TOP ACTIVATIONS
MAX = 0.200

<|endoftext|> M um woke up early . She wanted to make
her little boy went to Church . It was a big
<|endoftext|> T eddy woke up early and he was feeling sleepy
trip , Lily woke up early and got ready easily .
girl named Lucy woke up early in the morning . She
day , she woke up early to see the sunrise .
named Tim my woke up early in the morning . The
day , Benny woke up early and saw that there was
<|endoftext|> M olly woke up early in the morning . She
day , she woke up early and went to school .
. <|endoftext|> Bob woke up early one day feeling alert .
Wednesday , Lily woke up early and saw that her mom
morning , Lily woke up early . She heard Max crying
girl named Lily woke up early today . She was so
day , Lily woke up early and saw that the sun
who wanted to go to church . She got up early
<|endoftext|> M ila woke up early on her birthday morning feeling
girl named Jenny woke up early . She was so excited
. <|endoftext|> Jack woke up early in the morning and he
bear wanted to wake up early . He shook his head

MIN ACTIVATIONS
MIN = -0.213

surprise . He threw a tant rum . He kicked and
stubborn . She throws a tant rum . She kicks and
and Jimmy 's face sc run ched up as he ate
temper and often threw temper tant rums . One day ,
his feet and threw a tant rum . "
and they shared the cr ay ons . They drew nice
paws . So he sc run ched up his face and
the park . Julia sc run ched up her face and
them and never threw a tant rum again . <|endoftext|> Once
. He kept throwing a tant rum . His mom was
the dirt . He sc run ched up his face as
laughed and shared the cr ay ons .
was missing . She sc run ched up her face and
friends and share the cr ay ons and the paper ."
her candy , she sc run ched her eyes tight .
listen . She threw a tant rum in the store .
kept crying and throwing a tant rum . Finally
sad . She threw a tant rum and cried loudly .
and to share the cr ay ons . You can show
They share the cr ay ons and print the plate

INTERVAL 0.097 - 0.200
CONTAINS 0.099%

ste aming pie appeared in front of her . She was
They pretend to be cow boys and robbers . One day
He pretended to be a doctor and fixed Billy 's broken
" So when the sky closes , I won 't be
, there was an old lady . She was very old

INTERVAL -0.006 - 0.097
CONTAINS 58.755%

So , they looked around and found a new spoon that
" Hello , c actus ! Can I sit on you
by heard Tom 's cries . He came to see what
with Be cca , but Be cca was scared so Joe
very scared and she started to cry . Her

INTERVAL -0.110 - -0.006
CONTAINS 41.058%

come home early from work . He sees the smoke and
true and he was playing the best soccer of his life
ran off to play . He never let go of his
. The people wore bright colours and loved to dance .
the air . She said " Y ay , this is

INTERVAL -0.213 - -0.110
CONTAINS 0.088%

to colour with her cr ay ons . She used to
. The little girl was so happy to
and play with the boss y dog again . <|endoftext|> Once
play with the ash tr ay . It is dangerous .
the leaves and scattered them everywhere . S ara
Token<|endoftext|>
Token ID50256
Feature activation+3.53e-02

Pos logit contributions
 ranger+0.043
 years+0.042
 clearing+0.039
 banquet+0.038
 Tooth+0.038
Neg logit contributions
its-0.056
apy-0.055
ower-0.053
ikes-0.052
isel-0.051
TokenM
Token ID44
Feature activation+3.37e-02

Pos logit contributions
 ranger+0.046
 years+0.044
 since+0.044
 Tooth+0.042
 banquet+0.041
Neg logit contributions
its-0.074
ower-0.067
apy-0.067
ikes-0.065
aged-0.064
Tokenum
Token ID388
Feature activation+5.35e-02

Pos logit contributions
 ranger+0.052
 since+0.048
 clearing+0.048
 years+0.046
 Cave+0.046
Neg logit contributions
its-0.065
apy-0.059
ower-0.059
isel-0.056
iggle-0.056
Token woke
Token ID19092
Feature activation+2.17e-02

Pos logit contributions
 ranger+0.064
 years+0.058
 clearing+0.057
 since+0.056
 Tooth+0.055
Neg logit contributions
its-0.121
ower-0.112
apy-0.110
aged-0.110
isel-0.109
Token up
Token ID510
Feature activation+8.81e-02

Pos logit contributions
 ranger+0.038
 years+0.036
 clearing+0.036
 since+0.036
 café+0.035
Neg logit contributions
its-0.037
ower-0.033
apy-0.033
isel-0.033
aged-0.032
Token early
Token ID1903
Feature activation+1.80e-01

Pos logit contributions
 ranger+0.115
 years+0.106
 clearing+0.103
 since+0.103
 café+0.101
Neg logit contributions
its-0.187
ower-0.177
apy-0.174
aged-0.173
ikes-0.169
Token.
Token ID13
Feature activation+5.87e-02

Pos logit contributions
 ranger+0.252
 years+0.227
 clearing+0.217
 since+0.214
 Fairy+0.212
Neg logit contributions
ower-0.353
its-0.347
aged-0.330
apy-0.327
ikes-0.327
Token She
Token ID1375
Feature activation+6.86e-02

Pos logit contributions
 ranger+0.076
 years+0.072
 clearing+0.069
 since+0.069
 café+0.067
Neg logit contributions
its-0.126
ower-0.118
apy-0.115
isel-0.114
aged-0.114
Token wanted
Token ID2227
Feature activation-3.01e-02

Pos logit contributions
 ranger+0.083
 years+0.081
 since+0.078
 clearing+0.078
 café+0.076
Neg logit contributions
its-0.153
ower-0.145
ikes-0.140
isel-0.139
aged-0.137
Token to
Token ID284
Feature activation+2.63e-02

Pos logit contributions
its+0.067
ower+0.063
apy+0.062
aged+0.061
isel+0.061
Neg logit contributions
 ranger-0.036
 years-0.033
 clearing-0.033
 since-0.032
 Tooth-0.031
Token make
Token ID787
Feature activation+2.46e-02

Pos logit contributions
 ranger+0.043
 years+0.042
 café+0.041
 clearing+0.041
 since+0.040
Neg logit contributions
its-0.047
ower-0.045
aged-0.043
ikes-0.042
isel-0.042
Token her
Token ID607
Feature activation+1.19e-02

Pos logit contributions
 ranger+0.054
 since+0.053
 Prince+0.052
 café+0.051
 clearing+0.051
Neg logit contributions
its-0.112
ower-0.104
isel-0.100
ikes-0.100
aged-0.097
Token little
Token ID1310
Feature activation-4.17e-02

Pos logit contributions
 ranger+0.017
 years+0.016
 clearing+0.016
 since+0.016
 café+0.016
Neg logit contributions
its-0.025
ower-0.022
isel-0.022
apy-0.022
ikes-0.022
Token boy
Token ID2933
Feature activation+3.71e-02

Pos logit contributions
its+0.084
ower+0.079
apy+0.077
aged+0.076
isel+0.076
Neg logit contributions
 ranger-0.058
 years-0.055
 clearing-0.054
 since-0.054
 Tooth-0.052
Token went
Token ID1816
Feature activation+1.43e-04

Pos logit contributions
 ranger+0.045
 years+0.042
 clearing+0.041
 Tooth+0.041
 since+0.039
Neg logit contributions
its-0.080
apy-0.076
aged-0.075
ower-0.075
ikes-0.072
Token to
Token ID284
Feature activation+2.93e-02

Pos logit contributions
 years+0.000
 ranger+0.000
 Tooth+0.000
 Fairy+0.000
 since+0.000
Neg logit contributions
its-0.000
ower-0.000
ikes-0.000
aged-0.000
apy-0.000
Token Church
Token ID4564
Feature activation+1.72e-01

Pos logit contributions
 ranger+0.040
 years+0.038
 since+0.036
 clearing+0.035
 Tooth+0.035
Neg logit contributions
its-0.059
apy-0.055
ower-0.055
isel-0.054
ikes-0.053
Token.
Token ID13
Feature activation+4.41e-02

Pos logit contributions
 ranger+0.259
 dentist+0.227
 Tooth+0.226
 grizz+0.223
 years+0.222
Neg logit contributions
its-0.319
ower-0.313
ikes-0.302
apy-0.301
iggle-0.296
Token It
Token ID632
Feature activation+2.85e-03

Pos logit contributions
 years+0.065
 ranger+0.064
 Tooth+0.059
 tale+0.059
 since+0.057
Neg logit contributions
its-0.081
apy-0.081
ower-0.078
isel-0.076
ikes-0.075
Token was
Token ID373
Feature activation+1.82e-02

Pos logit contributions
 ranger+0.004
 years+0.004
 clearing+0.003
 since+0.003
 Prince+0.003
Neg logit contributions
its-0.006
ower-0.006
apy-0.006
aged-0.005
ikes-0.005
Token a
Token ID257
Feature activation+1.88e-02

Pos logit contributions
 ranger+0.026
 enclosure+0.025
 Prince+0.024
 café+0.024
 banquet+0.023
Neg logit contributions
its-0.034
apy-0.032
ower-0.032
aged-0.031
ikes-0.030
Token big
Token ID1263
Feature activation+1.37e-02

Pos logit contributions
 ranger+0.034
 enclosure+0.034
 since+0.033
 years+0.032
mother+0.032
Neg logit contributions
ower-0.026
apy-0.025
its-0.023
ikes-0.021
isel-0.021
Token<|endoftext|>
Token ID50256
Feature activation+3.86e-02

Pos logit contributions
its+0.013
ower+0.012
apy+0.012
aged+0.012
isel+0.012
Neg logit contributions
 ranger-0.006
 years-0.006
 since-0.006
 clearing-0.006
 café-0.005
TokenT
Token ID51
Feature activation-3.80e-03

Pos logit contributions
 ranger+0.050
 years+0.049
 since+0.047
 Tooth+0.046
 dentist+0.045
Neg logit contributions
its-0.079
ower-0.072
apy-0.071
ikes-0.071
oom-0.069
Tokeneddy
Token ID21874
Feature activation+1.20e-02

Pos logit contributions
its+0.007
apy+0.007
ower+0.007
isel+0.007
aged+0.007
Neg logit contributions
 ranger-0.006
 years-0.005
 since-0.005
 Tooth-0.005
 clearing-0.005
Token woke
Token ID19092
Feature activation+2.10e-02

Pos logit contributions
 ranger+0.020
Mrs+0.018
 clearing+0.018
 banquet+0.017
 years+0.017
Neg logit contributions
aged-0.018
its-0.018
ged-0.018
iggle-0.017
apy-0.016
Token up
Token ID510
Feature activation+8.79e-02

Pos logit contributions
 ranger+0.035
 years+0.035
 since+0.034
 clearing+0.034
 Tooth+0.033
Neg logit contributions
its-0.036
ower-0.033
isel-0.032
apy-0.032
aged-0.031
Token early
Token ID1903
Feature activation+1.68e-01

Pos logit contributions
 ranger+0.095
 years+0.089
 since+0.087
 clearing+0.087
 café+0.083
Neg logit contributions
its-0.209
ower-0.195
isel-0.191
apy-0.191
aged-0.189
Token and
Token ID290
Feature activation+5.49e-02

Pos logit contributions
 ranger+0.226
 years+0.206
 clearing+0.198
 Tooth+0.197
 dentist+0.194
Neg logit contributions
ower-0.333
its-0.332
aged-0.320
apy-0.317
ikes-0.315
Token he
Token ID339
Feature activation+4.99e-02

Pos logit contributions
 ranger+0.091
 years+0.088
 since+0.088
 clearing+0.086
 café+0.085
Neg logit contributions
its-0.099
ower-0.091
apy-0.087
isel-0.086
aged-0.086
Token was
Token ID373
Feature activation+2.85e-02

Pos logit contributions
 ranger+0.075
 years+0.071
 clearing+0.069
 since+0.068
 Tooth+0.068
Neg logit contributions
its-0.096
ower-0.089
apy-0.088
aged-0.087
isel-0.087
Token feeling
Token ID4203
Feature activation+1.69e-02

Pos logit contributions
 ranger+0.038
 years+0.035
 since+0.034
 clearing+0.034
 Tooth+0.033
Neg logit contributions
its-0.060
ower-0.057
apy-0.056
aged-0.055
isel-0.054
Token sleepy
Token ID42023
Feature activation+2.34e-02

Pos logit contributions
 ranger+0.027
 enclosure+0.024
 clearing+0.024
 café+0.023
 Tooth+0.023
Neg logit contributions
its-0.030
apy-0.029
aged-0.028
ower-0.028
isel-0.028
Token trip
Token ID5296
Feature activation-1.30e-02

Pos logit contributions
 ranger+0.040
 clearing+0.039
 since+0.039
 Tooth+0.038
 years+0.038
Neg logit contributions
its-0.046
ower-0.044
apy-0.043
aged-0.042
ikes-0.041
Token,
Token ID11
Feature activation+2.18e-02

Pos logit contributions
its+0.028
ower+0.027
aged+0.026
ikes+0.026
apy+0.025
Neg logit contributions
 ranger-0.016
 clearing-0.015
 years-0.015
 Tooth-0.015
 Prince-0.014
Token Lily
Token ID20037
Feature activation+1.38e-02

Pos logit contributions
 years+0.028
 ranger+0.028
 clearing+0.027
 Tooth+0.027
 Cave+0.026
Neg logit contributions
its-0.042
apy-0.041
ower-0.040
aged-0.040
ikes-0.039
Token woke
Token ID19092
Feature activation+4.87e-03

Pos logit contributions
 ranger+0.016
 clearing+0.015
 years+0.015
 Tooth+0.015
 café+0.014
Neg logit contributions
its-0.030
aged-0.029
ower-0.028
apy-0.028
ikes-0.027
Token up
Token ID510
Feature activation+8.51e-02

Pos logit contributions
 ranger+0.009
 years+0.008
 clearing+0.008
 since+0.008
 Tooth+0.008
Neg logit contributions
its-0.008
ower-0.007
apy-0.007
isel-0.007
aged-0.007
Token early
Token ID1903
Feature activation+1.63e-01

Pos logit contributions
 ranger+0.125
 years+0.114
 clearing+0.114
 Tooth+0.112
 Fairy+0.112
Neg logit contributions
its-0.165
ower-0.152
aged-0.151
apy-0.151
iggle-0.145
Token and
Token ID290
Feature activation+4.58e-02

Pos logit contributions
 ranger+0.220
 years+0.204
 Fairy+0.199
 clearing+0.198
 Tooth+0.197
Neg logit contributions
ower-0.302
its-0.300
aged-0.285
ged-0.283
ikes-0.278
Token got
Token ID1392
Feature activation-3.46e-02

Pos logit contributions
 ranger+0.067
 years+0.064
 clearing+0.062
 since+0.061
 Tooth+0.061
Neg logit contributions
its-0.088
apy-0.082
ower-0.082
aged-0.082
isel-0.080
Token ready
Token ID3492
Feature activation+1.02e-02

Pos logit contributions
its+0.063
ower+0.058
apy+0.058
aged+0.057
isel+0.056
Neg logit contributions
 ranger-0.056
 years-0.053
 clearing-0.052
 since-0.052
 café-0.051
Token easily
Token ID3538
Feature activation+6.11e-02

Pos logit contributions
 ranger+0.012
 years+0.011
 since+0.011
 clearing+0.011
 café+0.011
Neg logit contributions
its-0.023
ower-0.022
apy-0.021
isel-0.021
aged-0.021
Token.
Token ID13
Feature activation+1.05e-03

Pos logit contributions
 ranger+0.077
 clearing+0.071
 years+0.070
 Tooth+0.069
 Prince+0.069
Neg logit contributions
its-0.131
ower-0.125
aged-0.119
ikes-0.119
isel-0.118
Token girl
Token ID2576
Feature activation+4.74e-02

Pos logit contributions
its+0.096
ower+0.090
apy+0.088
isel+0.087
aged+0.087
Neg logit contributions
 ranger-0.060
 years-0.057
 clearing-0.056
 since-0.055
 café-0.054
Token named
Token ID3706
Feature activation+6.00e-02

Pos logit contributions
 ranger+0.036
 years+0.032
 clearing+0.031
 since+0.030
 Tooth+0.029
Neg logit contributions
its-0.127
ower-0.120
apy-0.119
aged-0.118
isel-0.117
Token Lucy
Token ID22162
Feature activation+4.04e-02

Pos logit contributions
 ranger+0.057
 since+0.055
 years+0.053
 café+0.049
 clearing+0.049
Neg logit contributions
its-0.153
ower-0.143
isel-0.142
ikes-0.141
apy-0.137
Token woke
Token ID19092
Feature activation+1.74e-02

Pos logit contributions
 years+0.055
 ranger+0.055
 since+0.052
 clearing+0.051
 café+0.051
Neg logit contributions
its-0.084
ower-0.080
ikes-0.079
isel-0.078
apy-0.076
Token up
Token ID510
Feature activation+8.52e-02

Pos logit contributions
 ranger+0.030
 years+0.029
 clearing+0.028
 since+0.028
 Tooth+0.028
Neg logit contributions
its-0.030
ower-0.027
isel-0.027
apy-0.026
aged-0.026
Token early
Token ID1903
Feature activation+1.62e-01

