars | +0.033 |
isher | +0.032 |
dollars | +0.031 |
mith | +0.031 |
Neg logit contributions | |
play | -0.023 |
joke | -0.022 |
eat | -0.021 |
swim | -0.020 |
chat | -0.020 |
Token | my |
Token ID | 1820 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
joke | +0.027 |
play | +0.026 |
chat | +0.025 |
eat | +0.025 |
sip | +0.024 |
Neg logit contributions | |
uster | -0.024 |
bars | -0.022 |
rier | -0.021 |
hole | -0.021 |
dollars | -0.021 |
Token | told |
Token ID | 1297 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
joke | +0.017 |
play | +0.016 |
chat | +0.016 |
sip | +0.015 |
eat | +0.015 |
Neg logit contributions | |
uster | -0.021 |
bars | -0.021 |
dollars | -0.020 |
hole | -0.020 |
isher | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | -5.37e-03 |
Pos logit contributions | |
uster | +0.047 |
bars | +0.044 |
rier | +0.044 |
hole | +0.043 |
dollars | +0.043 |
Neg logit contributions | |
joke | -0.027 |
play | -0.027 |
chat | -0.025 |
eat | -0.024 |
sip | -0.022 |
Token | about |
Token ID | 546 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
joke | +0.009 |
play | +0.009 |
chat | +0.009 |
sip | +0.008 |
eat | +0.008 |
Neg logit contributions | |
uster | -0.010 |
bars | -0.010 |
dollars | -0.010 |
rier | -0.009 |
hole | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
joke | +0.050 |
play | +0.049 |
chat | +0.045 |
eat | +0.044 |
sip | +0.042 |
Neg logit contributions | |
uster | -0.083 |
bars | -0.078 |
rier | -0.077 |
dollars | -0.076 |
hole | -0.076 |
Token | trade |
Token ID | 3292 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
uster | +0.025 |
bars | +0.023 |
rier | +0.022 |
dollars | +0.022 |
hole | +0.022 |
Neg logit contributions | |
joke | -0.017 |
play | -0.016 |
eat | -0.014 |
chat | -0.014 |
swim | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
uster | +0.138 |
rier | +0.125 |
bars | +0.122 |
hole | +0.117 |
isher | +0.114 |
Neg logit contributions | |
play | -0.077 |
joke | -0.070 |
eat | -0.063 |
swim | -0.063 |
catch | -0.061 |
Token | Tommy |
Token ID | 19919 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
play | +0.026 |
joke | +0.025 |
eat | +0.023 |
chat | +0.022 |
drink | +0.019 |
Neg logit contributions | |
uster | -0.061 |
rier | -0.058 |
bars | -0.058 |
hole | -0.057 |
dollars | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e-06 |
Pos logit contributions | |
uster | +0.167 |
bars | +0.161 |
dollars | +0.158 |
hole | +0.156 |
rier | +0.155 |
Neg logit contributions | |
joke | -0.123 |
play | -0.117 |
chat | -0.114 |
eat | -0.107 |
sip | -0.106 |
Token | His |
Token ID | 2399 |
Feature activation | +1.00e-01 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
uster | +0.167 |
bars | +0.157 |
dollars | +0.152 |
rier | +0.151 |
hole | +0.145 |
Neg logit contributions | |
joke | -0.190 |
play | -0.186 |
chat | -0.186 |
sip | -0.180 |
eat | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | +4.53e-03 |
Pos logit contributions | |
uster | +0.228 |
bars | +0.212 |
rier | +0.209 |
dollars | +0.206 |
hole | +0.204 |
Neg logit contributions | |
joke | -0.163 |
play | -0.160 |
chat | -0.150 |
eat | -0.147 |
sip | -0.140 |
Token | said |
Token ID | 531 |
Feature activation | +6.54e-03 |
Pos logit contributions | |
uster | +0.008 |
bars | +0.008 |
rier | +0.008 |
dollars | +0.007 |
hole | +0.007 |
Neg logit contributions | |
joke | -0.008 |
play | -0.008 |
chat | -0.007 |
eat | -0.007 |
sip | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
uster | +0.014 |
bars | +0.013 |
hole | +0.013 |
rier | +0.013 |
dollars | +0.012 |
Neg logit contributions | |
joke | -0.011 |
play | -0.010 |
chat | -0.010 |
eat | -0.010 |
laugh | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
uster | +0.009 |
bars | +0.008 |
isher | +0.008 |
hole | +0.008 |
dollars | +0.008 |
Neg logit contributions | |
joke | -0.008 |
play | -0.008 |
chat | -0.007 |
eat | -0.007 |
swim | -0.007 |
Token | You |
Token ID | 1639 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
uster | +0.152 |
rier | +0.142 |
hole | +0.141 |
dollars | +0.140 |
bars | +0.139 |
Neg logit contributions | |
play | -0.073 |
chat | -0.068 |
joke | -0.068 |
eat | -0.062 |
enjoy | -0.058 |
Token | were |
Token ID | 547 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
play | +0.082 |
joke | +0.082 |
eat | +0.075 |
chat | +0.074 |
laugh | +0.071 |
Neg logit contributions | |
uster | -0.128 |
bars | -0.122 |
rier | -0.120 |
hole | -0.116 |
dollars | -0.115 |
Token | very |
Token ID | 845 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
joke | +0.013 |
play | +0.013 |
eat | +0.012 |
chat | +0.012 |
laugh | +0.011 |
Neg logit contributions | |
uster | -0.022 |
bars | -0.021 |
rier | -0.020 |
isher | -0.019 |
hole | -0.019 |
Token | generous |
Token ID | 14431 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
joke | +0.030 |
play | +0.029 |
chat | +0.027 |
eat | +0.027 |
laugh | +0.026 |
Neg logit contributions | |
uster | -0.043 |
bars | -0.041 |
rier | -0.040 |
hole | -0.040 |
dollars | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +4.99e-03 |
Pos logit contributions | |
uster | +0.130 |
bars | +0.125 |