Pos logit contributions
 ranger+0.109
 years+0.103
 clearing+0.100
 since+0.100
 café+0.097
Neg logit contributions
its-0.184
ower-0.172
apy-0.168
isel-0.168
aged-0.166
Token in
Token ID287
Feature activation+2.56e-02

Pos logit contributions
 ranger+0.240
 years+0.218
 clearing+0.216
 Fairy+0.212
 Tooth+0.212
Neg logit contributions
its-0.303
ower-0.302
aged-0.288
apy-0.284
ikes-0.282
Token the
Token ID262
Feature activation+6.51e-02

Pos logit contributions
 ranger+0.043
 since+0.039
 enclosure+0.038
 clearing+0.038
 years+0.038
Neg logit contributions
its-0.044
apy-0.041
aged-0.040
ower-0.039
isel-0.039
Token morning
Token ID3329
Feature activation+7.24e-02

Pos logit contributions
 since+0.102
 ranger+0.101
 years+0.101
 indeed+0.091
 Fairy+0.090
Neg logit contributions
ower-0.110
its-0.108
apy-0.107
aged-0.099
ikes-0.097
Token.
Token ID13
Feature activation+3.82e-02

Pos logit contributions
 ranger+0.117
 grizz+0.104
 clearing+0.102
 Lion+0.100
 years+0.100
Neg logit contributions
ower-0.128
its-0.121
apy-0.119
aged-0.116
iggle-0.115
Token She
Token ID1375
Feature activation+4.67e-02

Pos logit contributions
 ranger+0.041
 years+0.038
 clearing+0.037
 since+0.037
 café+0.036
Neg logit contributions
its-0.091
ower-0.086
isel-0.084
apy-0.083
aged-0.083
Token day
Token ID1110
Feature activation+7.27e-03

Pos logit contributions
 ranger+0.034
 years+0.033
 clearing+0.032
 since+0.032
 Tooth+0.031
Neg logit contributions
its-0.033
ower-0.031
apy-0.030
isel-0.029
aged-0.029
Token,
Token ID11
Feature activation+2.35e-02

Pos logit contributions
 ranger+0.009
 years+0.009
 Tooth+0.008
 clearing+0.008
 café+0.008
Neg logit contributions
apy-0.016
its-0.015
aged-0.015
ower-0.015
isel-0.014
Token she
Token ID673
Feature activation+7.08e-02

Pos logit contributions
 ranger+0.035
 years+0.034
 clearing+0.032
 Tooth+0.032
 café+0.032
Neg logit contributions
its-0.044
apy-0.042
ower-0.042
aged-0.041
ikes-0.040
Token woke
Token ID19092
Feature activation+7.71e-03

Pos logit contributions
 ranger+0.109
 years+0.100
 clearing+0.100
 Tooth+0.099
 since+0.097
Neg logit contributions
its-0.135
aged-0.121
ower-0.121
apy-0.120
isel-0.119
Token up
Token ID510
Feature activation+8.73e-02

Pos logit contributions
 ranger+0.015
 years+0.015
 clearing+0.014
 since+0.014
 café+0.014
Neg logit contributions
its-0.011
ower-0.011
apy-0.010
aged-0.010
ikes-0.010
Token early
Token ID1903
Feature activation+1.62e-01

Pos logit contributions
 ranger+0.125
 years+0.114
 clearing+0.113
 since+0.111
 Tooth+0.109
Neg logit contributions
its-0.173
ower-0.162
aged-0.160
apy-0.159
ikes-0.153
Token to
Token ID284
Feature activation+2.79e-02

Pos logit contributions
 ranger+0.222
 years+0.199
THE+0.192
 Lion+0.191
 Fairy+0.191
Neg logit contributions
ower-0.313
its-0.307
aged-0.293
apy-0.287
ged-0.286
Token see
Token ID766
Feature activation+6.24e-02

Pos logit contributions
 clearing+0.040
 years+0.039
 since+0.038
 Prince+0.038
 Tooth+0.038
Neg logit contributions
its-0.058
ower-0.056
ikes-0.054
aged-0.052
apy-0.051
Token the
Token ID262
Feature activation+5.70e-02

Pos logit contributions
 ranger+0.079
 years+0.075
 clearing+0.073
 since+0.073
 Tooth+0.070
Neg logit contributions
its-0.137
ower-0.129
apy-0.125
isel-0.124
aged-0.124
Token sunrise
Token ID40048
Feature activation+9.90e-02

Pos logit contributions
 ranger+0.082
 since+0.079
 years+0.077
 clearing+0.075
 café+0.073
Neg logit contributions
its-0.110
ower-0.104
ikes-0.097
apy-0.096
aged-0.092
Token.
Token ID13
Feature activation+7.17e-03

Pos logit contributions
 ranger+0.133
 years+0.124
 Tooth+0.123
 clearing+0.122
 Prince+0.122
Neg logit contributions
its-0.201
ower-0.194
apy-0.188
ikes-0.182
aged-0.181
Token named
Token ID3706
Feature activation+6.00e-02

Pos logit contributions
 ranger+0.037
 years+0.033
 clearing+0.032
 since+0.031
 café+0.030
Neg logit contributions
its-0.139
ower-0.132
apy-0.130
aged-0.129
isel-0.129
Token Tim
Token ID5045
Feature activation-5.46e-03

Pos logit contributions
 ranger+0.096
 since+0.090
 years+0.090
 clearing+0.089
 café+0.087
Neg logit contributions
its-0.114
ower-0.105
apy-0.101
aged-0.101
isel-0.101
Tokenmy
Token ID1820
Feature activation+5.92e-04

Pos logit contributions
its+0.015
apy+0.015
ower+0.014
ikes+0.014
isel+0.014
Neg logit contributions
 ranger-0.004
 years-0.004
 since-0.004
 clearing-0.003
 café-0.003
Token woke
Token ID19092
Feature activation+1.62e-02

Pos logit contributions
 years+0.001
 ranger+0.001
 since+0.001
 clearing+0.001
 awoke+0.001
Neg logit contributions
its-0.001
ower-0.001
ikes-0.001
isel-0.001
apy-0.001
Token up
Token ID510
Feature activation+7.89e-02

Pos logit contributions
 ranger+0.028
 years+0.027
 clearing+0.026
 since+0.026
 Tooth+0.026
Neg logit contributions
its-0.028
ower-0.026
isel-0.025
apy-0.025
aged-0.024
Token early
Token ID1903
Feature activation+1.62e-01

Pos logit contributions
 ranger+0.107
 years+0.101
 clearing+0.099
 since+0.098
 café+0.096
Neg logit contributions
its-0.165
ower-0.154
apy-0.150
aged-0.149
isel-0.148
Token in
Token ID287
Feature activation+1.70e-02

Pos logit contributions
 ranger+0.239
 years+0.219
 clearing+0.213
 Fairy+0.213
 since+0.212
Neg logit contributions
ower-0.297
its-0.294
aged-0.284
apy-0.277
ikes-0.276
Token the
Token ID262
Feature activation+5.09e-02

Pos logit contributions
 ranger+0.024
 since+0.022
 Fairy+0.021
 years+0.021
 clearing+0.021
Neg logit contributions
its-0.034
apy-0.032
isel-0.031
aged-0.031
ower-0.031
Token morning
Token ID3329
Feature activation+6.19e-02

Pos logit contributions
 since+0.084
 ranger+0.084
 years+0.082
 Fairy+0.077
 indeed+0.075
Neg logit contributions
ower-0.080
apy-0.079
its-0.079
ikes-0.073
aged-0.070
Token.
Token ID13
Feature activation+2.42e-02

Pos logit contributions
 ranger+0.100
 grizz+0.087
 years+0.086
 clearing+0.085
 Fairy+0.085
Neg logit contributions
ower-0.110
its-0.102
apy-0.102
aged-0.099
iggle-0.096
Token The
Token ID383
Feature activation+3.17e-02

Pos logit contributions
 ranger+0.019
 clearing+0.016
 café+0.016
 since+0.015
 Tooth+0.014
Neg logit contributions
its-0.066
aged-0.062
ower-0.061
isel-0.060
apy-0.059
Token day
Token ID1110
Feature activation+1.50e-02

Pos logit contributions
 ranger+0.036
 years+0.035
 Tooth+0.034
 Prince+0.034
 clearing+0.033
Neg logit contributions
its-0.023
ower-0.023
apy-0.021
aged-0.020
isel-0.020
Token,
Token ID11
Feature activation+1.88e-02

Pos logit contributions
 ranger+0.010
 since+0.010
 years+0.010
 clearing+0.009
 Prince+0.009
Neg logit contributions
its-0.042
ower-0.039
ikes-0.038
isel-0.038
aged-0.037
Token Benny
Token ID44275
Feature activation-4.78e-02

Pos logit contributions
 ranger+0.022
 since+0.020
 years+0.020
 clearing+0.020
 Prince+0.019
Neg logit contributions
its-0.044
ower-0.041
aged-0.040
isel-0.040
ikes-0.039
Token woke
Token ID19092
Feature activation+7.57e-03

Pos logit contributions
its+0.087
aged+0.084
ower+0.082
iggle+0.077
apy+0.076
Neg logit contributions
 ranger-0.068
 years-0.065
 Tooth-0.064
 clearing-0.063
 banquet-0.063
Token up
Token ID510
Feature activation+8.39e-02

Pos logit contributions
 ranger+0.013
 years+0.013
 clearing+0.013
 since+0.012
 Tooth+0.012
Neg logit contributions
its-0.013
ower-0.012
apy-0.011
isel-0.011
aged-0.011
Token early
Token ID1903
Feature activation+1.61e-01

Pos logit contributions
 ranger+0.115
 years+0.107
 clearing+0.105
 café+0.103
 since+0.103
Neg logit contributions
its-0.171
ower-0.161
aged-0.158
apy-0.156
ikes-0.152
Token and
Token ID290
Feature activation+4.00e-02

Pos logit contributions
 ranger+0.199
 years+0.185
 clearing+0.174
 Fairy+0.172
 Prince+0.172
Neg logit contributions
its-0.337
ower-0.333
aged-0.321
ikes-0.313
apy-0.311
Token saw
Token ID2497
Feature activation+2.39e-02

Pos logit contributions
 ranger+0.061
 years+0.059
 clearing+0.056
 Fairy+0.056
 Tooth+0.056
Neg logit contributions
its-0.072
aged-0.069
apy-0.068
ower-0.068
isel-0.066
Token that
Token ID326
Feature activation+1.84e-02

Pos logit contributions
 ranger+0.031
 years+0.030
 since+0.030
 clearing+0.029
 café+0.029
Neg logit contributions
its-0.049
apy-0.048
aged-0.046
ower-0.046
isel-0.045
Token there
Token ID612
Feature activation-2.77e-02

Pos logit contributions
 years+0.029
 ranger+0.028
 enclosure+0.027
 since+0.027
 café+0.027
Neg logit contributions
apy-0.031
its-0.030
aged-0.029
ower-0.029
isel-0.028
Token was
Token ID373
Feature activation+3.33e-02

Pos logit contributions
its+0.056
apy+0.052
ower+0.051
ikes+0.050
aged+0.050
Neg logit contributions
 ranger-0.039
 years-0.037
 since-0.036
 Tooth-0.036
 clearing-0.036
Token<|endoftext|>
Token ID50256
Feature activation+3.27e-02

Pos logit contributions
its+0.054
apy+0.052
ower+0.050
isel+0.050
ikes+0.049
Neg logit contributions
 ranger-0.041
 years-0.039
 dentist-0.037
 since-0.037
 banquet-0.037
TokenM
Token ID44
Feature activation+3.09e-02

Pos logit contributions
 ranger+0.044
 years+0.043
 since+0.042
 Tooth+0.042
 banquet+0.040
Neg logit contributions
its-0.065
ower-0.059
apy-0.058
ikes-0.058
oom-0.057
Tokenolly
Token ID5098
Feature activation+4.72e-02

Pos logit contributions
 ranger+0.050
 clearing+0.048
 since+0.048
 Prince+0.046
 Cave+0.045
Neg logit contributions
its-0.057
apy-0.051
ower-0.051
iggle-0.049
ikes-0.047
Token woke
Token ID19092
Feature activation+1.43e-02

Pos logit contributions
 ranger+0.071
 clearing+0.065
 Tooth+0.064
 dentist+0.063
 years+0.063
Neg logit contributions
its-0.084
aged-0.080
ower-0.078
apy-0.078
ged-0.075
Token up
Token ID510
Feature activation+7.92e-02

Pos logit contributions
 ranger+0.025
 years+0.024
 since+0.024
 clearing+0.024
 Tooth+0.023
Neg logit contributions
its-0.024
ower-0.022
isel-0.022
apy-0.021
aged-0.021
Token early
Token ID1903
Feature activation+1.61e-01

Pos logit contributions
 ranger+0.094
 years+0.090
 clearing+0.087
 since+0.087
 café+0.084
Neg logit contributions
its-0.179
ower-0.167
isel-0.163
apy-0.163
ikes-0.161
Token in
Token ID287
Feature activation+2.18e-02

Pos logit contributions
 ranger+0.223
 years+0.205
 clearing+0.198
 Tooth+0.195
 since+0.195
Neg logit contributions
its-0.320
ower-0.314
aged-0.301
apy-0.300
ikes-0.294
Token the
Token ID262
Feature activation+5.61e-02

Pos logit contributions
 ranger+0.036
 years+0.030
 dentist+0.030
 Lion+0.030
 grizz+0.030
Neg logit contributions
its-0.038
apy-0.038
isel-0.035
aged-0.035
ower-0.035
Token morning
Token ID3329
Feature activation+6.76e-02

Pos logit contributions
 ranger+0.089
 years+0.084
 since+0.083
 indeed+0.081
 Fairy+0.078
Neg logit contributions
apy-0.089
ower-0.088
its-0.084
aged-0.079
ikes-0.079
Token.
Token ID13
Feature activation+3.20e-02

Pos logit contributions
 ranger+0.101
 grizz+0.087
 years+0.085
 dentist+0.083
 clearing+0.083
Neg logit contributions
ower-0.130
its-0.126
apy-0.124
aged-0.120
iggle-0.117
Token She
Token ID1375
Feature activation+4.85e-02

Pos logit contributions
 ranger+0.045
 years+0.043
 dentist+0.040
 Tooth+0.039
 clearing+0.039
Neg logit contributions
its-0.064
apy-0.061
ower-0.060
isel-0.058
aged-0.058
Token day
Token ID1110
Feature activation-1.32e-02

Pos logit contributions
its+0.090
aged+0.083
isel+0.082
ower+0.082
ikes+0.081
Neg logit contributions
 ranger-0.061
 years-0.059
 clearing-0.058
 café-0.058
 since-0.056
Token,
Token ID11
Feature activation+4.65e-03

Pos logit contributions
its+0.033
ower+0.031
apy+0.030
aged+0.030
isel+0.030
Neg logit contributions
 ranger-0.013
 years-0.012
 clearing-0.011
 since-0.011
 café-0.011
Token she
Token ID673
Feature activation+5.28e-02

Pos logit contributions
 ranger+0.007
 years+0.007
 clearing+0.007
 enclosure+0.006
 café+0.006
Neg logit contributions
its-0.009
apy-0.009
ower-0.008
aged-0.008
ikes-0.008
Token woke
Token ID19092
Feature activation-3.98e-04

Pos logit contributions
 ranger+0.083
 years+0.079
 clearing+0.077
 since+0.077
 café+0.075
Neg logit contributions
its-0.099
ower-0.091
apy-0.089
aged-0.088
isel-0.088
Token up
Token ID510
Feature activation+7.94e-02

Pos logit contributions
its+0.001
ower+0.001
isel+0.001
apy+0.001
ikes+0.001
Neg logit contributions
 ranger-0.001
 years-0.001
 since-0.001
 Tooth-0.001
 clearing-0.001
Token early
Token ID1903
Feature activation+1.59e-01

Pos logit contributions
 ranger+0.106
 years+0.100
 clearing+0.098
 since+0.097
 café+0.095
Neg logit contributions
its-0.168
ower-0.156
apy-0.153
isel-0.151
aged-0.151
Token and
Token ID290
Feature activation+3.73e-02

Pos logit contributions
 ranger+0.205
 years+0.189
 clearing+0.183
 since+0.180
 café+0.177
Neg logit contributions
its-0.338
ower-0.324
aged-0.312
apy-0.312
ikes-0.309
Token went
Token ID1816
Feature activation-2.11e-02

Pos logit contributions
 ranger+0.054
 years+0.052
 clearing+0.050
 since+0.050
 café+0.049
Neg logit contributions
its-0.074
ower-0.069
apy-0.067
isel-0.067
aged-0.067
Token to
Token ID284
Feature activation+1.58e-02

Pos logit contributions
its+0.041
ower+0.039
aged+0.038
apy+0.038
ikes+0.037
Neg logit contributions
 ranger-0.030
 years-0.030
 since-0.028
 Tooth-0.028
 clearing-0.027
Token school
Token ID1524
Feature activation+7.67e-02

Pos logit contributions
 ranger+0.018
 clearing+0.018
 years+0.018
 café+0.018
 Tooth+0.018
Neg logit contributions
its-0.037
ower-0.035
aged-0.033
isel-0.033
apy-0.033
Token.
Token ID13
Feature activation+1.71e-02

Pos logit contributions
 ranger+0.107
 clearing+0.105
 Tooth+0.102
 grizz+0.101
 Fairy+0.100
Neg logit contributions
its-0.147
ower-0.143
ikes-0.139
aged-0.138
apy-0.135
Token.
Token ID13
Feature activation-1.64e-02

Pos logit contributions
its+0.198
aged+0.190
ower+0.188
apy+0.181
ikes+0.179
Neg logit contributions
 clearing-0.121
 ranger-0.121
 Tooth-0.119
 dentist-0.118
 café-0.117
Token<|endoftext|>
Token ID50256
Feature activation+3.63e-02

Pos logit contributions
its+0.032
apy+0.031
ower+0.030
aged+0.030
isel+0.029
Neg logit contributions
 years-0.022
 ranger-0.021
 Tooth-0.021
 since-0.021
 banquet-0.020
TokenBob
Token ID18861
Feature activation+2.80e-02

Pos logit contributions
 ranger+0.045
 years+0.045
 Tooth+0.043
 since+0.043
 dentist+0.042
Neg logit contributions
its-0.076
ower-0.069
apy-0.069
ikes-0.068
oom-0.066
Token woke
Token ID19092
Feature activation+1.63e-02

Pos logit contributions
 ranger+0.039
 years+0.036
 clearing+0.035
 Tooth+0.035
 Prince+0.034
Neg logit contributions
its-0.057
ower-0.053
aged-0.052
apy-0.051
isel-0.051
Token up
Token ID510
Feature activation+7.95e-02

Pos logit contributions
 ranger+0.030
 years+0.028
 clearing+0.028
 since+0.028
 café+0.027
Neg logit contributions
its-0.027
ower-0.024
apy-0.024
isel-0.023
aged-0.023
Token early
Token ID1903
Feature activation+1.59e-01

Pos logit contributions
 ranger+0.099
 years+0.093
 clearing+0.091
 since+0.090
 café+0.088
Neg logit contributions
its-0.175
ower-0.164
apy-0.160
isel-0.159
aged-0.158
Token one
Token ID530
Feature activation+3.09e-02

Pos logit contributions
 ranger+0.219
 years+0.202
 Tooth+0.195
 dentist+0.194
 clearing+0.192
Neg logit contributions
ower-0.310
its-0.310
aged-0.295
apy-0.293
ikes-0.290
Token day
Token ID1110
Feature activation-1.49e-03

Pos logit contributions
 ranger+0.054
 Prince+0.051
 grizz+0.050
 Tooth+0.049
 café+0.048
Neg logit contributions
its-0.051
ower-0.048
apy-0.046
ikes-0.044
iggle-0.043
Token feeling
Token ID4203
Feature activation-3.73e-03

Pos logit contributions
its+0.003
ower+0.003
apy+0.003
aged+0.003
ikes+0.003
Neg logit contributions
 ranger-0.002
 years-0.002
 clearing-0.002
 Tooth-0.002
 café-0.002
Token alert
Token ID7995
Feature activation+1.69e-02

Pos logit contributions
its+0.007
ower+0.007
apy+0.006
isel+0.006
aged+0.006
Neg logit contributions
 ranger-0.006
 years-0.005
 clearing-0.005
 since-0.005
 café-0.005
Token.
Token ID13
Feature activation+3.68e-02

Pos logit contributions
 ranger+0.024
 clearing+0.022
 dentist+0.022
 Tooth+0.021
 café+0.021
Neg logit contributions
its-0.032
ower-0.031
aged-0.031
ikes-0.030
apy-0.029
Token Wednesday
Token ID3583
Feature activation+4.37e-02

Pos logit contributions
 ranger+0.030
 years+0.029
 clearing+0.029
 since+0.028
 Prince+0.028
Neg logit contributions
its-0.025
ower-0.024
apy-0.023
aged-0.022
isel-0.022
Token,
Token ID11
Feature activation+1.04e-02

Pos logit contributions
 years+0.065
 ranger+0.065
 Cave+0.062
 Tooth+0.062
 grizz+0.061
Neg logit contributions
apy-0.075
aged-0.075
ower-0.074
its-0.073
oom-0.072
Token Lily
Token ID20037
Feature activation+1.52e-02

Pos logit contributions
 ranger+0.013
 years+0.012
 since+0.012
 clearing+0.012
 café+0.011
Neg logit contributions
its-0.024
ower-0.022
isel-0.021
apy-0.021
aged-0.021
Token woke
Token ID19092
Feature activation+1.26e-03

Pos logit contributions
 ranger+0.026
 years+0.024
 clearing+0.024
 Tooth+0.023
 Prince+0.023
Neg logit contributions
its-0.026
aged-0.024
ower-0.023
apy-0.023
isel-0.022
Token up
Token ID510
Feature activation+8.11e-02

Pos logit contributions
 ranger+0.002
 years+0.002
 since+0.002
 clearing+0.002
 Tooth+0.002
Neg logit contributions
its-0.002
ower-0.002
isel-0.002
apy-0.002
aged-0.002
Token early
Token ID1903
Feature activation+1.59e-01

Pos logit contributions
 ranger+0.118
 clearing+0.107
 years+0.107
 enclosure+0.106
 café+0.105
Neg logit contributions
its-0.159
ower-0.151
aged-0.148
apy-0.145
ikes-0.141
Token and
Token ID290
Feature activation+4.00e-02

Pos logit contributions
 ranger+0.198
 years+0.181
 clearing+0.174
 Prince+0.170
 Tooth+0.169
Neg logit contributions
its-0.339
ower-0.332
aged-0.319
apy-0.314
ikes-0.314
Token saw
Token ID2497
Feature activation+2.43e-02

Pos logit contributions
 ranger+0.062
 years+0.059
 clearing+0.056
 Tooth+0.055
 Fairy+0.055
Neg logit contributions
its-0.071
apy-0.069
aged-0.068
ower-0.068
isel-0.066
Token that
Token ID326
Feature activation+2.19e-02

Pos logit contributions
 ranger+0.030
 years+0.028
 clearing+0.027
 since+0.027
 café+0.026
Neg logit contributions
its-0.054
ower-0.051
apy-0.050
aged-0.049
isel-0.049
Token her
Token ID607
Feature activation+2.09e-02

Pos logit contributions
 ranger+0.037
 years+0.036
 enclosure+0.035
 clearing+0.034
 since+0.034
Neg logit contributions
apy-0.035
its-0.035
ower-0.033
aged-0.033
ikes-0.032
Token mom
Token ID1995
Feature activation+6.71e-02

Pos logit contributions
 ranger+0.030
 years+0.029
 since+0.029
 clearing+0.028
 café+0.028
Neg logit contributions
its-0.041
ower-0.039
apy-0.038
aged-0.037
isel-0.037
Token morning
Token ID3329
Feature activation+5.22e-02

Pos logit contributions
 ranger+0.070
 Tooth+0.067
 Prince+0.066
 years+0.066
 since+0.066
Neg logit contributions
its-0.054
apy-0.049
ower-0.049
isel-0.046
aged-0.045
Token,
Token ID11
Feature activation+2.13e-02

Pos logit contributions
 ranger+0.075
 years+0.073
 enclosure+0.069
 Tooth+0.068
 dentist+0.067
Neg logit contributions
apy-0.101
aged-0.091
its-0.089
ower-0.089
ged-0.087
Token Lily
Token ID20037
Feature activation+1.92e-02

Pos logit contributions
 ranger+0.030
 years+0.030
 enclosure+0.028
 clearing+0.027
 tale+0.027
Neg logit contributions
apy-0.040
its-0.038
ower-0.037
aged-0.037
ikes-0.036
Token woke
Token ID19092
Feature activation+1.97e-03

Pos logit contributions
 ranger+0.031
 clearing+0.028
 years+0.027
 Tooth+0.027
THE+0.027
Neg logit contributions
its-0.034
aged-0.031
iggle-0.029
ower-0.029
apy-0.028
Token up
Token ID510
Feature activation+8.18e-02

Pos logit contributions
 ranger+0.004
 years+0.004
 clearing+0.004
 since+0.004
 café+0.004
Neg logit contributions
its-0.003
ower-0.003
apy-0.002
aged-0.002
ikes-0.002
Token early
Token ID1903
Feature activation+1.58e-01

Pos logit contributions
 ranger+0.119
 years+0.109
 clearing+0.107
 since+0.106
 café+0.104
Neg logit contributions
its-0.159
ower-0.149
aged-0.147
apy-0.146
iggle-0.143
Token.
Token ID13
Feature activation+1.70e-02

Pos logit contributions
 ranger+0.227
 years+0.208
THE+0.206
 Lion+0.201
 grizz+0.199
Neg logit contributions
ower-0.289
its-0.279
aged-0.269
ged-0.264
iggle-0.263
Token She
Token ID1375
Feature activation+3.99e-02

Pos logit contributions
 ranger+0.021
 years+0.020
 clearing+0.019
 since+0.019
 café+0.019
Neg logit contributions
its-0.037
ower-0.035
apy-0.034
aged-0.034
isel-0.034
Token heard
Token ID2982
Feature activation+4.39e-02

Pos logit contributions
 ranger+0.062
 Prince+0.056
 clearing+0.056
 Tooth+0.055
 since+0.055
Neg logit contributions
its-0.074
apy-0.070
aged-0.068
ower-0.067
isel-0.066
Token Max
Token ID5436
Feature activation+4.85e-04

Pos logit contributions
 ranger+0.057
 years+0.053
 clearing+0.052
 since+0.052
 café+0.050
Neg logit contributions
its-0.092
apy-0.087
ower-0.085
aged-0.085
ikes-0.083
Token crying
Token ID13774
Feature activation-1.68e-02

Pos logit contributions
 ranger+0.001
 years+0.001
 clearing+0.001
 since+0.001
 Tooth+0.001
Neg logit contributions
its-0.001
ower-0.001
apy-0.001
aged-0.001
ikes-0.001
Token girl
Token ID2576
Feature activation+6.42e-02

Pos logit contributions
its+0.086
ower+0.079
aged+0.077
apy+0.077
isel+0.077
Neg logit contributions
 ranger-0.048
 years-0.045
 clearing-0.044
 since-0.044
 café-0.043
Token named
Token ID3706
Feature activation+5.54e-02

Pos logit contributions
 ranger+0.057
 clearing+0.049
 years+0.048
 since+0.048
 Tooth+0.047
Neg logit contributions
its-0.162
ower-0.154
apy-0.153
aged-0.153
isel-0.150
Token Lily
Token ID20037
Feature activation+4.01e-02

Pos logit contributions
 ranger+0.056
 since+0.054
 years+0.052
 clearing+0.050
 café+0.049
Neg logit contributions
its-0.137
ower-0.129
isel-0.127
ikes-0.126
apy-0.124
Token woke
Token ID19092
Feature activation+1.76e-02

Pos logit contributions
 years+0.052
 ranger+0.051
 since+0.051
 clearing+0.048
 café+0.047
Neg logit contributions
its-0.087
ower-0.082
ikes-0.081
apy-0.080
isel-0.080
Token up
Token ID510
Feature activation+8.13e-02

Pos logit contributions
 ranger+0.030
 years+0.029
 clearing+0.029
 since+0.029
 Tooth+0.028
Neg logit contributions
its-0.030
ower-0.028
isel-0.027
apy-0.027
aged-0.026
Token early
Token ID1903
Feature activation+1.58e-01

Pos logit contributions
 ranger+0.109
 years+0.102
 clearing+0.100
 since+0.099
 café+0.097
Neg logit contributions
its-0.172
ower-0.160
apy-0.156
aged-0.155
isel-0.155
Token today
Token ID1909
Feature activation+8.95e-02

Pos logit contributions
 ranger+0.238
 years+0.220
 clearing+0.216
 since+0.214
 Fairy+0.212
Neg logit contributions
ower-0.287
its-0.285
aged-0.276
apy-0.270
ikes-0.265
Token.
Token ID13
Feature activation+3.00e-02

Pos logit contributions
 ranger+0.136
 grizz+0.122
 clearing+0.122
 years+0.118
 cal+0.118
Neg logit contributions
ower-0.163
its-0.161
apy-0.157
aged-0.148
iggle-0.147
Token She
Token ID1375
Feature activation+4.34e-02

Pos logit contributions
 ranger+0.030
 since+0.028
 years+0.028
 clearing+0.027
 café+0.027
Neg logit contributions
its-0.074
ower-0.069
isel-0.068
apy-0.067
aged-0.067
Token was
Token ID373
Feature activation+7.19e-03

Pos logit contributions
 ranger+0.068
 clearing+0.063
 years+0.063
 since+0.062
 café+0.061
Neg logit contributions
its-0.082
ower-0.075
apy-0.075
aged-0.074
isel-0.072
Token so
Token ID523
Feature activation-2.97e-02

Pos logit contributions
 ranger+0.009
 years+0.009
 clearing+0.008
 since+0.008
 Tooth+0.008
Neg logit contributions
its-0.016
ower-0.015
isel-0.015
apy-0.015
ikes-0.015
Token day
Token ID1110
Feature activation+1.23e-02

Pos logit contributions
 ranger+0.027
 years+0.025
 clearing+0.025
 since+0.025
 Tooth+0.024
Neg logit contributions
its-0.024
ower-0.022
apy-0.022
aged-0.021
isel-0.021
Token,
Token ID11
Feature activation+1.46e-02

Pos logit contributions
 ranger+0.010
 years+0.009
 since+0.009
 clearing+0.009
 café+0.008
Neg logit contributions
its-0.033
ower-0.031
isel-0.030
ikes-0.030
aged-0.029
Token Lily
Token ID20037
Feature activation+1.59e-02

Pos logit contributions
 ranger+0.018
 since+0.016
 years+0.016
 clearing+0.016
 café+0.015
Neg logit contributions
its-0.034
ower-0.031
isel-0.031
ikes-0.030
aged-0.030
Token woke
Token ID19092
Feature activation+2.01e-03

Pos logit contributions
 ranger+0.020
 clearing+0.019
 Fairy+0.018
 Tooth+0.018
 years+0.018
Neg logit contributions
its-0.034
aged-0.032
ower-0.032
apy-0.030
ikes-0.030
Token up
Token ID510
Feature activation+8.14e-02

Pos logit contributions
 ranger+0.003
 years+0.003
 since+0.003
 Tooth+0.003
 clearing+0.003
Neg logit contributions
its-0.004
ower-0.003
isel-0.003
apy-0.003
aged-0.003
Token early
Token ID1903
Feature activation+1.57e-01

Pos logit contributions
 ranger+0.102
 years+0.096
 clearing+0.094
 since+0.093
 café+0.091
Neg logit contributions
its-0.178
ower-0.167
apy-0.163
isel-0.162
aged-0.162
Token and
Token ID290
Feature activation+3.87e-02

Pos logit contributions
 ranger+0.182
 years+0.169
 clearing+0.164
 since+0.158
 Tooth+0.157
Neg logit contributions
its-0.351
ower-0.338
aged-0.327
apy-0.324
ikes-0.322
Token saw
Token ID2497
Feature activation+2.28e-02

Pos logit contributions
 ranger+0.060
 years+0.058
 clearing+0.056
 Tooth+0.055
 Fairy+0.054
Neg logit contributions
its-0.070
aged-0.066
apy-0.066
ower-0.066
isel-0.063
Token that
Token ID326
Feature activation+1.96e-02

Pos logit contributions
 ranger+0.028
 years+0.026
 clearing+0.026
 since+0.025
 café+0.025
Neg logit contributions
its-0.051
ower-0.048
apy-0.047
aged-0.046
isel-0.046
Token the
Token ID262
Feature activation+4.10e-02

Pos logit contributions
 ranger+0.033
 years+0.032
 clearing+0.032
 enclosure+0.031
 since+0.031
Neg logit contributions
its-0.033
apy-0.031
ower-0.031
aged-0.030
ikes-0.029
Token sun
Token ID4252
Feature activation+5.00e-02

Pos logit contributions
 ranger+0.060
 years+0.058
 clearing+0.057
 since+0.057
 café+0.054
Neg logit contributions
its-0.080
ower-0.075
ikes-0.072
apy-0.071
aged-0.071
Token who
Token ID508
Feature activation+3.65e-02

Pos logit contributions
 ranger+0.096
 Prince+0.093
 banquet+0.091
 clearing+0.091
 Tooth+0.088
Neg logit contributions
ower-0.161
aged-0.159
its-0.159
apy-0.154
ot-0.152
Token wanted
Token ID2227
Feature activation-4.12e-02

Pos logit contributions
 ranger+0.065
 years+0.062
 clearing+0.061
 since+0.061
 café+0.060
Neg logit contributions
its-0.062
ower-0.057
apy-0.055
isel-0.055
ikes-0.054
Token to
Token ID284
Feature activation+2.77e-02