hole | +0.123 |
mith | +0.121 |
isher | +0.119 |
Neg logit contributions | |
play | -0.063 |
joke | -0.059 |
eat | -0.052 |
chat | -0.050 |
dance | -0.049 |
Token | Sharing |
Token ID | 36644 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
uster | +0.009 |
rier | +0.009 |
hole | +0.009 |
dollars | +0.009 |
ier | +0.009 |
Neg logit contributions | |
play | -0.009 |
joke | -0.008 |
eat | -0.008 |
enjoy | -0.008 |
dance | -0.007 |
Token | your |
Token ID | 534 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
joke | +0.154 |
play | +0.152 |
chat | +0.138 |
eat | +0.138 |
laugh | +0.131 |
Neg logit contributions | |
uster | -0.214 |
bars | -0.197 |
rier | -0.195 |
hole | -0.193 |
dollars | -0.191 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
uster | +0.021 |
bars | +0.020 |
rier | +0.019 |
hole | +0.019 |
dollars | +0.019 |
Neg logit contributions | |
joke | -0.021 |
play | -0.021 |
chat | -0.020 |
eat | -0.020 |
sip | -0.019 |
Token | named |
Token ID | 3706 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
play | +0.047 |
joke | +0.046 |
chat | +0.042 |
eat | +0.041 |
sip | +0.038 |
Neg logit contributions | |
uster | -0.092 |
rier | -0.087 |
bars | -0.086 |
dollars | -0.084 |
hole | -0.083 |
Token | Emma |
Token ID | 18966 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
uster | +0.121 |
bars | +0.113 |
hole | +0.111 |
rier | +0.107 |
dollars | +0.106 |
Neg logit contributions | |
joke | -0.106 |
chat | -0.097 |
play | -0.095 |
swim | -0.089 |
laugh | -0.089 |
Token | who |
Token ID | 508 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
joke | +0.003 |
play | +0.003 |
chat | +0.003 |
eat | +0.003 |
sip | +0.003 |
Neg logit contributions | |
uster | -0.005 |
bars | -0.005 |
rier | -0.005 |
hole | -0.004 |
dollars | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
uster | +0.060 |
hole | +0.054 |
bars | +0.054 |
ac | +0.052 |
isher | +0.052 |
Neg logit contributions | |
joke | -0.061 |
jokes | -0.059 |
sip | -0.057 |
chat | -0.056 |
swamp | -0.056 |
Token | three |
Token ID | 1115 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
joke | +0.038 |
chat | +0.034 |
sip | +0.034 |
play | +0.033 |
eat | +0.032 |
Neg logit contributions | |
uster | -0.045 |
rier | -0.043 |
bars | -0.042 |
ubby | -0.041 |
dollars | -0.040 |
Token | years |
Token ID | 812 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
uster | +0.026 |
bars | +0.024 |
dollars | +0.024 |
rier | +0.024 |
hole | +0.023 |
Neg logit contributions | |
joke | -0.027 |
play | -0.026 |
chat | -0.025 |
eat | -0.024 |
sip | -0.024 |
Token | old |
Token ID | 1468 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
uster | +0.112 |
hole | +0.103 |
dollars | +0.100 |
isher | +0.100 |
bars | +0.099 |
Neg logit contributions | |
play | -0.127 |
eat | -0.116 |
joke | -0.116 |
swamp | -0.113 |
dance | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
uster | +0.157 |
rier | +0.149 |
bars | +0.149 |
dollars | +0.148 |
hole | +0.146 |
Neg logit contributions | |
joke | -0.144 |
play | -0.136 |
chat | -0.135 |
sip | -0.128 |
eat | -0.127 |
Token | She |
Token ID | 1375 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
joke | +0.020 |
play | +0.018 |
chat | +0.018 |
eat | +0.017 |
swim | +0.017 |
Neg logit contributions | |
uster | -0.024 |
bars | -0.023 |
rier | -0.022 |
hole | -0.022 |
dollars | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
sip | +0.051 |
joke | +0.050 |
chat | +0.047 |
jokes | +0.046 |
laugh | +0.046 |
Neg logit contributions | |
uster | -0.039 |
bars | -0.037 |
belt | -0.036 |
hole | -0.036 |
ubby | -0.035 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
uster | +0.012 |
bars | +0.011 |
dollars | +0.010 |
rier | +0.010 |
hole | +0.010 |
Neg logit contributions | |
joke | -0.015 |
chat | -0.014 |
play | -0.013 |
swamp | -0.013 |
sip | -0.013 |
Token | look |
Token ID | 804 |
Feature activation | -3.36e-03 |
Pos logit contributions | |
uster | +0.042 |
hole | +0.041 |
bars | +0.041 |
rier | +0.038 |
dollars | +0.038 |
Neg logit contributions | |
joke | -0.029 |
swamp | -0.027 |
chat | -0.026 |
| | -0.026 |
tea | -0.025 |
Token | at |
Token ID | 379 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
joke | +0.007 |
chat | +0.007 |
play | +0.006 |
eat | +0.006 |
walk | +0.006 |
Neg logit contributions | |
uster | -0.005 |
rier | -0.005 |
dollars | -0.005 |
hole | -0.005 |
bars | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
joke | +0.063 |
play | +0.059 |
chat | +0.058 |
eat | +0.055 |
laugh | +0.052 |
Neg logit contributions | |
uster | -0.090 |
bars | -0.086 |
rier | -0.085 |
isher | -0.082 |
hole | -0.082 |
Token | roof |
Token ID | 9753 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
uster | +0.028 |
bars | +0.027 |
rier | +0.026 |
dollars | +0.025 |
hole | +0.025 |
Neg logit contributions | |
joke | -0.029 |
play | -0.029 |
chat | -0.027 |
eat | -0.027 |
sip | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
uster | +0.208 |
dollars | +0.185 |
bars | +0.183 |
rier | +0.183 |
isher | +0.182 |
Neg logit contributions | |
play | -0.111 |
joke | -0.109 |
chat | -0.098 |
eat | -0.098 |
laugh | -0.094 |