Pos logit contributions
aged+0.060
apy+0.058
its+0.057
ower+0.054
ubs+0.053
Neg logit contributions
 clearing-0.069
 ranger-0.069
 grizz-0.069
 Fairy-0.067
 enclosure-0.067
Token go
Token ID467
Feature activation+3.28e-02

Pos logit contributions
 ranger+0.048
 café+0.045
 years+0.045
 Tooth+0.044
 dentist+0.044
Neg logit contributions
its-0.049
ower-0.046
aged-0.044
ikes-0.043
isel-0.043
Token to
Token ID284
Feature activation+3.68e-02

Pos logit contributions
 ranger+0.050
 years+0.048
 since+0.047
 clearing+0.046
 Tooth+0.046
Neg logit contributions
its-0.061
ower-0.057
apy-0.056
aged-0.056
ikes-0.056
Token church
Token ID4928
Feature activation+1.57e-01

Pos logit contributions
 ranger+0.049
 years+0.046
 since+0.045
 clearing+0.043
 Fairy+0.042
Neg logit contributions
its-0.075
apy-0.069
ower-0.068
ikes-0.067
isel-0.067
Token.
Token ID13
Feature activation+4.52e-02

Pos logit contributions
 ranger+0.226
 grizz+0.212
 clearing+0.210
 Tooth+0.208
 Fairy+0.206
Neg logit contributions
its-0.294
ower-0.294
ikes-0.281
aged-0.277
apy-0.267
Token She
Token ID1375
Feature activation+5.14e-02

Pos logit contributions
 ranger+0.046
 since+0.042
 years+0.041
 clearing+0.041
 café+0.040
Neg logit contributions
its-0.112
ower-0.105
apy-0.103
isel-0.103
aged-0.102
Token got
Token ID1392
Feature activation-3.25e-02

Pos logit contributions
 years+0.067
 ranger+0.067
 since+0.063
 clearing+0.063
 café+0.062
Neg logit contributions
its-0.111
ower-0.106
isel-0.102
ikes-0.102
apy-0.100
Token up
Token ID510
Feature activation+5.92e-02

Pos logit contributions
its+0.071
ower+0.066
apy+0.065
isel+0.065
aged+0.064
Neg logit contributions
 ranger-0.041
 years-0.039
 clearing-0.037
 since-0.037
 café-0.036
Token early
Token ID1903
Feature activation+1.40e-01

Pos logit contributions
 ranger+0.085
 clearing+0.079
 years+0.076
 since+0.076
 Prince+0.076
Neg logit contributions
its-0.117
ower-0.111
aged-0.109
apy-0.108
ikes-0.105
Token<|endoftext|>
Token ID50256
Feature activation+3.37e-02

Pos logit contributions
its+0.073
ower+0.066
apy+0.066
isel+0.066
ikes+0.065
Neg logit contributions
 ranger-0.048
 banquet-0.045
 café-0.044
 years-0.044
 clearing-0.043
TokenM
Token ID44
Feature activation+2.87e-02

Pos logit contributions
 ranger+0.043
 years+0.042
 since+0.041
 Tooth+0.040
 banquet+0.039
Neg logit contributions
its-0.071
ower-0.064
ikes-0.063
apy-0.063
oom-0.061
Tokenila
Token ID10102
Feature activation+3.86e-02

Pos logit contributions
 ranger+0.045
 clearing+0.044
 since+0.043
 Prince+0.041
 Fairy+0.040
Neg logit contributions
its-0.055
apy-0.049
ower-0.048
iggle-0.048
isel-0.046
Token woke
Token ID19092
Feature activation+1.49e-02

Pos logit contributions
 ranger+0.056
 clearing+0.054
 years+0.051
 Tooth+0.051
 banquet+0.050
Neg logit contributions
its-0.074
aged-0.068
ower-0.068
apy-0.065
isel-0.064
Token up
Token ID510
Feature activation+7.61e-02

Pos logit contributions
 ranger+0.025
 years+0.024
 since+0.024
 clearing+0.024
 Tooth+0.023
Neg logit contributions
its-0.026
isel-0.023
ower-0.023
apy-0.023
aged-0.022
Token early
Token ID1903
Feature activation+1.56e-01

Pos logit contributions
 ranger+0.093
 years+0.091
 since+0.089
 clearing+0.087
 café+0.084
Neg logit contributions
its-0.168
ower-0.156
isel-0.154
apy-0.153
ikes-0.152
Token on
Token ID319
Feature activation+3.71e-04

Pos logit contributions
 ranger+0.211
 years+0.193
 clearing+0.187
 Tooth+0.184
 café+0.183
Neg logit contributions
its-0.312
ower-0.309
aged-0.296
apy-0.294
ikes-0.291
Token her
Token ID607
Feature activation+9.06e-03

Pos logit contributions
 ranger+0.001
 years+0.000
 clearing+0.000
 since+0.000
 grizz+0.000
Neg logit contributions
its-0.001
apy-0.001
ower-0.001
aged-0.001
ikes-0.001
Token birthday
Token ID10955
Feature activation+1.93e-02

Pos logit contributions
 ranger+0.014
 years+0.013
 since+0.013
 clearing+0.013
 café+0.013
Neg logit contributions
its-0.017
ower-0.016
isel-0.016
apy-0.016
aged-0.015
Token morning
Token ID3329
Feature activation+6.81e-02

Pos logit contributions
 ranger+0.028
 grizz+0.025
 clearing+0.025
 cal+0.024
 years+0.024
Neg logit contributions
ower-0.035
its-0.033
ikes-0.033
apy-0.032
iggle-0.032
Token feeling
Token ID4203
Feature activation+9.10e-03

Pos logit contributions
 ranger+0.096
 clearing+0.085
 years+0.083
 grizz+0.082
 Tooth+0.080
Neg logit contributions
ower-0.134
its-0.134
apy-0.128
aged-0.127
ikes-0.123
Token girl
Token ID2576
Feature activation+4.29e-02

Pos logit contributions
its+0.091
ower+0.090
apy+0.088
isel+0.085
aged+0.083
Neg logit contributions
 ranger-0.072
 years-0.072
 since-0.069
 clearing-0.067
 Tooth-0.066
Token named
Token ID3706
Feature activation+5.46e-02

Pos logit contributions
 ranger+0.039
 years+0.034
 clearing+0.034
 since+0.033
 Tooth+0.033
Neg logit contributions
its-0.107
ower-0.101
apy-0.101
aged-0.100
isel-0.099
Token Jenny
Token ID28437
Feature activation+3.05e-02

Pos logit contributions
 ranger+0.057
 since+0.054
 years+0.053
 clearing+0.051
 café+0.050
Neg logit contributions
its-0.134
ower-0.126
isel-0.124
ikes-0.122
apy-0.121
Token woke
Token ID19092
Feature activation+1.34e-02

Pos logit contributions
 ranger+0.041
 years+0.039
 since+0.038
 clearing+0.037
 café+0.037
Neg logit contributions
its-0.065
ower-0.060
apy-0.059
isel-0.059
ikes-0.059
Token up
Token ID510
Feature activation+7.64e-02

Pos logit contributions
 ranger+0.024
 years+0.023
 clearing+0.022
 since+0.022
 Tooth+0.022
Neg logit contributions
its-0.022
ower-0.020
apy-0.020
isel-0.020
aged-0.020
Token early
Token ID1903
Feature activation+1.56e-01

Pos logit contributions
 ranger+0.101
 years+0.095
 clearing+0.093
 since+0.092
 café+0.090
Neg logit contributions
its-0.162
ower-0.152
apy-0.148
aged-0.147
isel-0.145
Token.
Token ID13
Feature activation+3.25e-02

Pos logit contributions
 ranger+0.224
 years+0.203
 clearing+0.202
 Fairy+0.200
 Prince+0.198
Neg logit contributions
ower-0.293
its-0.289
aged-0.278
apy-0.271
ikes-0.270
Token She
Token ID1375
Feature activation+4.29e-02

Pos logit contributions
 ranger+0.035
 years+0.032
 since+0.032
 clearing+0.031
 café+0.031
Neg logit contributions
its-0.077
ower-0.072
apy-0.071
isel-0.070
aged-0.070
Token was
Token ID373
Feature activation+7.25e-03

Pos logit contributions
 ranger+0.065
 years+0.060
 clearing+0.060
 since+0.059
 café+0.058
Neg logit contributions
its-0.083
ower-0.077
apy-0.076
aged-0.075
isel-0.074
Token so
Token ID523
Feature activation-2.96e-02

Pos logit contributions
 ranger+0.010
 years+0.010
 clearing+0.009
 since+0.009
 café+0.009
Neg logit contributions
its-0.015
ower-0.014
isel-0.014
ikes-0.014
apy-0.014
Token excited
Token ID6568
Feature activation-1.81e-02

Pos logit contributions
its+0.068
isel+0.065
ikes+0.064
ged+0.061
uing+0.061
Neg logit contributions
 years-0.033
 ranger-0.029
 café-0.028
 banquet-0.028
 Mrs-0.028
Token.
Token ID13
Feature activation-2.59e-02

Pos logit contributions
its+0.041
ower+0.038
apy+0.037
ikes+0.037
iggle+0.036
Neg logit contributions
 ranger-0.031
 Tooth-0.029
 café-0.029
 clearing-0.028
 dentist-0.028
Token<|endoftext|>
Token ID50256
Feature activation+2.98e-02

Pos logit contributions
its+0.053
apy+0.051
ower+0.049
isel+0.049
ikes+0.049
Neg logit contributions
 ranger-0.035
 café-0.032
 years-0.032
 banquet-0.031
 cafe-0.031
TokenJack
Token ID14295
Feature activation-1.08e-02

Pos logit contributions
 ranger+0.040
 years+0.038
 since+0.037
 Tooth+0.036
 dentist+0.035
Neg logit contributions
its-0.061
ower-0.055
apy-0.055
ikes-0.054
oom-0.053
Token woke
Token ID19092
Feature activation+1.09e-02

Pos logit contributions
its+0.020
ower+0.019
aged+0.018
apy+0.018
isel+0.018
Neg logit contributions
 ranger-0.017
 clearing-0.015
 years-0.015
 Tooth-0.015
 café-0.015
Token up
Token ID510
Feature activation+7.67e-02

Pos logit contributions
 ranger+0.019
 years+0.018
 since+0.018
 clearing+0.018
 Prince+0.017
Neg logit contributions
its-0.019
ower-0.017
isel-0.017
apy-0.017
aged-0.016
Token early
Token ID1903
Feature activation+1.56e-01

Pos logit contributions
 ranger+0.096
 years+0.090
 clearing+0.088
 since+0.087
 café+0.085
Neg logit contributions
its-0.169
ower-0.158
apy-0.154
isel-0.153
aged-0.153
Token in
Token ID287
Feature activation+1.90e-02

Pos logit contributions
 ranger+0.220
 years+0.200
 clearing+0.193
 Tooth+0.193
 café+0.191
Neg logit contributions
ower-0.298
its-0.294
aged-0.282
apy-0.280
ikes-0.279
Token the
Token ID262
Feature activation+5.52e-02

Pos logit contributions
 ranger+0.028
 years+0.024
 Tooth+0.024
 since+0.024
 Fairy+0.024
Neg logit contributions
its-0.036
apy-0.035
isel-0.034
ower-0.033
aged-0.033
Token morning
Token ID3329
Feature activation+6.51e-02

Pos logit contributions
 ranger+0.088
 years+0.083
 since+0.080
 indeed+0.079
 Fairy+0.077
Neg logit contributions
apy-0.088
ower-0.087
its-0.083
ikes-0.079
aged-0.077
Token and
Token ID290
Feature activation+4.40e-02

Pos logit contributions
 ranger+0.096
 grizz+0.082
 years+0.081
 clearing+0.080
 dentist+0.079
Neg logit contributions
ower-0.125
its-0.121
apy-0.119
aged-0.115
ikes-0.113
Token he
Token ID339
Feature activation+4.36e-02

Pos logit contributions
 ranger+0.067
 years+0.063
 clearing+0.062
 since+0.061
 Tooth+0.060
Neg logit contributions
its-0.084
ower-0.078
apy-0.077
aged-0.076
isel-0.075
Token bear
Token ID6842
Feature activation+3.27e-02

Pos logit contributions
 Tooth+0.086
 clearing+0.085
 ranger+0.084
 grizz+0.083
 Prince+0.083
Neg logit contributions
ower-0.107
its-0.106
ikes-0.100
aged-0.100
apy-0.098
Token wanted
Token ID2227
Feature activation-1.08e-03

Pos logit contributions
 ranger+0.042
 years+0.041
 clearing+0.040
 Tooth+0.039
 café+0.039
Neg logit contributions
its-0.067
aged-0.063
ower-0.063
apy-0.062
ikes-0.060
Token to
Token ID284
Feature activation+3.85e-02

Pos logit contributions
its+0.002
apy+0.002
aged+0.002
ower+0.002
ikes+0.002
Neg logit contributions
 clearing-0.001
 ranger-0.001
 years-0.001
 café-0.001
 Tooth-0.001
Token wake
Token ID7765
Feature activation+6.87e-02

Pos logit contributions
 ranger+0.068
 years+0.063
 clearing+0.062
 café+0.061
 since+0.061
Neg logit contributions
its-0.066
ower-0.064
aged-0.060
ikes-0.059
apy-0.059
Token up
Token ID510
Feature activation+7.54e-02

Pos logit contributions
 ranger+0.116
 years+0.110
 clearing+0.108
 since+0.108
 café+0.106
Neg logit contributions
its-0.122
ower-0.112
apy-0.109
isel-0.108
aged-0.107
Token early
Token ID1903
Feature activation+1.55e-01

Pos logit contributions
 ranger+0.100
 clearing+0.093
 years+0.090
 café+0.088
 Tooth+0.088
Neg logit contributions
its-0.153
ower-0.146
apy-0.144
aged-0.139
ikes-0.138
Token.
Token ID13
Feature activation+1.46e-02

Pos logit contributions
 ranger+0.213
 clearing+0.197
 years+0.194
 Fairy+0.188
 enclosure+0.187
Neg logit contributions
its-0.286
ower-0.284
ikes-0.269
aged-0.263
iggle-0.261
Token He
Token ID679
Feature activation+8.97e-03

Pos logit contributions
 years+0.021
 ranger+0.020
 banquet+0.020
 tale+0.020
 Tooth+0.019
Neg logit contributions
apy-0.026
its-0.025
ower-0.025
ikes-0.024
aged-0.024
Token shook
Token ID14682
Feature activation+3.95e-02

Pos logit contributions
 ranger+0.014
 years+0.014
 since+0.013
 Prince+0.013
 Tooth+0.013
Neg logit contributions
its-0.016
apy-0.015
aged-0.014
ower-0.014
isel-0.014
Token his
Token ID465
Feature activation-2.23e-02

Pos logit contributions
 ranger+0.052
 years+0.050
 clearing+0.049
 since+0.049
 café+0.047
Neg logit contributions
its-0.085
ower-0.079
apy-0.076
isel-0.076
ikes-0.076
Token head
Token ID1182
Feature activation-1.79e-02

Pos logit contributions
its+0.036
ower+0.033
apy+0.031
aged+0.031
isel+0.031
Neg logit contributions
 ranger-0.042
 years-0.040
 clearing-0.039
 since-0.039
 café-0.038
Token surprise
Token ID5975
Feature activation-2.61e-02

Pos logit contributions
its+0.029
ower+0.027
ikes+0.025
isel+0.025
apy+0.025
Neg logit contributions
 ranger-0.023
 since-0.023
 years-0.022
 clearing-0.022
 Fairy-0.021
Token.
Token ID13
Feature activation-6.15e-03

Pos logit contributions
its+0.055
ower+0.051
ikes+0.049
apy+0.049
aged+0.048
Neg logit contributions
 clearing-0.033
 ranger-0.032
 years-0.032
 Tooth-0.031
 since-0.030
Token He
Token ID679
Feature activation-1.30e-02

Pos logit contributions
its+0.014
ower+0.013
apy+0.013
isel+0.013
aged+0.013
Neg logit contributions
 ranger-0.007
 years-0.007
 clearing-0.007
 since-0.007
 café-0.007
Token threw
Token ID9617
Feature activation-2.76e-02

Pos logit contributions
its+0.021
aged+0.019
apy+0.018
isel+0.018
ower+0.017
Neg logit contributions
 clearing-0.023
 ranger-0.022
 since-0.022
 Fairy-0.022
 Prince-0.022
Token a
Token ID257
Feature activation-2.54e-02

Pos logit contributions
its+0.062
ower+0.060
apy+0.057
ikes+0.057
aged+0.057
Neg logit contributions
 ranger-0.034
 years-0.031
 since-0.030
 clearing-0.030
 Prince-0.029
Token tant
Token ID24246
Feature activation-2.13e-01

Pos logit contributions
its+0.046
ikes+0.043
ower+0.042
aged+0.042
oving+0.040
Neg logit contributions
 ranger-0.043
 clearing-0.040
 café-0.039
 Prince-0.038
 Tooth-0.038
Tokenrum
Token ID6582
Feature activation-6.09e-02

Pos logit contributions
apy+0.299
its+0.297
inters+0.296
ower+0.286
ikes+0.272
Neg logit contributions
 years-0.406
 ranger-0.375
mother-0.363
 since-0.354
 grizz-0.342
Token.
Token ID13
Feature activation-7.99e-03