Token | They |
Token ID | 1119 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
uster | +0.030 |
bars | +0.028 |
rier | +0.028 |
dollars | +0.027 |
hole | +0.027 |
Neg logit contributions | |
joke | -0.018 |
play | -0.018 |
chat | -0.017 |
eat | -0.016 |
laugh | -0.015 |
Token | see |
Token ID | 766 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
joke | +0.092 |
chat | +0.083 |
play | +0.080 |
sip | +0.074 |
eat | +0.073 |
Neg logit contributions | |
uster | -0.169 |
bars | -0.166 |
hole | -0.164 |
rier | -0.156 |
dollars | -0.155 |
Token | a |
Token ID | 257 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
uster | +0.048 |
bars | +0.044 |
rier | +0.044 |
dollars | +0.043 |
hole | +0.043 |
Neg logit contributions | |
play | -0.024 |
joke | -0.024 |
chat | -0.022 |
eat | -0.021 |
laugh | -0.020 |
Token | black |
Token ID | 2042 |
Feature activation | +3.27e-03 |
Pos logit contributions | |
joke | +0.007 |
play | +0.007 |
chat | +0.006 |
eat | +0.006 |
sip | +0.006 |
Neg logit contributions | |
uster | -0.008 |
bars | -0.008 |
rier | -0.008 |
dollars | -0.008 |
hole | -0.008 |
Token | cat |
Token ID | 3797 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
uster | +0.007 |
bars | +0.006 |
rier | +0.006 |
dollars | +0.006 |
hole | +0.006 |
Neg logit contributions | |
joke | -0.006 |
play | -0.005 |
chat | -0.005 |
eat | -0.005 |
sip | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
joke | +0.014 |
play | +0.014 |
chat | +0.013 |
eat | +0.012 |
sip | +0.012 |
Neg logit contributions | |
uster | -0.025 |
bars | -0.023 |
dollars | -0.023 |
rier | -0.023 |
hole | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
joke | +0.063 |
play | +0.057 |
chat | +0.055 |
eat | +0.053 |
sip | +0.051 |
Neg logit contributions | |
uster | -0.093 |
bars | -0.086 |
rier | -0.085 |
hole | -0.085 |
dollars | -0.084 |
Token | car |
Token ID | 1097 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
uster | +0.019 |
bars | +0.019 |
hole | +0.018 |
rier | +0.018 |
isher | +0.018 |
Neg logit contributions | |
joke | -0.014 |
chat | -0.012 |
laugh | -0.011 |
sip | -0.011 |
eat | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
uster | +0.142 |
rier | +0.136 |
dollars | +0.129 |
isher | +0.129 |
bars | +0.128 |
Neg logit contributions | |
play | -0.073 |
joke | -0.063 |
chat | -0.061 |
eat | -0.060 |
walk | -0.059 |
Token | They |
Token ID | 1119 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
play | +0.007 |
joke | +0.007 |
chat | +0.006 |
eat | +0.006 |
sip | +0.006 |
Neg logit contributions | |
uster | -0.017 |
bars | -0.016 |
rier | -0.016 |
dollars | -0.016 |
hole | -0.015 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
play | +0.101 |
chat | +0.077 |
eat | +0.076 |
laugh | +0.073 |
walk | +0.071 |
Neg logit contributions | |
rier | -0.268 |
uster | -0.259 |
dollars | -0.244 |
isher | -0.241 |
bars | -0.238 |
Token | to |
Token ID | 284 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
joke | +0.027 |
play | +0.027 |
chat | +0.025 |
eat | +0.024 |
sip | +0.023 |
Neg logit contributions | |
uster | -0.043 |
bars | -0.040 |
rier | -0.040 |
dollars | -0.039 |
hole | -0.039 |
Token | go |
Token ID | 467 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
play | +0.032 |
joke | +0.032 |
chat | +0.027 |
eat | +0.027 |
laugh | +0.024 |
Neg logit contributions | |
uster | -0.097 |
bars | -0.092 |
rier | -0.092 |
dollars | -0.090 |
hole | -0.090 |
Token | to |
Token ID | 284 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
play | +0.073 |
joke | +0.071 |
chat | +0.066 |
eat | +0.065 |
swim | +0.062 |
Neg logit contributions | |
uster | -0.121 |
rier | -0.115 |
bars | -0.115 |
dollars | -0.112 |
hole | -0.110 |
Token | the |
Token ID | 262 |
Feature activation | +4.96e-03 |
Pos logit contributions | |
joke | +0.048 |
play | +0.046 |
chat | +0.044 |
eat | +0.042 |
sip | +0.040 |
Neg logit contributions | |
uster | -0.080 |
bars | -0.076 |
rier | -0.075 |
hole | -0.074 |
dollars | -0.074 |
Token | zoo |
Token ID | 26626 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
uster | +0.012 |
bars | +0.011 |
rier | +0.011 |
dollars | +0.011 |
hole | +0.011 |
Neg logit contributions | |
joke | -0.006 |
play | -0.006 |
chat | -0.006 |
eat | -0.006 |
sip | -0.005 |
Token | his |
Token ID | 465 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
uster | +0.237 |
dollars | +0.224 |
bars | +0.223 |
rier | +0.220 |
hole | +0.215 |
Neg logit contributions | |
play | -0.107 |
joke | -0.101 |
chat | -0.094 |
eat | -0.090 |
swim | -0.086 |
Token | eyes |
Token ID | 2951 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
uster | +0.073 |
bars | +0.068 |
rier | +0.066 |
hole | +0.066 |
dollars | +0.065 |
Neg logit contributions | |
joke | -0.119 |
play | -0.116 |
chat | -0.113 |
eat | -0.111 |
sip | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | -4.51e-03 |
Pos logit contributions | |
uster | +0.163 |
isher | +0.154 |
dollars | +0.151 |
rier | +0.149 |
bars | +0.149 |
Neg logit contributions | |
play | -0.089 |
chat | -0.081 |
joke | -0.081 |
eat | -0.079 |
sip | -0.076 |
Token | A |
Token ID | 317 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
joke | +0.008 |
play | +0.008 |
chat | +0.007 |
eat | +0.007 |
sip | +0.007 |
Neg logit contributions | |
uster | -0.009 |
bars | -0.008 |
rier | -0.008 |
dollars | -0.008 |
hole | -0.008 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
uster | +0.030 |
bars | +0.028 |
rier | +0.028 |
dollars | +0.027 |
hole | +0.027 |
Neg logit contributions | |
joke | -0.021 |
play | -0.021 |
chat | -0.020 |
eat | -0.019 |
sip | -0.018 |
Token | rainbow |
Token ID | 27223 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
joke | +0.077 |
play | +0.076 |
chat | +0.071 |
eat | +0.070 |
sip | +0.067 |
Neg logit contributions | |
uster | -0.113 |
bars | -0.106 |
rier | -0.106 |
hole | -0.104 |
dollars | -0.103 |
Token | was |
Token ID | 373 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
joke | +0.052 |
play | +0.051 |
chat | +0.048 |
eat | +0.047 |
sip | +0.045 |
Neg logit contributions | |
uster | -0.074 |
bars | -0.070 |
rier | -0.069 |
dollars | -0.068 |
hole | -0.067 |
Token | shining |
Token ID | 22751 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
play | +0.029 |
joke | +0.028 |
chat | +0.027 |
dance | +0.025 |
eat | +0.025 |
Neg logit contributions | |
uster | -0.058 |
dollars | -0.055 |
bars | -0.055 |
isher | -0.053 |
rier | -0.053 |
Token | in |
Token ID | 287 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
joke | +0.090 |
play | +0.090 |
chat | +0.084 |
eat | +0.082 |
dance | +0.079 |
Neg logit contributions | |
uster | -0.117 |
bars | -0.109 |
dollars | -0.106 |
rier | -0.105 |
hole | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | +7.83e-03 |
Pos logit contributions | |
play | +0.043 |
joke | +0.039 |
chat | +0.036 |
eat | +0.036 |
dance | +0.032 |
Neg logit contributions | |
uster | -0.113 |
bars | -0.107 |
dollars | -0.106 |
rier | -0.105 |
hole | -0.100 |
Token | mirror |
Token ID | 10162 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
uster | +0.014 |
bars | +0.013 |
rier | +0.013 |
hole | +0.013 |
dollars | +0.013 |
Neg logit contributions | |
joke | -0.015 |
play | -0.014 |
chat | -0.014 |
eat | -0.014 |
sip | -0.013 |
Token | grab |
Token ID | 5552 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
joke | +0.048 |
chat | +0.042 |
sip | +0.041 |
| | +0.041 |
Boo | +0.040 |
Neg logit contributions | |
uster | -0.046 |
hole | -0.045 |
rier | -0.043 |
bars | -0.042 |
dollars | -0.041 |
Token | it |
Token ID | 340 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
uster | +0.062 |
bars | +0.059 |
rier | +0.058 |
dollars | +0.057 |
hole | +0.057 |
Neg logit contributions | |
joke | -0.035 |
play | -0.035 |
chat | -0.032 |
eat | -0.031 |
sip | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -6.43e-03 |
Pos logit contributions | |
uster | +0.034 |
bars | +0.032 |
rier | +0.031 |
dollars | +0.031 |
isher | +0.031 |
Neg logit contributions | |
play | -0.022 |
joke | -0.022 |
chat | -0.021 |
eat | -0.020 |
sip | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
joke | +0.011 |
play | +0.011 |
chat | +0.011 |
eat | +0.011 |
sip | +0.010 |
Neg logit contributions | |
uster | -0.012 |
bars | -0.012 |
rier | -0.011 |
dollars | -0.011 |
hole | -0.011 |
Token | started |
Token ID | 2067 |
Feature activation | -3.96e-03 |
Pos logit contributions | |
joke | +0.010 |
play | +0.009 |
chat | +0.009 |
eat | +0.008 |
sip | +0.008 |
Neg logit contributions | |
uster | -0.013 |
bars | -0.012 |
rier | -0.012 |
hole | -0.012 |
dollars | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
joke | +0.006 |
play | +0.006 |
sip | +0.006 |
| | +0.006 |
swamp | +0.006 |
Neg logit contributions | |
uster | -0.007 |
bars | -0.007 |
dollars | -0.006 |
rier | -0.006 |
hole | -0.006 |
Token | feed |
Token ID | 3745 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
joke | +0.024 |
| | +0.024 |
< | +0.024 |
Boo | +0.023 |
swamp | +0.023 |
Neg logit contributions | |
hole | -0.058 |
bars | -0.057 |
uster | -0.057 |
rier | -0.056 |
bar | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -6.06e-03 |
Pos logit contributions | |
joke | +0.045 |
play | +0.045 |
chat | +0.041 |
eat | +0.040 |
sip | +0.038 |
Neg logit contributions | |
uster | -0.082 |
bars | -0.078 |
rier | -0.076 |
dollars | -0.075 |
hole | -0.075 |
Token | She |
Token ID | 1375 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
joke | +0.010 |
play | +0.009 |
chat | +0.009 |
eat | +0.008 |
swim | +0.008 |
Neg logit contributions | |
uster | -0.013 |
bars | -0.012 |
rier | -0.012 |
hole | -0.012 |
dollars | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
joke | +0.034 |
play | +0.033 |
chat | +0.030 |
eat | +0.030 |
sip | +0.029 |
Neg logit contributions | |
uster | -0.058 |
bars | -0.055 |
dollars | -0.054 |
rier | -0.054 |
hole | -0.053 |
Token | so |
Token ID | 523 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
joke | +0.044 |
play | +0.043 |
chat | +0.041 |
eat | +0.040 |
sip | +0.038 |
Neg logit contributions | |
uster | -0.054 |
bars | -0.050 |
rier | -0.050 |
dollars | -0.049 |
hole | -0.049 |
Token | sound |
Token ID | 2128 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
play | +0.014 |