Pos logit contributions
its+0.143
ower+0.134
apy+0.131
isel+0.131
aged+0.130
Neg logit contributions
 ranger-0.067
 years-0.063
 since-0.060
 clearing-0.060
 café-0.058
Token He
Token ID679
Feature activation-1.14e-02

Pos logit contributions
its+0.019
ower+0.018
apy+0.018
isel+0.017
aged+0.017
Neg logit contributions
 ranger-0.009
 years-0.008
 clearing-0.008
 since-0.008
 café-0.007
Token kicked
Token ID12165
Feature activation-5.74e-02

Pos logit contributions
its+0.019
aged+0.017
apy+0.017
ower+0.017
isel+0.017
Neg logit contributions
 ranger-0.020
 clearing-0.019
 since-0.019
 years-0.019
 Fairy-0.019
Token and
Token ID290
Feature activation+6.79e-03

Pos logit contributions
its+0.140
ower+0.134
apy+0.130
isel+0.128
ikes+0.128
Neg logit contributions
 ranger-0.060
 years-0.056
 since-0.055
 clearing-0.053
 Prince-0.051
Token stubborn
Token ID24444
Feature activation+7.45e-03

Pos logit contributions
 ranger+0.050
 years+0.048
 since+0.047
 clearing+0.047
 café+0.046
Neg logit contributions
its-0.056
ower-0.051
aged-0.050
apy-0.050
isel-0.049
Token.
Token ID13
Feature activation-1.29e-02

Pos logit contributions
 clearing+0.010
 ranger+0.010
 Tooth+0.009
 Fairy+0.009
 banquet+0.009
Neg logit contributions
its-0.016
ower-0.014
aged-0.014
ikes-0.014
apy-0.013
Token She
Token ID1375
Feature activation+1.27e-02

Pos logit contributions
its+0.029
ower+0.027
apy+0.027
aged+0.026
isel+0.026
Neg logit contributions
 ranger-0.016
 years-0.014
 clearing-0.014
 since-0.014
 café-0.014
Token throws
Token ID12542
Feature activation-4.26e-02

Pos logit contributions
 ranger+0.022
 clearing+0.020
 since+0.020
 years+0.020
 café+0.020
Neg logit contributions
its-0.023
ower-0.020
apy-0.020
isel-0.019
aged-0.019
Token a
Token ID257
Feature activation-3.11e-02

Pos logit contributions
its+0.099
ower+0.098
ikes+0.093
isel+0.093
apy+0.092
Neg logit contributions
 ranger-0.047
 years-0.043
 since-0.042
 clearing-0.042
 Prince-0.041
Token tant
Token ID24246
Feature activation-2.12e-01

Pos logit contributions
its+0.046
ikes+0.045
aged+0.044
ower+0.043
oving+0.042
Neg logit contributions
 ranger-0.061
 café-0.057
 clearing-0.057
 cafe-0.056
 Prince-0.055
Tokenrum
Token ID6582
Feature activation-6.35e-02

Pos logit contributions
inters+0.308
apy+0.307
its+0.295
ower+0.291
isel+0.284
Neg logit contributions
 years-0.399
mother-0.357
 ranger-0.352
 since-0.336
 Fairy-0.326
Token.
Token ID13
Feature activation-1.64e-02

Pos logit contributions
its+0.154
isel+0.145
ower+0.145
apy+0.142
aged+0.140
Neg logit contributions
 ranger-0.064
 years-0.061
 since-0.058
 clearing-0.055
 Tooth-0.053
Token She
Token ID1375
Feature activation+1.25e-02

Pos logit contributions
its+0.039
ower+0.036
apy+0.036
isel+0.035
aged+0.035
Neg logit contributions
 ranger-0.018
 years-0.017
 clearing-0.016
 since-0.016
 café-0.016
Token kicks
Token ID17364
Feature activation-5.97e-02

Pos logit contributions
 ranger+0.023
 clearing+0.022
 since+0.022
 years+0.021
 Fairy+0.021
Neg logit contributions
its-0.022
apy-0.018
isel-0.018
aged-0.018
ower-0.018
Token and
Token ID290
Feature activation-8.52e-03

Pos logit contributions
its+0.147
ower+0.143
isel+0.139
apy+0.138
aged+0.137
Neg logit contributions
 ranger-0.058
 years-0.055
 since-0.054
 Prince-0.050
 clearing-0.050
Token and
Token ID290
Feature activation-1.87e-02

Pos logit contributions
 ranger+0.022
 clearing+0.021
 Tooth+0.020
 Fairy+0.020
 years+0.019
Neg logit contributions
its-0.044
ower-0.042
aged-0.040
apy-0.040
ikes-0.040
Token Jimmy
Token ID12963
Feature activation-4.42e-02

Pos logit contributions
its+0.038
ower+0.036
ikes+0.036
isel+0.035
aged+0.034
Neg logit contributions
 ranger-0.027
 years-0.026
 since-0.026
 Ms-0.024
 indeed-0.023
Token's
Token ID338
Feature activation+6.02e-03

Pos logit contributions
its+0.097
ower+0.090
apy+0.088
isel+0.088
aged+0.087
Neg logit contributions
 ranger-0.055
 years-0.052
 clearing-0.051
 since-0.051
 café-0.049
Token face
Token ID1986
Feature activation-3.40e-03

Pos logit contributions
 ranger+0.009
 years+0.009
 since+0.008
 clearing+0.008
 Tooth+0.008
Neg logit contributions
its-0.012
ower-0.011
ikes-0.011
isel-0.011
apy-0.010
Token sc
Token ID629
Feature activation-4.95e-02

Pos logit contributions
its+0.008
isel+0.007
ower+0.007
ikes+0.007
utes+0.007
Neg logit contributions
 years-0.004
 ranger-0.004
 since-0.004
 café-0.003
 indeed-0.003
Tokenrun
Token ID5143
Feature activation-2.10e-01

Pos logit contributions
its+0.096
ower+0.088
isel+0.087
aged+0.085
apy+0.085
Neg logit contributions
 ranger-0.071
 years-0.066
 enclosure-0.066
 since-0.065
 grizz-0.062
Tokenched
Token ID1740
Feature activation-8.01e-02

Pos logit contributions
ower+0.350
its+0.339
isel+0.331
utes+0.306
iggle+0.302
Neg logit contributions
-0.350
 since-0.345
 years-0.335
 ranger-0.332
Mrs-0.301
Token up
Token ID510
Feature activation+1.53e-02

Pos logit contributions
its+0.173
ower+0.161
isel+0.159
apy+0.157
ikes+0.154
Neg logit contributions
 ranger-0.104
 years-0.100
 since-0.098
 clearing-0.094
 Prince-0.092
Token as
Token ID355
Feature activation-7.19e-02

Pos logit contributions
 ranger+0.019
 clearing+0.018
 Tooth+0.018
 café+0.018
 Fairy+0.018
Neg logit contributions
its-0.032
ower-0.030
apy-0.030
aged-0.030
ikes-0.029
Token he
Token ID339
Feature activation+4.06e-03

Pos logit contributions
its+0.153
ower+0.143
ikes+0.138
aged+0.138
isel+0.138
Neg logit contributions
 ranger-0.096
 years-0.091
 since-0.088
 clearing-0.087
 Tooth-0.085
Token ate
Token ID15063
Feature activation-1.61e-02

Pos logit contributions
 ranger+0.006
 years+0.006
 since+0.005
 clearing+0.005
 café+0.005
Neg logit contributions
its-0.008
ower-0.008
apy-0.007
isel-0.007
ikes-0.007
Token temper
Token ID4124
Feature activation-3.45e-02

Pos logit contributions
its+0.073
apy+0.072
ikes+0.069
ower+0.068
isel+0.067
Neg logit contributions
 ranger-0.062
 years-0.061
 cave-0.056
 dentist-0.055
 café-0.055
Token and
Token ID290
Feature activation-1.79e-02

Pos logit contributions
its+0.083
ower+0.078
apy+0.077
isel+0.077
ikes+0.076
Neg logit contributions
 ranger-0.036
 years-0.034
 since-0.033
 clearing-0.031
 café-0.031
Token often
Token ID1690
Feature activation+4.69e-03

Pos logit contributions
its+0.039
ower+0.036
isel+0.035
ikes+0.035
apy+0.035
Neg logit contributions
 ranger-0.023
 years-0.023
 since-0.022
 clearing-0.021
 café-0.021
Token threw
Token ID9617
Feature activation-1.96e-02

Pos logit contributions
 ranger+0.007
 years+0.006
 since+0.006
 clearing+0.006
 café+0.006
Neg logit contributions
its-0.010
ower-0.009
ikes-0.009
isel-0.009
apy-0.009
Token temper
Token ID4124
Feature activation-3.96e-02

Pos logit contributions
its+0.041
ower+0.039
apy+0.037
ikes+0.037
isel+0.037
Neg logit contributions
 years-0.027
 ranger-0.026
 since-0.026
 clearing-0.025
 Prince-0.025
Token tant
Token ID24246
Feature activation-2.10e-01

Pos logit contributions
its+0.070
ower+0.066
apy+0.064
isel+0.064
ikes+0.063
Neg logit contributions
 ranger-0.065
 years-0.064
 since-0.062
 café-0.058
 clearing-0.058
Tokenrums
Token ID45241
Feature activation-3.97e-02

Pos logit contributions
apy+0.319
inters+0.312
its+0.309
ower+0.303
isel+0.288
Neg logit contributions
 years-0.402
mother-0.356
 since-0.327
 Fairy-0.318
 indeed-0.316
Token.
Token ID13
Feature activation+9.14e-03

Pos logit contributions
its+0.099
isel+0.093
apy+0.090
ower+0.090
aged+0.087
Neg logit contributions
 since-0.038
 years-0.038
 ranger-0.037
 Tooth-0.032
 Prince-0.032
Token One
Token ID1881
Feature activation+7.25e-03

Pos logit contributions
 ranger+0.011
 years+0.010
 clearing+0.010
 since+0.010
 Tooth+0.009
Neg logit contributions
its-0.021
ower-0.019
apy-0.019
isel-0.019
ikes-0.019
Token day
Token ID1110
Feature activation-2.77e-04

Pos logit contributions
 ranger+0.014
 years+0.013
 clearing+0.013
 since+0.013
 Tooth+0.013
Neg logit contributions
its-0.011
ower-0.010
apy-0.010
aged-0.010
isel-0.010
Token,
Token ID11
Feature activation+1.15e-03

Pos logit contributions
its+0.001
apy+0.001
ower+0.001
aged+0.001
isel+0.001
Neg logit contributions
 ranger-0.000
 years-0.000
 clearing-0.000
 Tooth-0.000
 café-0.000
Token his
Token ID465
Feature activation-3.91e-02

Pos logit contributions
 ranger+0.017
 years+0.016
 since+0.016
 Prince+0.015
 clearing+0.014
Neg logit contributions
its-0.039
ower-0.038
ikes-0.037
apy-0.035
isel-0.035
Token feet
Token ID3625
Feature activation-5.67e-02

Pos logit contributions
its+0.070
isel+0.063
apy+0.063
ower+0.063
ikes+0.062
Neg logit contributions
 ranger-0.068
 years-0.064
 enclosure-0.060
 clearing-0.060
 café-0.059
Token and
Token ID290
Feature activation+2.87e-03

Pos logit contributions
its+0.143
ower+0.135
apy+0.133
isel+0.132
aged+0.131
Neg logit contributions
 ranger-0.052
 years-0.048
 since-0.047
 clearing-0.045
 café-0.044
Token threw
Token ID9617
Feature activation-2.22e-02

Pos logit contributions
 ranger+0.005
 years+0.004
 clearing+0.004
 since+0.004
 Tooth+0.004
Neg logit contributions
its-0.005
apy-0.005
aged-0.005
ower-0.005
isel-0.005
Token a
Token ID257
Feature activation-2.25e-02

Pos logit contributions
its+0.048
ower+0.047
ikes+0.044
apy+0.044
aged+0.044
Neg logit contributions
 ranger-0.029
 years-0.027
 clearing-0.026
 since-0.026
 Prince-0.025
Token tant
Token ID24246
Feature activation-2.09e-01

Pos logit contributions
its+0.040
ikes+0.038
ower+0.037
aged+0.037
oving+0.035
Neg logit contributions
 ranger-0.039
 clearing-0.036
 café-0.035
 cafe-0.033
 Prince-0.033
Tokenrum
Token ID6582
Feature activation-5.74e-02

Pos logit contributions
apy+0.315
inters+0.304
its+0.291
ower+0.290
isel+0.278
Neg logit contributions
 years-0.391
mother-0.353
 ranger-0.345
 since-0.327
 Lion-0.321
Token.
Token ID13
Feature activation-8.34e-03

Pos logit contributions
its+0.141
ower+0.131
isel+0.131
apy+0.129
ikes+0.127
Neg logit contributions
 ranger-0.057
 years-0.053
 since-0.051
 clearing-0.048
 café-0.046
Token
Token ID198
Feature activation-2.68e-04

Pos logit contributions
its+0.019
apy+0.018
ower+0.017
aged+0.017
isel+0.017
Neg logit contributions
 years-0.010
 ranger-0.010
 since-0.009
 clearing-0.009
 café-0.009
Token
Token ID198
Feature activation+1.05e-02

Pos logit contributions
its+0.001
ower+0.001
aged+0.001
isel+0.001
apy+0.001
Neg logit contributions
 ranger-0.000
 years-0.000
 clearing-0.000
 since-0.000
 café-0.000
Token"
Token ID1
Feature activation-9.23e-03

Pos logit contributions
 ranger+0.015
 banquet+0.015
 Fairy+0.015
 Tooth+0.015
 years+0.015
Neg logit contributions
its-0.020
apy-0.019
ower-0.018
aged-0.018
isel-0.018
Token and
Token ID290
Feature activation-3.14e-02

Pos logit contributions
 clearing+0.024
 ranger+0.023
 banquet+0.022
 grizz+0.022
 Tooth+0.022
Neg logit contributions
its-0.039
ower-0.036
ikes-0.036
iggle-0.034
aged-0.034
Token they
Token ID484
Feature activation-9.78e-03

Pos logit contributions
its+0.060
aged+0.058
apy+0.058
isel+0.054
ower+0.054
Neg logit contributions
 clearing-0.044
 years-0.044
 ranger-0.043
 enclosure-0.041
 café-0.041
Token shared
Token ID4888
Feature activation-2.51e-02

Pos logit contributions
its+0.020
ower+0.019
ikes+0.018
apy+0.018
isel+0.018
Neg logit contributions
 ranger-0.014
 years-0.013
 since-0.013
 clearing-0.012
 Tooth-0.012
Token the
Token ID262
Feature activation-6.52e-02

Pos logit contributions
its+0.046
ower+0.042
apy+0.041
aged+0.040
isel+0.040
Neg logit contributions
 ranger-0.041
 years-0.039
 clearing-0.039
 since-0.038
 café-0.038
Token cr
Token ID1067
Feature activation-7.69e-02

Pos logit contributions
its+0.122
ower+0.111
apy+0.110
isel+0.109
aged+0.109
Neg logit contributions
 ranger-0.103
 years-0.099
 clearing-0.097
 Tooth-0.096
 since-0.096
Tokenay
Token ID323
Feature activation-2.09e-01

Pos logit contributions
its+0.111
apy+0.103
aged+0.102
isel+0.101
ower+0.101
Neg logit contributions
 ranger-0.142
 years-0.142
 since-0.138
 Fairy-0.136
 Tooth-0.136
Tokenons
Token ID684
Feature activation-9.51e-02

Pos logit contributions
its+0.376
isel+0.367
ower+0.361
inters+0.355
aged+0.354
Neg logit contributions
 years-0.314
 ranger-0.300
mother-0.290
 Fairy-0.282
 Tooth-0.277
Token.
Token ID13
Feature activation-2.89e-02

Pos logit contributions
its+0.180
ower+0.173
apy+0.167
aged+0.165
ikes+0.163
Neg logit contributions
 clearing-0.142
 grizz-0.135
 Tooth-0.135
 ranger-0.133
 café-0.131
Token They
Token ID1119
Feature activation-1.56e-02

Pos logit contributions
its+0.057
ower+0.052
apy+0.052
aged+0.050
ikes+0.049
Neg logit contributions
 ranger-0.043
 years-0.043
 since-0.042
 clearing-0.041
 Fairy-0.040
Token drew
Token ID9859
Feature activation-3.16e-02

Pos logit contributions
its+0.030
ower+0.028
apy+0.027
isel+0.027
aged+0.027
Neg logit contributions
 ranger-0.024
 years-0.023
 clearing-0.022
 since-0.022
 café-0.022
Token nice
Token ID3621
Feature activation-2.49e-02

Pos logit contributions
its+0.064
ower+0.060
apy+0.058
isel+0.058
aged+0.058
Neg logit contributions
 ranger-0.045
 years-0.042
 clearing-0.041
 since-0.041
 café-0.040
Token paws
Token ID49193
Feature activation-4.84e-02