chat | +0.013 |
joke | +0.013 |
| | +0.013 |
walks | +0.013 |
Neg logit contributions | |
rier | -0.017 |
uster | -0.016 |
dollars | -0.015 |
hole | -0.015 |
bars | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +7.42e-03 |
Pos logit contributions | |
joke | +0.073 |
chat | +0.071 |
play | +0.071 |
walk | +0.065 |
eat | +0.065 |
Neg logit contributions | |
rier | -0.076 |
uster | -0.075 |
hole | -0.072 |
bars | -0.071 |
dollars | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
uster | +0.018 |
bars | +0.018 |
isher | +0.017 |
rier | +0.017 |
hole | +0.017 |
Neg logit contributions | |
play | -0.009 |
joke | -0.009 |
eat | -0.008 |
chat | -0.008 |
sip | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
play | +0.013 |
joke | +0.013 |
chat | +0.012 |
eat | +0.011 |
sip | +0.011 |
Neg logit contributions | |
uster | -0.031 |
bars | -0.030 |
rier | -0.030 |
dollars | -0.029 |
hole | -0.029 |
Token | The |
Token ID | 464 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
play | +0.018 |
catch | +0.016 |
eat | +0.016 |
joke | +0.015 |
chat | +0.015 |
Neg logit contributions | |
uster | -0.025 |
bars | -0.024 |
rier | -0.024 |
isher | -0.023 |
hole | -0.023 |
Token | twins |
Token ID | 20345 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
uster | +0.073 |
rier | +0.070 |
bars | +0.068 |
dollars | +0.066 |
hole | +0.065 |
Neg logit contributions | |
joke | -0.053 |
play | -0.052 |
chat | -0.051 |
eat | -0.048 |
laugh | -0.046 |
Token | g |
Token ID | 308 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
joke | +0.114 |
fl | +0.111 |
sport | +0.109 |
exercise | +0.108 |
| | +0.108 |
Neg logit contributions | |
bars | -0.155 |
hole | -0.151 |
rier | -0.141 |
dollars | -0.134 |
uster | -0.132 |
Token | iggle |
Token ID | 24082 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
joke | +0.102 |
play | +0.099 |
chat | +0.094 |
eat | +0.089 |
walk | +0.082 |
Neg logit contributions | |
uster | -0.208 |
bars | -0.193 |
rier | -0.192 |
hole | -0.188 |
isher | -0.188 |
Token | . |
Token ID | 13 |
Feature activation | +6.83e-03 |
Pos logit contributions | |
joke | +0.035 |
swamp | +0.033 |
chat | +0.032 |
discover | +0.031 |
play | +0.031 |
Neg logit contributions | |
rier | -0.028 |
uster | -0.027 |
bars | -0.025 |
dollars | -0.025 |
hole | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
uster | +0.013 |
bars | +0.012 |
rier | +0.012 |
hole | +0.012 |
mith | +0.012 |
Neg logit contributions | |
joke | -0.011 |
chat | -0.010 |
play | -0.010 |
eat | -0.010 |
walk | -0.010 |
Token | think |
Token ID | 892 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
joke | +0.092 |
sport | +0.084 |
fl | +0.083 |
| | +0.083 |
conversation | +0.081 |
Neg logit contributions | |
bars | -0.143 |
hole | -0.139 |
uster | -0.138 |
rier | -0.132 |
dollars | -0.132 |
Token | was |
Token ID | 373 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
sip | +0.036 |
joke | +0.034 |
chat | +0.033 |
swamp | +0.032 |
eat | +0.032 |
Neg logit contributions | |
bars | -0.026 |
uster | -0.026 |
belt | -0.024 |
ubby | -0.024 |
hole | -0.024 |
Token | three |
Token ID | 1115 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
joke | +0.035 |
play | +0.033 |
chat | +0.032 |
eat | +0.031 |
sip | +0.031 |
Neg logit contributions | |
uster | -0.049 |
bars | -0.046 |
rier | -0.045 |
dollars | -0.044 |
hole | -0.044 |
Token | years |
Token ID | 812 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
uster | +0.042 |
bars | +0.039 |
rier | +0.039 |
dollars | +0.038 |
hole | +0.038 |
Neg logit contributions | |
joke | -0.045 |
play | -0.044 |
chat | -0.042 |
eat | -0.041 |
sip | -0.040 |
Token | old |
Token ID | 1468 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
uster | +0.127 |
hole | +0.125 |
bars | +0.116 |
isher | +0.116 |
rier | +0.116 |
Neg logit contributions | |
play | -0.132 |
eat | -0.119 |
joke | -0.119 |
swamp | -0.116 |
dance | -0.115 |
Token | and |
Token ID | 290 |
Feature activation | +6.83e-04 |
Pos logit contributions | |
uster | +0.179 |
bars | +0.169 |
rier | +0.166 |
dollars | +0.164 |
hole | +0.163 |
Neg logit contributions | |
joke | -0.148 |
play | -0.144 |
chat | -0.137 |
eat | -0.133 |
sip | -0.128 |
Token | very |
Token ID | 845 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
uster | +0.002 |
bars | +0.002 |
rier | +0.002 |
dollars | +0.002 |
hole | +0.002 |
Neg logit contributions | |
joke | -0.001 |
play | -0.001 |
chat | -0.001 |
eat | -0.001 |
sip | -0.001 |
Token | happy |
Token ID | 3772 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
joke | +0.035 |
play | +0.034 |
chat | +0.033 |
eat | +0.031 |
sip | +0.031 |
Neg logit contributions | |
uster | -0.044 |
bars | -0.042 |
rier | -0.042 |
dollars | -0.041 |
hole | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-03 |
Pos logit contributions | |
joke | +0.095 |
sip | +0.089 |
chat | +0.088 |
laugh | +0.086 |
play | +0.085 |
Neg logit contributions | |
uster | -0.072 |
bars | -0.071 |
rier | -0.071 |
dollars | -0.068 |
hole | -0.068 |
Token | One |
Token ID | 1881 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
uster | +0.004 |
bars | +0.003 |