Pos logit contributions
its+0.062
isel+0.057
ower+0.056
ikes+0.056
apy+0.054
Neg logit contributions
 years-0.055
 ranger-0.055
 Tooth-0.051
 clearing-0.051
 café-0.051
Token.
Token ID13
Feature activation+8.66e-03

Pos logit contributions
its+0.122
isel+0.112
ower+0.112
apy+0.112
ikes+0.109
Neg logit contributions
 ranger-0.046
 since-0.046
 years-0.043
 clearing-0.039
 café-0.038
Token So
Token ID1406
Feature activation+5.72e-03

Pos logit contributions
 ranger+0.011
 years+0.011
 since+0.010
 clearing+0.010
 Fairy+0.010
Neg logit contributions
its-0.018
ower-0.017
ikes-0.017
apy-0.017
isel-0.017
Token he
Token ID339
Feature activation-5.36e-03

Pos logit contributions
 ranger+0.009
 café+0.008
 cafe+0.008
 enclosure+0.008
 Tooth+0.008
Neg logit contributions
apy-0.010
aged-0.010
isel-0.010
its-0.009
ower-0.009
Token sc
Token ID629
Feature activation-4.86e-02

Pos logit contributions
its+0.009
ower+0.008
aged+0.008
apy+0.008
isel+0.008
Neg logit contributions
 ranger-0.009
 years-0.009
 clearing-0.009
 since-0.009
 Tooth-0.008
Tokenrun
Token ID5143
Feature activation-2.07e-01

Pos logit contributions
its+0.096
ower+0.090
ikes+0.086
apy+0.084
isel+0.084
Neg logit contributions
 ranger-0.072
 years-0.066
 since-0.065
 clearing-0.064
 enclosure-0.063
Tokenched
Token ID1740
Feature activation-7.46e-02

Pos logit contributions
ower+0.359
its+0.342
ikes+0.315
isel+0.310
apy+0.304
Neg logit contributions
 since-0.354
 years-0.342
 ranger-0.338
 clearing-0.326
-0.325
Token up
Token ID510
Feature activation+2.27e-02

Pos logit contributions
its+0.187
ower+0.177
ikes+0.170
apy+0.167
isel+0.166
Neg logit contributions
 years-0.074
 since-0.073
 Prince-0.072
 ranger-0.072
 Tooth-0.070
Token his
Token ID465
Feature activation-2.34e-02

Pos logit contributions
 ranger+0.028
 clearing+0.026
 café+0.026
 years+0.026
 banquet+0.025
Neg logit contributions
its-0.048
aged-0.045
ower-0.045
apy-0.045
isel-0.044
Token face
Token ID1986
Feature activation+7.62e-03

Pos logit contributions
its+0.047
isel+0.043
ikes+0.041
ower+0.041
apy+0.040
Neg logit contributions
 ranger-0.035
 years-0.034
 clearing-0.033
 since-0.032
 Tooth-0.032
Token and
Token ID290
Feature activation+1.07e-02

Pos logit contributions
 ranger+0.007
 years+0.007
 since+0.007
 clearing+0.006
 café+0.006
Neg logit contributions
its-0.019
ower-0.018
apy-0.017
isel-0.017
aged-0.017
Token the
Token ID262
Feature activation+1.31e-02

Pos logit contributions
its+0.063
ower+0.059
apy+0.058
aged+0.057
isel+0.057
Neg logit contributions
 ranger-0.030
 years-0.029
 clearing-0.028
 since-0.028
 café-0.027
Token park
Token ID3952
Feature activation+4.05e-02

Pos logit contributions
 ranger+0.018
 years+0.017
 since+0.017
 Tooth+0.016
 clearing+0.016
Neg logit contributions
its-0.027
ower-0.025
apy-0.025
aged-0.024
isel-0.024
Token.
Token ID13
Feature activation-1.55e-02

Pos logit contributions
 ranger+0.047
 years+0.045
 clearing+0.044
 Tooth+0.044
 since+0.043
Neg logit contributions
its-0.090
ower-0.086
apy-0.083
aged-0.083
ikes-0.082
Token Julia
Token ID22300
Feature activation+1.07e-02

Pos logit contributions
its+0.030
ower+0.028
apy+0.028
isel+0.027
aged+0.027
Neg logit contributions
 ranger-0.024
 years-0.023
 Tooth-0.022
 clearing-0.022
 since-0.021
Token sc
Token ID629
Feature activation-5.91e-02

Pos logit contributions
 ranger+0.015
 years+0.014
 clearing+0.014
 since+0.014
 Tooth+0.014
Neg logit contributions
its-0.021
ower-0.020
apy-0.020
aged-0.019
isel-0.019
Tokenrun
Token ID5143
Feature activation-2.07e-01

Pos logit contributions
its+0.105
ower+0.095
ikes+0.091
isel+0.088
aged+0.087
Neg logit contributions
 ranger-0.096
 enclosure-0.088
 years-0.088
 since-0.087
 clearing-0.084
Tokenched
Token ID1740
Feature activation-7.88e-02

Pos logit contributions
ower+0.374
its+0.365
ikes+0.334
isel+0.330
aged+0.329
Neg logit contributions
 since-0.329
 years-0.318
 ranger-0.310
 clearing-0.307
-0.305
Token up
Token ID510
Feature activation+1.67e-02

Pos logit contributions
its+0.189
ower+0.174
isel+0.173
ikes+0.169
apy+0.167
Neg logit contributions
 years-0.084
 ranger-0.083
 since-0.082
 Prince-0.078
 clearing-0.078
Token her
Token ID607
Feature activation-2.04e-02

Pos logit contributions
 ranger+0.019
 clearing+0.018
 years+0.018
 Tooth+0.017
 since+0.017
Neg logit contributions
its-0.038
ower-0.035
apy-0.035
aged-0.035
isel-0.034
Token face
Token ID1986
Feature activation+1.85e-03

Pos logit contributions
its+0.040
isel+0.036
ikes+0.034
apy+0.033
oving+0.032
Neg logit contributions
 ranger-0.032
 years-0.031
 since-0.031
 clearing-0.029
 front-0.028
Token and
Token ID290
Feature activation+2.73e-04

Pos logit contributions
 ranger+0.002
 years+0.002
 clearing+0.002
 since+0.002
 café+0.002
Neg logit contributions
its-0.004
ower-0.004
apy-0.004
aged-0.004
isel-0.004
Token them
Token ID606
Feature activation-6.79e-02

Pos logit contributions
 years+0.019
 ranger+0.018
 since+0.017
 Tooth+0.017
 clearing+0.017
Neg logit contributions
its-0.029
ower-0.027
isel-0.027
ikes-0.026
apy-0.026
Token and
Token ID290
Feature activation+7.44e-03

Pos logit contributions
its+0.127
ower+0.123
aged+0.121
ikes+0.117
apy+0.116
Neg logit contributions
 ranger-0.097
 clearing-0.095
 grizz-0.092
 Tooth-0.092
 café-0.090
Token never
Token ID1239
Feature activation-6.43e-04

Pos logit contributions
 ranger+0.011
 years+0.010
 since+0.010
 clearing+0.010
 Tooth+0.009
Neg logit contributions
its-0.015
ower-0.014
apy-0.014
isel-0.014
ikes-0.014
Token threw
Token ID9617
Feature activation-1.61e-02

Pos logit contributions
its+0.001
ower+0.001
apy+0.001
isel+0.001
aged+0.001
Neg logit contributions
 ranger-0.001
 years-0.001
 clearing-0.001
 since-0.001
 café-0.001
Token a
Token ID257
Feature activation-2.52e-02

Pos logit contributions
its+0.028
ower+0.026
apy+0.025
isel+0.025
ikes+0.025
Neg logit contributions
 ranger-0.027
 years-0.027
 since-0.026
 clearing-0.025
 Prince-0.025
Token tant
Token ID24246
Feature activation-2.06e-01

Pos logit contributions
its+0.044
ower+0.041
aged+0.040
ikes+0.040
apy+0.039
Neg logit contributions
 ranger-0.043
 years-0.040
 clearing-0.040
 since-0.040
 café-0.039
Tokenrum
Token ID6582
Feature activation-5.70e-02

Pos logit contributions
apy+0.310
inters+0.305
ower+0.286
its+0.286
isel+0.280
Neg logit contributions
 years-0.398
mother-0.365
 since-0.324
 ranger-0.322
 god-0.319
Token again
Token ID757
Feature activation+5.93e-02

Pos logit contributions
its+0.133
ower+0.125
apy+0.122
isel+0.122
aged+0.121
Neg logit contributions
 ranger-0.063
 years-0.059
 since-0.057
 clearing-0.057
 café-0.055
Token.
Token ID13
Feature activation-1.14e-02

Pos logit contributions
 ranger+0.067
 years+0.062
 clearing+0.061
 since+0.059
 café+0.059
Neg logit contributions
its-0.137
ower-0.129
apy-0.126
aged-0.125
isel-0.124
Token<|endoftext|>
Token ID50256
Feature activation+2.59e-02

Pos logit contributions
its+0.022
ower+0.021
apy+0.021
aged+0.020
ikes+0.020
Neg logit contributions
 years-0.016
 ranger-0.015
 banquet-0.015
 clearing-0.015
 café-0.014
TokenOnce
Token ID7454
Feature activation-2.37e-02

Pos logit contributions
 ranger+0.034
 since+0.032
 years+0.032
 Tooth+0.031
 banquet+0.031
Neg logit contributions
its-0.055
ower-0.049
apy-0.048
ikes-0.048
aged-0.047
Token.
Token ID13
Feature activation-7.92e-03

Pos logit contributions
 clearing+0.108
 ranger+0.105
 Tooth+0.100
 years+0.100
 Fairy+0.100
Neg logit contributions
its-0.178
ower-0.167
aged-0.163
ikes-0.160
apy-0.159
Token He
Token ID679
Feature activation-1.13e-02

Pos logit contributions
its+0.018
ower+0.017
apy+0.017
isel+0.017
aged+0.017
Neg logit contributions
 ranger-0.009
 years-0.009
 clearing-0.008
 since-0.008
 café-0.008
Token kept
Token ID4030
Feature activation-2.42e-02

Pos logit contributions
its+0.018
aged+0.017
apy+0.016
ower+0.015
isel+0.015
Neg logit contributions
 clearing-0.019
 ranger-0.019
 banquet-0.019
 Prince-0.019
 since-0.019
Token throwing
Token ID9644
Feature activation-4.31e-02

Pos logit contributions
its+0.051
ower+0.049
apy+0.047
ikes+0.047
isel+0.047
Neg logit contributions
 ranger-0.033
 years-0.031
 clearing-0.030
 Tooth-0.029
 café-0.029
Token a
Token ID257
Feature activation-2.47e-02

Pos logit contributions
its+0.092
ower+0.087
apy+0.084
isel+0.083
ikes+0.083
Neg logit contributions
 ranger-0.058
 years-0.055
 since-0.053
 clearing-0.052
 Prince-0.051
Token tant
Token ID24246
Feature activation-2.06e-01

Pos logit contributions
its+0.045
ower+0.041
aged+0.041
ikes+0.041
isel+0.040
Neg logit contributions
 ranger-0.041
 clearing-0.039
 café-0.038
 years-0.037
 Prince-0.037
Tokenrum
Token ID6582
Feature activation-5.74e-02

Pos logit contributions
apy+0.295
inters+0.292
its+0.283
ower+0.277
ikes+0.264
Neg logit contributions
 years-0.384
 ranger-0.359
mother-0.348
 since-0.334
 Fairy-0.334
Token.
Token ID13
Feature activation-3.37e-03

Pos logit contributions
its+0.128
ower+0.121
aged+0.118
apy+0.118
ikes+0.117
Neg logit contributions
 ranger-0.068
 clearing-0.065
 years-0.063
 café-0.063
 Tooth-0.062
Token His
Token ID2399
Feature activation-3.13e-02

Pos logit contributions
its+0.008
ower+0.008
apy+0.008
isel+0.007
aged+0.007
Neg logit contributions
 ranger-0.004
 years-0.003
 clearing-0.003
 since-0.003
 café-0.003
Token mom
Token ID1995
Feature activation+2.15e-02

Pos logit contributions
its+0.064
ower+0.059
isel+0.057
apy+0.057
ikes+0.057
Neg logit contributions
 ranger-0.045
 years-0.042
 clearing-0.041
 since-0.040
 café-0.040
Token was
Token ID373
Feature activation+5.79e-03

Pos logit contributions
 ranger+0.032
 clearing+0.032
 banquet+0.030
 Prince+0.030
 Tooth+0.030
Neg logit contributions
its-0.041
aged-0.038
ower-0.037
apy-0.037
isel-0.036
Token the
Token ID262
Feature activation-1.11e-02

Pos logit contributions
its+0.024
ower+0.023
apy+0.022
aged+0.022
isel+0.022
Neg logit contributions
 ranger-0.015
 years-0.015
 clearing-0.014
 since-0.014
 café-0.014
Token dirt
Token ID13647
Feature activation-4.84e-02

Pos logit contributions
its+0.021
ower+0.019
isel+0.019
apy+0.019
aged+0.019
Neg logit contributions
 ranger-0.017
 years-0.016
 since-0.016
 clearing-0.016
 Tooth-0.015
Token.
Token ID13
Feature activation-3.80e-03

Pos logit contributions
its+0.117
ower+0.111
isel+0.110
ikes+0.109
apy+0.109
Neg logit contributions
 ranger-0.049
 years-0.044
 since-0.043
 clearing-0.042
 café-0.040
Token He
Token ID679
Feature activation-1.02e-02

Pos logit contributions
its+0.008
ower+0.008
apy+0.008
isel+0.008
aged+0.008
Neg logit contributions
 ranger-0.005
 years-0.004
 since-0.004
 clearing-0.004
 Tooth-0.004
Token sc
Token ID629
Feature activation-5.34e-02

Pos logit contributions
its+0.020
ower+0.018
apy+0.018
aged+0.018
isel+0.018
Neg logit contributions
 ranger-0.015
 years-0.014
 clearing-0.014
 since-0.014
 café-0.014
Tokenrun
Token ID5143
Feature activation-2.06e-01

Pos logit contributions
its+0.107
ower+0.099
ikes+0.096
apy+0.092
aged+0.090
Neg logit contributions
 ranger-0.074
 enclosure-0.071
 years-0.067
 clearing-0.066
 since-0.065
Tokenched
Token ID1740
Feature activation-7.70e-02

Pos logit contributions
ower+0.346
its+0.327
ikes+0.307
isel+0.306
aged+0.296
Neg logit contributions
 since-0.350
 years-0.336
 ranger-0.335
 clearing-0.329
-0.326
Token up
Token ID510
Feature activation+1.88e-02

Pos logit contributions
its+0.181
ower+0.172
isel+0.164
ikes+0.164
apy+0.163
Neg logit contributions
 ranger-0.088
 years-0.084
 since-0.083
 Prince-0.081
 clearing-0.080
Token his
Token ID465
Feature activation-2.92e-02

Pos logit contributions
 ranger+0.022
 Tooth+0.021
 clearing+0.021
 café+0.021
 years+0.020
Neg logit contributions
its-0.040
ower-0.038
aged-0.038
apy-0.038
isel-0.037
Token face
Token ID1986
Feature activation+1.33e-03

Pos logit contributions
its+0.053
isel+0.047
ower+0.046
apy+0.046
ikes+0.046
Neg logit contributions
 ranger-0.049
 years-0.048
 clearing-0.046
 since-0.045
 enclosure-0.045
Token as
Token ID355
Feature activation-7.45e-02

Pos logit contributions
 ranger+0.001
 years+0.001
 clearing+0.001
 since+0.001
 café+0.001
Neg logit contributions
its-0.003
ower-0.003
apy-0.003
aged-0.003
ikes-0.003
Token laughed
Token ID13818
Feature activation-3.13e-03

Pos logit contributions
its+0.134
ower+0.130
ikes+0.125
isel+0.120
apy+0.119
Neg logit contributions
 since-0.073
 ranger-0.071
 years-0.071
 clearing-0.065
 Fairy-0.064
Token and
Token ID290
Feature activation-1.83e-02

Pos logit contributions
its+0.006
apy+0.006
ower+0.006
ikes+0.006
aged+0.006
Neg logit contributions
 ranger-0.005
 café-0.004
 clearing-0.004
 Tooth-0.004
 enclosure-0.004
Token shared
Token ID4888
Feature activation-1.54e-02

Pos logit contributions
its+0.039
ower+0.036
isel+0.035
apy+0.035
ikes+0.035
Neg logit contributions
 ranger-0.025
 years-0.024
 since-0.023
 clearing-0.023
 café-0.022
Token the
Token ID262
Feature activation-5.79e-02

Pos logit contributions
its+0.031
ower+0.028
apy+0.028
aged+0.028
isel+0.027
Neg logit contributions
 ranger-0.022
 years-0.021
 clearing-0.021
 since-0.020
 Tooth-0.020
Token cr
Token ID1067
Feature activation-6.93e-02

Pos logit contributions
its+0.104
ower+0.097
apy+0.093
ikes+0.092
aged+0.092
Neg logit contributions
 ranger-0.094
 years-0.089
 since-0.087
 clearing-0.087
 café-0.086
Tokenay
Token ID323
Feature activation-2.04e-01