hole | +0.003 |
rier | +0.003 |
dollars | +0.003 |
Neg logit contributions | |
joke | -0.002 |
play | -0.002 |
chat | -0.002 |
eat | -0.002 |
swim | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
uster | +0.076 |
bars | +0.076 |
ubby | +0.072 |
iest | +0.072 |
hole | +0.068 |
Neg logit contributions | |
joke | -0.087 |
chat | -0.086 |
walks | -0.085 |
chase | -0.081 |
jokes | -0.080 |
Token | she |
Token ID | 673 |
Feature activation | -7.61e-03 |
Pos logit contributions | |
joke | +0.069 |
play | +0.069 |
chat | +0.065 |
eat | +0.063 |
sip | +0.060 |
Neg logit contributions | |
uster | -0.089 |
bars | -0.084 |
rier | -0.083 |
dollars | -0.081 |
hole | -0.080 |
Token | jump |
Token ID | 4391 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
uster | +0.005 |
bars | +0.005 |
rier | +0.005 |
hole | +0.005 |
dollars | +0.005 |
Neg logit contributions | |
joke | -0.003 |
chat | -0.003 |
play | -0.002 |
sip | -0.002 |
jokes | -0.002 |
Token | out |
Token ID | 503 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
joke | +0.066 |
play | +0.063 |
chat | +0.060 |
eat | +0.057 |
sip | +0.055 |
Neg logit contributions | |
uster | -0.107 |
bars | -0.101 |
rier | -0.101 |
hole | -0.098 |
dollars | -0.098 |
Token | and |
Token ID | 290 |
Feature activation | +2.95e-03 |
Pos logit contributions | |
uster | +0.022 |
bars | +0.020 |
dollars | +0.019 |
isher | +0.019 |
rier | +0.019 |
Neg logit contributions | |
play | -0.021 |
joke | -0.020 |
eat | -0.019 |
chat | -0.019 |
swim | -0.018 |
Token | say |
Token ID | 910 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
bars | +0.007 |
rier | +0.007 |
hole | +0.007 |
uster | +0.007 |
dollars | +0.006 |
Neg logit contributions | |
joke | -0.003 |
jokes | -0.002 |
chat | -0.002 |
sip | -0.002 |
conversation | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
joke | +0.030 |
play | +0.030 |
chat | +0.028 |
eat | +0.027 |
sip | +0.026 |
Neg logit contributions | |
uster | -0.040 |
bars | -0.038 |
rier | -0.037 |
hole | -0.036 |
dollars | -0.036 |
Token | Boo |
Token ID | 46120 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
uster | +0.123 |
bars | +0.116 |
rier | +0.114 |
dollars | +0.112 |
hole | +0.111 |
Neg logit contributions | |
joke | -0.091 |
play | -0.090 |
chat | -0.084 |
eat | -0.082 |
sip | -0.078 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
joke | +0.469 |
play | +0.462 |
chat | +0.442 |
eat | +0.434 |
sip | +0.419 |
Neg logit contributions | |
uster | -0.328 |
bars | -0.305 |
rier | -0.291 |
hole | -0.287 |
dollars | -0.285 |
Token |
|
Token ID | 198 |
Feature activation | -9.49e-03 |
Pos logit contributions | |
uster | +0.048 |
bars | +0.045 |
rier | +0.044 |
dollars | +0.044 |
hole | +0.043 |
Neg logit contributions | |
joke | -0.034 |
play | -0.031 |
chat | -0.030 |
eat | -0.029 |
laugh | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
play | +0.009 |
joke | +0.009 |
chat | +0.008 |
eat | +0.007 |
swim | +0.007 |
Neg logit contributions | |
uster | -0.026 |
rier | -0.026 |
bars | -0.025 |
dollars | -0.025 |
isher | -0.025 |
Token | One |
Token ID | 3198 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
joke | +0.013 |
play | +0.013 |
chat | +0.012 |
eat | +0.012 |
sip | +0.012 |
Neg logit contributions | |
uster | -0.019 |
bars | -0.018 |
rier | -0.018 |
hole | -0.018 |
dollars | -0.017 |
Token | day |
Token ID | 1110 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
uster | +0.082 |
bars | +0.077 |
hole | +0.074 |
dollars | +0.074 |
ubby | +0.074 |
Neg logit contributions | |
joke | -0.061 |
chat | -0.059 |
play | -0.057 |
sip | -0.054 |
eat | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-03 |
Pos logit contributions | |
joke | +0.241 |
play | +0.231 |
chat | +0.223 |
eat | +0.211 |
sip | +0.204 |
Neg logit contributions | |
uster | -0.321 |
bars | -0.307 |
rier | -0.304 |
dollars | -0.298 |
hole | -0.297 |
Token | |
Token ID | 220 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
uster | +0.002 |
rier | +0.002 |
bars | +0.002 |
hole | +0.002 |
dollars | +0.002 |
Neg logit contributions | |
joke | -0.002 |
chat | -0.002 |
play | -0.002 |
dance | -0.002 |
laugh | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
uster | +0.167 |
rier | +0.159 |
bars | +0.159 |
dollars | +0.159 |
isher | +0.158 |
Neg logit contributions | |
play | -0.056 |
joke | -0.054 |
chat | -0.046 |
eat | -0.046 |
laugh | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | -9.80e-03 |
Pos logit contributions | |
joke | +0.013 |
play | +0.012 |
chat | +0.012 |
eat | +0.011 |
sip | +0.011 |
Neg logit contributions | |
uster | -0.024 |
bars | -0.023 |
rier | -0.022 |
hole | -0.022 |
dollars | -0.022 |
Token | Fred |
Token ID | 30847 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
joke | +0.015 |
play | +0.014 |
chat | +0.014 |
laugh | +0.013 |
dance | +0.013 |
Neg logit contributions | |
uster | -0.020 |
rier | -0.018 |
dollars | -0.018 |
bars | -0.017 |
one | -0.017 |
Token | dy |
Token ID | 9892 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
joke | +0.123 |
play | +0.117 |
chat | +0.114 |
eat | +0.111 |
sip | +0.108 |
Neg logit contributions | |
uster | -0.139 |
dollars | -0.130 |
hole | -0.128 |
isher | -0.127 |
bars | -0.126 |
Token | saw |
Token ID | 2497 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
joke | +0.302 |
play | +0.286 |
chat | +0.272 |
eat | +0.266 |
sip | +0.259 |
Neg logit contributions | |
uster | -0.426 |
bars | -0.402 |
dollars | -0.393 |
rier | -0.389 |
hole | -0.386 |
Token | a |
Token ID | 257 |
Feature activation | -8.27e-03 |
Pos logit contributions | |
uster | +0.060 |
rier | +0.059 |
isher | +0.056 |
one | +0.055 |
ubby | +0.054 |
Neg logit contributions | |
chat | -0.079 |
joke | -0.079 |
| | -0.073 |
play | -0.072 |
walk | -0.072 |
Token | big |
Token ID | 1263 |
Feature activation | +7.78e-03 |
Pos logit contributions | |
play | +0.014 |
joke | +0.013 |
chat | +0.013 |
eat | +0.013 |
walks | +0.012 |
Neg logit contributions | |
uster | -0.016 |
rier | -0.015 |
dollars | -0.014 |
bars | -0.014 |
hole | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
uster | +0.016 |
rier | +0.015 |
bars | +0.015 |
dollars | +0.015 |
hole | +0.015 |
Neg logit contributions | |
joke | -0.012 |
play | -0.011 |
chat | -0.011 |
eat | -0.010 |
sip | -0.010 |
Token | juicy |
Token ID | 35075 |
Feature activation | -4.69e-03 |
Pos logit contributions | |
uster | +0.005 |
bars | +0.004 |
rier | +0.004 |
dollars | +0.004 |
hole | +0.004 |
Neg logit contributions | |
joke | -0.004 |
play | -0.004 |
chat | -0.004 |
eat | -0.003 |
sip | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -5.93e-03 |
Pos logit contributions | |
joke | +0.090 |
play | +0.089 |
chat | +0.083 |
eat | +0.081 |
sip | +0.077 |
Neg logit contributions | |
uster | -0.139 |
bars | -0.132 |
rier | -0.130 |
dollars | -0.128 |
hole | -0.127 |
Token | She |
Token ID | 1375 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
joke | +0.010 |
play | +0.010 |
chat | +0.010 |
eat | +0.009 |
sip | +0.009 |
Neg logit contributions | |
uster | -0.012 |
bars | -0.011 |
rier | -0.011 |
hole | -0.010 |
dollars | -0.010 |
Token | knew |
Token ID | 2993 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
joke | +0.032 |
play | +0.031 |
chat | +0.029 |
eat | +0.028 |
sip | +0.027 |
Neg logit contributions | |
uster | -0.053 |
bars | -0.050 |
rier | -0.049 |
dollars | -0.049 |
hole | -0.049 |
Token | where |
Token ID | 810 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
uster | +0.045 |
bars | +0.043 |
rier | +0.042 |
hole | +0.042 |
dollars | +0.041 |
Neg logit contributions | |
play | -0.029 |
joke | -0.028 |
chat | -0.026 |
eat | -0.026 |
swim | -0.025 |
Token | Fur |
Token ID | 22384 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
uster | +0.221 |
rier | +0.209 |
bars | +0.205 |
hole | +0.205 |
dollars | +0.203 |
Neg logit contributions | |
play | -0.129 |
joke | -0.126 |
chat | -0.117 |
eat | -0.114 |
swim | -0.107 |
Token | ball |
Token ID | 1894 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
joke | +0.049 |
play | +0.047 |
chat | +0.044 |
eat | +0.044 |
laugh | +0.041 |
Neg logit contributions | |
uster | -0.087 |
bars | -0.082 |
rier | -0.080 |
hole | -0.080 |
dollars | -0.079 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
joke | +0.243 |
play | +0.232 |
chat | +0.218 |
eat | +0.212 |
sip | +0.207 |
Neg logit contributions | |
uster | -0.415 |
bars | -0.400 |
dollars | -0.388 |
hole | -0.387 |
rier | -0.386 |
Token | to |
Token ID | 284 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
joke | +0.025 |
play | +0.025 |
chat | +0.023 |
eat | +0.022 |
sip | +0.021 |
Neg logit contributions | |
uster | -0.037 |
bars | -0.035 |
rier | -0.034 |
dollars | -0.033 |
hole | -0.033 |
Token | go |
Token ID | 467 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
joke | +0.025 |
chat | +0.022 |
sip | +0.021 |
play | +0.020 |
jokes | +0.019 |
Neg logit contributions | |
uster | -0.080 |
bars | -0.077 |
hole | -0.075 |
rier | -0.074 |
dollars | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
joke | +0.084 |
play | +0.083 |
chat | +0.078 |
eat | +0.076 |
sip | +0.072 |
Neg logit contributions | |
uster | -0.117 |
bars | -0.110 |
rier | -0.109 |
dollars | -0.107 |
hole | -0.106 |
Token | quickly |
Token ID | 2952 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
joke | +0.007 |
sip | +0.006 |
| | +0.005 |
chat | +0.005 |
swamp | +0.005 |
Neg logit contributions | |
bars | -0.014 |
hole | -0.012 |
uster | -0.012 |
rier | -0.012 |
dollars | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
play | +0.001 |
joke | +0.001 |
eat | +0.001 |
chat | +0.001 |
walks | +0.001 |
Neg logit contributions | |
uster | -0.002 |
bars | -0.002 |
rier | -0.002 |
hole | -0.002 |
isher | -0.002 |
Token | |
Token ID | 220 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
joke | +0.018 |
chat | +0.017 |
play | +0.017 |
dance | +0.016 |
laugh | +0.016 |
Neg logit contributions | |
uster | -0.019 |
rier | -0.018 |
bars | -0.017 |
hole | -0.017 |
dollars | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
uster | +0.146 |
rier | +0.140 |
bars | +0.140 |
dollars | +0.139 |
isher | +0.138 |
Neg logit contributions | |
play | -0.051 |
joke | -0.049 |
chat | -0.042 |
eat | -0.042 |