Pos logit contributions
its+0.102
isel+0.093
aged+0.093
apy+0.093
ower+0.092
Neg logit contributions
 ranger-0.128
 years-0.126
 since-0.123
 Fairy-0.122
 Tooth-0.121
Tokenons
Token ID684
Feature activation-8.96e-02

Pos logit contributions
its+0.394
isel+0.383
ower+0.376
inters+0.368
aged+0.368
Neg logit contributions
 years-0.281
 ranger-0.271
 Fairy-0.252
mother-0.250
 since-0.247
Token.
Token ID13
Feature activation-1.72e-02

Pos logit contributions
its+0.175
ower+0.169
apy+0.164
aged+0.161
ikes+0.159
Neg logit contributions
 clearing-0.127
 ranger-0.124
 Tooth-0.122
 grizz-0.120
 dentist-0.119
Token
Token ID220
Feature activation-5.28e-02

Pos logit contributions
its+0.037
apy+0.034
ower+0.034
aged+0.033
isel+0.033
Neg logit contributions
 ranger-0.023
 years-0.021
 clearing-0.020
 since-0.020
 Tooth-0.020
Token
Token ID198
Feature activation-4.25e-03

Pos logit contributions
its+0.155
isel+0.153
ower+0.149
aged+0.147
apy+0.147
Neg logit contributions
 ranger-0.021
 clearing-0.014
 Ms-0.014
 since-0.013
-0.013
Token
Token ID198
Feature activation+5.77e-03

Pos logit contributions
its+0.012
ower+0.012
isel+0.011
aged+0.011
apy+0.011
Neg logit contributions
 ranger-0.003
 clearing-0.002
 years-0.002
 since-0.002
 café-0.002
Token was
Token ID373
Feature activation-1.51e-02

Pos logit contributions
 ranger+0.014
 years+0.014
 since+0.014
 clearing+0.012
 café+0.012
Neg logit contributions
its-0.026
isel-0.024
ower-0.024
ikes-0.023
apy-0.023
Token missing
Token ID4814
Feature activation-3.44e-02

Pos logit contributions
its+0.031
ower+0.029
apy+0.028
aged+0.028
isel+0.028
Neg logit contributions
 ranger-0.021
 years-0.020
 clearing-0.020
 since-0.019
 café-0.019
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
its+0.076
ower+0.072
apy+0.071
aged+0.070
isel+0.069
Neg logit contributions
 ranger-0.041
 years-0.038
 clearing-0.038
 café-0.037
 Tooth-0.037
Token She
Token ID1375
Feature activation+2.11e-02

Pos logit contributions
its+0.021
ower+0.020
apy+0.019
isel+0.019
ikes+0.019
Neg logit contributions
 ranger-0.015
 years-0.015
 clearing-0.014
 Tooth-0.014
 banquet-0.014
Token sc
Token ID629
Feature activation-5.23e-02

Pos logit contributions
 ranger+0.033
 café+0.032
 Tooth+0.032
 clearing+0.031
 cafe+0.031
Neg logit contributions
its-0.037
aged-0.036
apy-0.034
isel-0.033
ower-0.033
Tokenrun
Token ID5143
Feature activation-2.03e-01

Pos logit contributions
its+0.099
ower+0.093
ikes+0.089
apy+0.087
isel+0.087
Neg logit contributions
 ranger-0.079
 years-0.074
 since-0.072
 enclosure-0.070
 clearing-0.070
Tokenched
Token ID1740
Feature activation-7.45e-02

Pos logit contributions
ower+0.299
its+0.292
ikes+0.270
isel+0.265
aged+0.257
Neg logit contributions
 since-0.383
 years-0.371
 ranger-0.369
-0.365
 clearing-0.357
Token up
Token ID510
Feature activation+1.80e-02

Pos logit contributions
its+0.154
ower+0.144
apy+0.139
ikes+0.138
isel+0.137
Neg logit contributions
 ranger-0.102
 since-0.099
 years-0.099
 Prince-0.095
 clearing-0.094
Token her
Token ID607
Feature activation-1.92e-02

Pos logit contributions
 ranger+0.022
 clearing+0.021
 years+0.021
 café+0.020
 Tooth+0.020
Neg logit contributions
its-0.038
ower-0.036
aged-0.036
apy-0.036
isel-0.035
Token face
Token ID1986
Feature activation+1.63e-03

Pos logit contributions
its+0.037
ower+0.034
isel+0.033
apy+0.033
ikes+0.033
Neg logit contributions
 ranger-0.030
 years-0.029
 since-0.028
 clearing-0.027
 Tooth-0.027
Token and
Token ID290
Feature activation+3.48e-03

Pos logit contributions
 ranger+0.002
 years+0.002
 clearing+0.002
 café+0.002
 since+0.001
Neg logit contributions
its-0.004
ower-0.004
apy-0.004
aged-0.004
isel-0.003
Token friends
Token ID2460
Feature activation-1.51e-02

Pos logit contributions
 ranger+0.037
 clearing+0.035
 years+0.034
 since+0.033
 café+0.033
Neg logit contributions
its-0.065
ower-0.061
aged-0.060
ikes-0.059
apy-0.059
Token and
Token ID290
Feature activation-2.75e-02

Pos logit contributions
its+0.018
ower+0.017
ikes+0.016
aged+0.015
oom+0.015
Neg logit contributions
 clearing-0.032
 grizz-0.031
 ranger-0.029
 doorway-0.029
 café-0.029
Token share
Token ID2648
Feature activation+1.76e-03

Pos logit contributions
its+0.050
ower+0.046
isel+0.044
ikes+0.044
apy+0.043
Neg logit contributions
 ranger-0.047
 years-0.045
 since-0.044
 Tooth-0.042
 clearing-0.042
Token the
Token ID262
Feature activation-5.74e-02

Pos logit contributions
 clearing+0.003
 ranger+0.003
 grizz+0.003
 café+0.003
 banquet+0.003
Neg logit contributions
its-0.003
ower-0.003
apy-0.003
ikes-0.003
aged-0.003
Token cr
Token ID1067
Feature activation-7.16e-02

Pos logit contributions
its+0.106
ower+0.096
apy+0.096
isel+0.095
aged+0.093
Neg logit contributions
 ranger-0.093
 years-0.090
 clearing-0.087
 since-0.087
 Tooth-0.086
Tokenay
Token ID323
Feature activation-2.03e-01

Pos logit contributions
its+0.104
apy+0.099
aged+0.098
isel+0.096
ower+0.093
Neg logit contributions
 years-0.131
 ranger-0.130
 since-0.127
 Fairy-0.125
 Tooth-0.124
Tokenons
Token ID684
Feature activation-8.75e-02

Pos logit contributions
its+0.355
isel+0.350
apy+0.333
inters+0.332
aged+0.332
Neg logit contributions
 years-0.321
 ranger-0.307
 Fairy-0.288
 Tooth-0.287
mother-0.287
Token and
Token ID290
Feature activation-3.82e-02

Pos logit contributions
its+0.148
ower+0.145
ikes+0.134
aged+0.131
apy+0.130
Neg logit contributions
 clearing-0.156
 grizz-0.146
 café-0.136
 ranger-0.134
 awoke-0.133
Token the
Token ID262
Feature activation-4.13e-02

Pos logit contributions
its+0.065
apy+0.059
ower+0.059
aged+0.058
isel+0.058
Neg logit contributions
 ranger-0.065
 clearing-0.062
 years-0.062
 café-0.060
 since-0.060
Token paper
Token ID3348
Feature activation-1.43e-02

Pos logit contributions
its+0.073
ower+0.067
apy+0.065
aged+0.064
isel+0.064
Neg logit contributions
 ranger-0.069
 years-0.066
 clearing-0.065
 since-0.065
 café-0.064
Token."
Token ID526
Feature activation-8.02e-03

Pos logit contributions
its+0.026
ower+0.025
apy+0.023
ikes+0.023
aged+0.023
Neg logit contributions
 clearing-0.022
 café-0.021
 ranger-0.021
 years-0.021
 grizz-0.020
Token her
Token ID607
Feature activation-2.69e-02

Pos logit contributions
 ranger+0.060
 years+0.057
 clearing+0.055
 since+0.055
 café+0.054
Neg logit contributions
its-0.084
ower-0.078
apy-0.076
isel-0.076
ikes-0.075
Token candy
Token ID18550
Feature activation+2.85e-02

Pos logit contributions
its+0.056
ower+0.052
apy+0.051
isel+0.051
aged+0.050
Neg logit contributions
 ranger-0.037
 years-0.035
 clearing-0.034
 since-0.034
 café-0.034
Token,
Token ID11
Feature activation-1.74e-02

Pos logit contributions
 ranger+0.029
 years+0.027
 clearing+0.026
 since+0.026
 café+0.025
Neg logit contributions
its-0.068
ower-0.065
apy-0.063
aged-0.063
ikes-0.062
Token she
Token ID673
Feature activation+3.38e-02

Pos logit contributions
its+0.033
apy+0.032
aged+0.031
ower+0.031
isel+0.029
Neg logit contributions
 ranger-0.026
 years-0.024
 enclosure-0.023
 café-0.023
 clearing-0.023
Token sc
Token ID629
Feature activation-4.19e-02

Pos logit contributions
 ranger+0.057
 clearing+0.053
 years+0.052
 Cave+0.051
 café+0.051
Neg logit contributions
its-0.058
aged-0.054
apy-0.053
isel-0.051
ower-0.050
Tokenrun
Token ID5143
Feature activation-2.03e-01

Pos logit contributions
its+0.083
ower+0.077
ikes+0.073
isel+0.073
apy+0.072
Neg logit contributions
 ranger-0.062
 years-0.057
 since-0.056
 clearing-0.056
 café-0.056
Tokenched
Token ID1740
Feature activation-7.43e-02

Pos logit contributions
its+0.321
ower+0.311
isel+0.285
ikes+0.285
apy+0.277
Neg logit contributions
 ranger-0.367
 since-0.361
 years-0.359
 clearing-0.350
 Tooth-0.340
Token her
Token ID607
Feature activation-2.27e-02

Pos logit contributions
its+0.163
ower+0.152
isel+0.147
apy+0.146
ikes+0.146
Neg logit contributions
 ranger-0.096
 since-0.094
 years-0.093
 Prince-0.093
 Tooth-0.093
Token eyes
Token ID2951
Feature activation-3.49e-02

Pos logit contributions
its+0.042
ower+0.040
aged+0.039
apy+0.038
ikes+0.038
Neg logit contributions
 ranger-0.035
 clearing-0.032
 since-0.032
 years-0.032
 café-0.031
Token tight
Token ID5381
Feature activation-2.90e-02

Pos logit contributions
its+0.077
ower+0.073
apy+0.072
aged+0.072
ikes+0.070
Neg logit contributions
 ranger-0.042
 years-0.038
 clearing-0.038
 café-0.036
 Prince-0.036
Token.
Token ID13
Feature activation-8.42e-03

Pos logit contributions
its+0.061
ower+0.058
aged+0.058
ikes+0.056
apy+0.055
Neg logit contributions
 ranger-0.038
 clearing-0.035
 years-0.034
 café-0.034
 banquet-0.033
Token listen
Token ID6004
Feature activation+7.99e-02

Pos logit contributions
 ranger+0.029
 years+0.028
 since+0.028
 café+0.026
 Tooth+0.026
Neg logit contributions
its-0.020
ower-0.019
apy-0.019
aged-0.018
ikes-0.018
Token.
Token ID13
Feature activation-6.68e-03

Pos logit contributions
 clearing+0.107
 ranger+0.104
 Tooth+0.098
 banquet+0.098
 enclosure+0.097
Neg logit contributions
its-0.167
ower-0.157
aged-0.155
ikes-0.149
apy-0.149
Token She
Token ID1375
Feature activation+1.79e-02

Pos logit contributions
its+0.016
ower+0.015
apy+0.015
isel+0.015
aged+0.015
Neg logit contributions
 ranger-0.007
 years-0.007
 since-0.006
 clearing-0.006
 Tooth-0.006
Token threw
Token ID9617
Feature activation-2.42e-02

Pos logit contributions
 clearing+0.032
 ranger+0.030
 banquet+0.030
 Prince+0.030
 Tooth+0.030
Neg logit contributions
its-0.030
aged-0.026
apy-0.024
ower-0.024
isel-0.023
Token a
Token ID257
Feature activation-1.97e-02

Pos logit contributions
its+0.056
ower+0.054
isel+0.051
apy+0.051
ikes+0.051
Neg logit contributions
 ranger-0.028
 years-0.026
 since-0.026
 clearing-0.025
 Prince-0.025
Token tant
Token ID24246
Feature activation-2.02e-01

Pos logit contributions
its+0.023
ower+0.020
ikes+0.020
aged+0.020
isel+0.019
Neg logit contributions
 ranger-0.046
 clearing-0.043
 years-0.043
 café-0.043
 since-0.042
Tokenrum
Token ID6582
Feature activation-5.38e-02

Pos logit contributions
inters+0.286
its+0.280
apy+0.275
ower+0.274
ikes+0.268
Neg logit contributions
 years-0.380
 ranger-0.342
mother-0.342
 since-0.330
 Fairy-0.328
Token in
Token ID287
Feature activation-1.78e-02

Pos logit contributions
its+0.125
ower+0.119
aged+0.116
apy+0.116
ikes+0.114
Neg logit contributions
 ranger-0.060
 clearing-0.056
 years-0.055
 café-0.054
 Tooth-0.053
Token the
Token ID262
Feature activation+2.06e-02

Pos logit contributions
its+0.043
ower+0.042
ikes+0.041
isel+0.040
apy+0.039
Neg logit contributions
 years-0.019
 ranger-0.019
 since-0.018
 clearing-0.017
 café-0.016
Token store
Token ID3650
Feature activation+3.35e-02

Pos logit contributions
 since+0.037
 ranger+0.036
 Fairy+0.036
 Tooth+0.035
 years+0.035
Neg logit contributions
its-0.034
ower-0.029
apy-0.029
isel-0.028
aged-0.028
Token.
Token ID13
Feature activation-8.25e-04

Pos logit contributions
 clearing+0.039
 Tooth+0.038
 Fairy+0.037
 banquet+0.037
 ranger+0.037
Neg logit contributions
its-0.072
ower-0.069
aged-0.068
ikes-0.065
apy-0.064
Token kept
Token ID4030
Feature activation-2.32e-02

Pos logit contributions
 ranger+0.033
 clearing+0.031
 years+0.030
 banquet+0.030
 café+0.030
Neg logit contributions
its-0.035
aged-0.032
ower-0.031
apy-0.031
isel-0.030
Token crying
Token ID13774
Feature activation-4.21e-02

Pos logit contributions
its+0.048
ower+0.044
isel+0.043
apy+0.043
ikes+0.043
Neg logit contributions
 ranger-0.033
 years-0.032
 clearing-0.030
 since-0.030
 Tooth-0.030
Token and
Token ID290
Feature activation+9.09e-03

Pos logit contributions
its+0.102
ower+0.096
apy+0.094
aged+0.094
isel+0.093
Neg logit contributions
 ranger-0.043
 years-0.039
 clearing-0.039
 since-0.038
 café-0.038
Token throwing
Token ID9644
Feature activation-4.06e-02

Pos logit contributions
 ranger+0.012
 years+0.012
 since+0.012
 clearing+0.011
 Tooth+0.011
Neg logit contributions
its-0.019
ower-0.018
ikes-0.018
isel-0.018
apy-0.017
Token a
Token ID257
Feature activation-1.90e-02

Pos logit contributions
its+0.089
ower+0.088
ikes+0.085
isel+0.084
apy+0.081
Neg logit contributions
 years-0.048
 ranger-0.048
 since-0.046
 clearing-0.044
 Prince-0.044
Token tant
Token ID24246
Feature activation-2.02e-01

Pos logit contributions
its+0.028
ikes+0.026
ower+0.025
isel+0.024
aged+0.024
Neg logit contributions
 ranger-0.038
 clearing-0.036
 café-0.036
 years-0.035
 since-0.035
Tokenrum
Token ID6582
Feature activation-5.20e-02

Pos logit contributions
inters+0.284
its+0.281
ower+0.278
apy+0.274
ikes+0.273
Neg logit contributions
 years-0.377
mother-0.345
 since-0.334
 Fairy-0.332
 ranger-0.329
Token.
Token ID13
Feature activation-4.33e-03

Pos logit contributions
its+0.122
ower+0.114
apy+0.112
isel+0.112
aged+0.111
Neg logit contributions
 ranger-0.057
 years-0.054
 since-0.052
 clearing-0.051
 café-0.049
Token
Token ID198
Feature activation+6.29e-03

Pos logit contributions
its+0.011
isel+0.010
ower+0.010
ikes+0.010
apy+0.010
Neg logit contributions
 ranger-0.004
 since-0.004
 years-0.004
 clearing-0.004
 café-0.003
Token
Token ID198
Feature activation+1.58e-02