laugh | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
joke | +0.020 |
play | +0.019 |
chat | +0.018 |
eat | +0.018 |
laugh | +0.017 |
Neg logit contributions | |
uster | -0.034 |
bars | -0.032 |
hole | -0.031 |
rier | -0.031 |
dollars | -0.031 |
Token | Fred |
Token ID | 30847 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
joke | +0.027 |
chat | +0.026 |
play | +0.026 |
laugh | +0.025 |
dance | +0.024 |
Neg logit contributions | |
uster | -0.022 |
dollars | -0.020 |
rier | -0.020 |
one | -0.019 |
ubby | -0.019 |
Token | dy |
Token ID | 9892 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
joke | +0.146 |
play | +0.140 |
chat | +0.138 |
eat | +0.135 |
sip | +0.134 |
Neg logit contributions | |
uster | -0.148 |
hole | -0.139 |
dollars | -0.139 |
bars | -0.136 |
isher | -0.134 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
joke | +0.323 |
play | +0.297 |
sip | +0.291 |
chat | +0.288 |
eat | +0.286 |
Neg logit contributions | |
uster | -0.398 |
bars | -0.388 |
dollars | -0.376 |
hole | -0.374 |
rier | -0.366 |
Token | to |
Token ID | 284 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
sip | +0.032 |
joke | +0.031 |
chat | +0.031 |
play | +0.030 |
| | +0.030 |
Neg logit contributions | |
bars | -0.024 |
uster | -0.024 |
dollars | -0.022 |
rier | -0.021 |
isher | -0.021 |
Token | watch |
Token ID | 2342 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
fl | +0.027 |
chat | +0.027 |
| | +0.027 |
joke | +0.026 |
sip | +0.025 |
Neg logit contributions | |
uster | -0.070 |
bars | -0.069 |
mith | -0.063 |
hole | -0.063 |
rier | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | +6.19e-03 |
Pos logit contributions | |
joke | +0.057 |
chat | +0.057 |
sip | +0.055 |
play | +0.054 |
eat | +0.052 |
Neg logit contributions | |
uster | -0.067 |
rier | -0.066 |
bars | -0.065 |
hole | -0.060 |
dollars | -0.060 |
Token | light |
Token ID | 1657 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
rier | +0.011 |
uster | +0.011 |
bars | +0.011 |
dollars | +0.010 |
isher | +0.010 |
Neg logit contributions | |
chat | -0.009 |
sip | -0.009 |
play | -0.009 |
eat | -0.009 |
enjoy | -0.009 |
Token | told |
Token ID | 1297 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
play | +0.014 |
joke | +0.013 |
chat | +0.013 |
eat | +0.012 |
sip | +0.012 |
Neg logit contributions | |
uster | -0.022 |
rier | -0.020 |
bars | -0.020 |
dollars | -0.020 |
hole | -0.020 |
Token | them |
Token ID | 606 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
uster | +0.026 |
rier | +0.024 |
bars | +0.024 |
dollars | +0.023 |
mith | +0.023 |
Neg logit contributions | |
joke | -0.022 |
chat | -0.021 |
play | -0.020 |
dance | -0.019 |
sip | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
bars | +0.062 |
uster | +0.061 |
dollars | +0.060 |
rier | +0.059 |
one | +0.054 |
Neg logit contributions | |
play | -0.063 |
chat | -0.062 |
joke | -0.062 |
sip | -0.058 |
| | -0.058 |
Token | stop |
Token ID | 2245 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
joke | +0.051 |
play | +0.048 |
chat | +0.047 |
sip | +0.044 |
eat | +0.044 |
Neg logit contributions | |
uster | -0.086 |
bars | -0.083 |
rier | -0.081 |
hole | -0.079 |
dollars | -0.079 |
Token | qu |
Token ID | 627 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
joke | +0.022 |
play | +0.021 |
chat | +0.020 |
eat | +0.019 |
sip | +0.019 |
Neg logit contributions | |
uster | -0.032 |
rier | -0.030 |
bars | -0.030 |
dollars | -0.029 |
hole | -0.029 |
Token | arre |
Token ID | 9624 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
joke | +0.265 |
chat | +0.264 |
play | +0.261 |
walk | +0.259 |
eat | +0.251 |
Neg logit contributions | |
uster | -0.283 |
ubby | -0.265 |
isher | -0.251 |
dollars | -0.250 |
ac | -0.247 |
Token | lling |
Token ID | 2680 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
play | +0.338 |
joke | +0.337 |
chat | +0.325 |
eat | +0.307 |
sip | +0.301 |
Neg logit contributions | |
uster | -0.375 |
rier | -0.363 |
bars | -0.352 |
hole | -0.346 |
dollars | -0.342 |
Token | and |
Token ID | 290 |
Feature activation | -6.78e-03 |
Pos logit contributions | |
joke | +0.120 |
play | +0.119 |
chat | +0.108 |
eat | +0.106 |
laugh | +0.101 |
Neg logit contributions | |
uster | -0.205 |
bars | -0.193 |
rier | -0.188 |
dollars | -0.187 |
hole | -0.186 |
Token | to |
Token ID | 284 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
joke | +0.009 |
play | +0.009 |
chat | +0.009 |
sip | +0.008 |
eat | +0.008 |
Neg logit contributions | |
uster | -0.014 |
bars | -0.014 |
rier | -0.014 |
dollars | -0.013 |
hole | -0.013 |
Token | share |
Token ID | 2648 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
joke | +0.047 |
chat | +0.044 |
play | +0.044 |
sip | +0.041 |
eat | +0.040 |
Neg logit contributions | |
uster | -0.087 |
bars | -0.082 |
rier | -0.082 |
dollars | -0.080 |
isher | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | +3.72e-03 |
Pos logit contributions | |
joke | +0.117 |
play | +0.113 |
chat | +0.108 |
eat | +0.102 |
sip | +0.098 |
Neg logit contributions | |
uster | -0.188 |
bars | -0.179 |
rier | -0.178 |
dollars | -0.176 |
hole | -0.174 |