Pos logit contributions
 ranger+0.003
 years+0.003
 since+0.003
 clearing+0.003
Mrs+0.003
Neg logit contributions
its-0.018
isel-0.017
ower-0.017
aged-0.017
ikes-0.017
TokenFinally
Token ID11158
Feature activation+2.95e-02

Pos logit contributions
 ranger+0.019
 years+0.018
 since+0.018
 clearing+0.017
 café+0.016
Neg logit contributions
its-0.036
isel-0.033
ower-0.033
apy-0.033
ikes-0.032
Token sad
Token ID6507
Feature activation-5.53e-02

Pos logit contributions
 ranger+0.002
 since+0.002
 years+0.002
 café+0.002
 Prince+0.002
Neg logit contributions
its-0.003
ower-0.003
ikes-0.003
isel-0.003
apy-0.003
Token.
Token ID13
Feature activation-1.08e-02

Pos logit contributions
its+0.127
ower+0.120
apy+0.117
aged+0.117
ikes+0.116
Neg logit contributions
 ranger-0.063
 years-0.059
 clearing-0.059
 café-0.057
 since-0.056
Token She
Token ID1375
Feature activation+1.60e-02

Pos logit contributions
its+0.026
ower+0.025
isel+0.024
apy+0.024
aged+0.024
Neg logit contributions
 ranger-0.011
 years-0.010
 since-0.010
 clearing-0.010
 café-0.010
Token threw
Token ID9617
Feature activation-2.61e-02

Pos logit contributions
 ranger+0.028
 clearing+0.027
 years+0.026
 café+0.026
 banquet+0.026
Neg logit contributions
its-0.027
aged-0.024
ower-0.024
apy-0.023
isel-0.023
Token a
Token ID257
Feature activation-1.85e-02

Pos logit contributions
its+0.065
ower+0.063
ikes+0.060
apy+0.059
isel+0.059
Neg logit contributions
 ranger-0.026
 years-0.024
 since-0.024
 clearing-0.023
 Prince-0.023
Token tant
Token ID24246
Feature activation-2.01e-01

Pos logit contributions
its+0.026
ikes+0.024
ower+0.023
aged+0.023
oving+0.022
Neg logit contributions
 ranger-0.039
 clearing-0.037
 café-0.036
 since-0.035
 years-0.035
Tokenrum
Token ID6582
Feature activation-5.36e-02

Pos logit contributions
its+0.281
inters+0.274
ower+0.268
apy+0.267
ikes+0.262
Neg logit contributions
 years-0.388
mother-0.353
 since-0.347
 Fairy-0.345
 ranger-0.345
Token and
Token ID290
Feature activation+2.09e-03

Pos logit contributions
its+0.130
ower+0.122
isel+0.120
apy+0.119
ikes+0.118
Neg logit contributions
 ranger-0.055
 years-0.052
 since-0.050
 clearing-0.049
 café-0.047
Token cried
Token ID16896
Feature activation-1.63e-02

Pos logit contributions
 ranger+0.003
 years+0.003
 since+0.003
 clearing+0.003
 Tooth+0.003
Neg logit contributions
its-0.004
ower-0.004
isel-0.004
ikes-0.004
apy-0.004
Token loudly
Token ID23112
Feature activation+2.62e-02

Pos logit contributions
its+0.042
isel+0.039
ower+0.038
ikes+0.038
apy+0.037
Neg logit contributions
 since-0.015
 years-0.014
 ranger-0.014
 Prince-0.013
 again-0.013
Token.
Token ID13
Feature activation+9.53e-04

Pos logit contributions
 ranger+0.032
 clearing+0.031
 years+0.031
 café+0.029
 Tooth+0.029
Neg logit contributions
its-0.056
ower-0.054
aged-0.053
apy-0.052
ikes-0.051
Token and
Token ID290
Feature activation-1.25e-03

Pos logit contributions
 ranger+0.003
 clearing+0.002
 years+0.002
 Tooth+0.002
 since+0.002
Neg logit contributions
its-0.005
ower-0.005
aged-0.005
apy-0.005
ikes-0.005
Token to
Token ID284
Feature activation-2.95e-02

Pos logit contributions
its+0.002
ower+0.002
apy+0.002
ikes+0.002
isel+0.002
Neg logit contributions
 ranger-0.002
 years-0.002
 since-0.002
 clearing-0.002
 Tooth-0.002
Token share
Token ID2648
Feature activation+1.21e-02

Pos logit contributions
its+0.070
ower+0.068
apy+0.066
isel+0.066
ikes+0.065
Neg logit contributions
 ranger-0.033
 years-0.033
 since-0.030
 Prince-0.030
 Tooth-0.029
Token the
Token ID262
Feature activation-6.02e-02

Pos logit contributions
 clearing+0.017
 ranger+0.017
 Fairy+0.016
 grizz+0.016
 café+0.016
Neg logit contributions
its-0.024
ower-0.021
ikes-0.021
apy-0.021
aged-0.021
Token cr
Token ID1067
Feature activation-6.85e-02

Pos logit contributions
its+0.112
ower+0.103
apy+0.100
aged+0.099
isel+0.099
Neg logit contributions
 ranger-0.095
 years-0.091
 clearing-0.089
 since-0.089
 café-0.087
Tokenay
Token ID323
Feature activation-2.00e-01

Pos logit contributions
its+0.097
apy+0.089
aged+0.087
isel+0.087
ower+0.087
Neg logit contributions
 ranger-0.135
 years-0.132
 since-0.129
 Tooth-0.127
 clearing-0.126
Tokenons
Token ID684
Feature activation-8.52e-02

Pos logit contributions
its+0.328
isel+0.308
apy+0.303
ower+0.302
aged+0.295
Neg logit contributions
 ranger-0.349
 years-0.346
 Tooth-0.321
 since-0.320
 Fairy-0.320
Token.
Token ID13
Feature activation-2.61e-02

Pos logit contributions
its+0.164
ower+0.155
ikes+0.147
aged+0.147
apy+0.145
Neg logit contributions
 clearing-0.129
 grizz-0.120
 ranger-0.120
 café-0.115
 banquet-0.112
Token You
Token ID921
Feature activation-1.86e-02

Pos logit contributions
its+0.046
ikes+0.044
ower+0.043
apy+0.042
aged+0.040
Neg logit contributions
 ranger-0.040
 clearing-0.040
 years-0.039
 banquet-0.038
 café-0.038
Token can
Token ID460
Feature activation+2.46e-03

Pos logit contributions
its+0.033
ower+0.031
apy+0.030
aged+0.030
isel+0.030
Neg logit contributions
 ranger-0.031
 years-0.030
 since-0.029
 clearing-0.028
 Tooth-0.028
Token show
Token ID905
Feature activation+5.33e-02

Pos logit contributions
 ranger+0.004
 years+0.004
 clearing+0.004
 since+0.004
 café+0.004
Neg logit contributions
its-0.004
ower-0.004
apy-0.004
isel-0.004
ikes-0.004
Token
Token ID198
Feature activation-9.77e-03

Pos logit contributions
its+0.060
ower+0.058
isel+0.057
aged+0.057
apy+0.056
Neg logit contributions
 ranger-0.018
 years-0.015
 clearing-0.015
 since-0.014
 Tooth-0.013
TokenThey
Token ID2990
Feature activation-7.81e-04

Pos logit contributions
its+0.017
apy+0.016
ower+0.016
ikes+0.015
aged+0.015
Neg logit contributions
 Prince-0.015
 banquet-0.015
 Tooth-0.015
 Fairy-0.015
 since-0.015
Token share
Token ID2648
Feature activation+4.81e-03

Pos logit contributions
its+0.001
ower+0.001
apy+0.001
ikes+0.001
aged+0.001
Neg logit contributions
 ranger-0.001
 years-0.001
 since-0.001
 clearing-0.001
 Prince-0.001
Token the
Token ID262
Feature activation-6.00e-02

Pos logit contributions
 ranger+0.007
 clearing+0.007
 years+0.006
 Fairy+0.006
 Tooth+0.006
Neg logit contributions
its-0.010
apy-0.009
aged-0.009
ower-0.009
ikes-0.008
Token cr
Token ID1067
Feature activation-6.83e-02

Pos logit contributions
its+0.119
ower+0.110
apy+0.107
aged+0.106
ikes+0.106
Neg logit contributions
 ranger-0.087
 years-0.084
 since-0.082
 clearing-0.081
 café-0.079
Tokenay
Token ID323
Feature activation-2.00e-01

Pos logit contributions
its+0.101
apy+0.097
aged+0.096
isel+0.095
ower+0.095
Neg logit contributions
 ranger-0.121
 years-0.119
 Tooth-0.116
 since-0.116
 Fairy-0.114
Tokenons
Token ID684
Feature activation-8.73e-02

Pos logit contributions
its+0.378
isel+0.370
ower+0.368
apy+0.361
aged+0.360
Neg logit contributions
 ranger-0.279
 years-0.276
 Tooth-0.251
 dentist-0.250
 Prince-0.248
Token and
Token ID290
Feature activation-3.89e-02

Pos logit contributions
its+0.197
ower+0.186
apy+0.181
aged+0.181
ikes+0.176
Neg logit contributions
 ranger-0.099
 clearing-0.098
 Tooth-0.095
 years-0.094
 café-0.092
Token print
Token ID3601
Feature activation+8.22e-03

Pos logit contributions
its+0.062
apy+0.056
ower+0.055
aged+0.055
isel+0.055
Neg logit contributions
 ranger-0.070
 clearing-0.068
 years-0.068
 since-0.066
 Tooth-0.065
Token the
Token ID262
Feature activation-3.12e-02

Pos logit contributions
 ranger+0.011
 years+0.010
 clearing+0.010
 since+0.010
 Prince+0.010
Neg logit contributions
its-0.017
ower-0.017
isel-0.016
apy-0.016
aged-0.016
Token plate
Token ID7480
Feature activation-7.34e-02

Pos logit contributions
its+0.058
ower+0.053
apy+0.051
ikes+0.051
aged+0.050
Neg logit contributions
 ranger-0.049
 years-0.047
 since-0.046
 clearing-0.046
 café-0.045
Token ste
Token ID2876
Feature activation+7.97e-03

Pos logit contributions
its+0.034
apy+0.031
ower+0.031
isel+0.030
aged+0.030
Neg logit contributions
 ranger-0.034
 years-0.033
 since-0.032
 enclosure-0.032
 clearing-0.032
Tokenaming
Token ID3723
Feature activation+1.70e-02

Pos logit contributions
 ranger+0.013
 since+0.012
 café+0.012
 Prince+0.012
 Tooth+0.012
Neg logit contributions
its-0.015
ower-0.014
aged-0.013
apy-0.013
isel-0.013
Token pie
Token ID2508
Feature activation+5.26e-02

Pos logit contributions
 years+0.029
 ranger+0.028
 since+0.028
 Prince+0.028
 clearing+0.027
Neg logit contributions
ower-0.027
its-0.027
apy-0.026
aged-0.025
isel-0.024
Token appeared
Token ID4120
Feature activation+2.61e-04

Pos logit contributions
 ranger+0.062
 years+0.060
 clearing+0.057
 Tooth+0.057
 café+0.056
Neg logit contributions
its-0.117
ower-0.111
apy-0.109
aged-0.108
ikes-0.105
Token in
Token ID287
Feature activation+2.20e-02

Pos logit contributions
 ranger+0.000
 café+0.000
 years+0.000
 Tooth+0.000
 dentist+0.000
Neg logit contributions
its-0.000
ower-0.000
aged-0.000
ikes-0.000
apy-0.000
Token front
Token ID2166
Feature activation+1.00e-01

Pos logit contributions
 ranger+0.032
 enclosure+0.029
 café+0.028
 dentist+0.028
 banquet+0.028
Neg logit contributions
its-0.043
apy-0.038
isel-0.037
aged-0.036
ower-0.036
Token of
Token ID286
Feature activation+1.48e-02

Pos logit contributions
 Tooth+0.197
 Prince+0.197
 ranger+0.187
 Princess+0.186
 Fairy+0.186
Neg logit contributions
its-0.148
apy-0.124
ower-0.120
isel-0.120
aged-0.117
Token her
Token ID607
Feature activation+1.91e-02

Pos logit contributions
 ranger+0.023
 years+0.022
 since+0.021
 clearing+0.021
 café+0.021
Neg logit contributions
its-0.028
ower-0.025
apy-0.025
aged-0.025
isel-0.025
Token.
Token ID13
Feature activation-1.13e-03

Pos logit contributions
 ranger+0.024
 clearing+0.022
 café+0.022
 since+0.022
 Tooth+0.021
Neg logit contributions
its-0.041
ower-0.040
aged-0.038
apy-0.038
ikes-0.037
Token She
Token ID1375
Feature activation+2.49e-02

Pos logit contributions
apy+0.002
its+0.002
aged+0.002
ower+0.002
isel+0.002
Neg logit contributions
 years-0.002
 ranger-0.002
 tale-0.002
 banquet-0.002
 clearing-0.001
Token was
Token ID373
Feature activation-4.24e-03

Pos logit contributions
 ranger+0.039
 clearing+0.036
 café+0.036
 Tooth+0.036
 years+0.036
Neg logit contributions
its-0.046
apy-0.043
aged-0.043
ower-0.040
isel-0.040
Token They
Token ID1119
Feature activation+2.29e-02

Pos logit contributions
 ranger+0.034
 years+0.033
 clearing+0.032
 Tooth+0.032
 since+0.032
Neg logit contributions
its-0.054
ower-0.050
apy-0.049
ikes-0.049
isel-0.049
Token pretend
Token ID16614
Feature activation+3.23e-02

Pos logit contributions
 ranger+0.038
 since+0.036
 years+0.035
 Prince+0.034
 clearing+0.034
Neg logit contributions
its-0.043
ower-0.041
aged-0.039
apy-0.039
ikes-0.039
Token to
Token ID284
Feature activation-2.27e-03

Pos logit contributions
 clearing+0.047
 ranger+0.047
 Tooth+0.045
 years+0.045
 since+0.044
Neg logit contributions
its-0.061
apy-0.057
ower-0.057
aged-0.055
ikes-0.055
Token be
Token ID307
Feature activation+1.93e-02

Pos logit contributions
its+0.004
ower+0.004
apy+0.004
aged+0.004
isel+0.004
Neg logit contributions
 ranger-0.004
 clearing-0.003
 years-0.003
 enclosure-0.003
 Lion-0.003
Token cow
Token ID9875
Feature activation+7.07e-02

Pos logit contributions
 ranger+0.027
 years+0.026
 clearing+0.025
 since+0.025
 café+0.024
Neg logit contributions
its-0.040
ower-0.037
apy-0.036
aged-0.036
isel-0.036
Tokenboys
Token ID13202
Feature activation+1.03e-01

Pos logit contributions
 clearing+0.116
 Tooth+0.106
 doorway+0.102
 awoke+0.101
 nowhere+0.101
Neg logit contributions
ower-0.117
its-0.115
ikes-0.113
aged-0.108
iggle-0.102
Token and
Token ID290
Feature activation-2.86e-04

Pos logit contributions
 clearing+0.135
 ranger+0.128
 years+0.125
 Tooth+0.123
 banquet+0.120
Neg logit contributions
its-0.204
ikes-0.200
ower-0.200
aged-0.188
iggle-0.184
Token robbers
Token ID46988
Feature activation-4.70e-03

Pos logit contributions
its+0.001
ower+0.001
apy+0.001
isel+0.001
aged+0.001
Neg logit contributions
 ranger-0.000
 years-0.000
 clearing-0.000
 since-0.000
 café-0.000
Token.
Token ID13
Feature activation+1.48e-02

Pos logit contributions
its+0.010
ower+0.009
aged+0.009
ikes+0.009
apy+0.009
Neg logit contributions
 ranger-0.006
 Tooth-0.006
 clearing-0.006
 years-0.006
 since-0.005
Token One
Token ID1881
Feature activation+6.63e-03

Pos logit contributions
 ranger+0.019
 years+0.018
 clearing+0.018
 since+0.017
 Tooth+0.017
Neg logit contributions
its-0.032
ower-0.030
apy-0.029
ikes-0.029
isel-0.029
Token day
Token ID1110
Feature activation+7.97e-03

Pos logit contributions
 ranger+0.012
 years+0.012
 clearing+0.012
 since+0.011
 Tooth+0.011
Neg logit contributions
its-0.011
ower-0.010
apy-0.009
aged-0.009
isel-0.009
Token He
Token ID679
Feature activation-7.02e-03

Pos logit contributions
its+0.035
ower+0.033
ikes+0.033
aged+0.033
apy+0.033
Neg logit contributions
 years-0.020
 ranger-0.020
 clearing-0.019
 banquet-0.019
 café-0.018
Token pretended
Token ID36766
Feature activation+6.31e-03

Pos logit contributions
its+0.012
aged+0.011
isel+0.011
apy+0.010
ower+0.010
Neg logit contributions
 years-0.012
 clearing-0.011
 ranger-0.011
 cafe-0.011
 café-0.011
Token to
Token ID284
Feature activation-5.86e-03

Pos logit contributions
 clearing+0.008
 years+0.008
 ranger+0.008
 Tooth+0.008
 café+0.008
Neg logit contributions
its-0.012
aged-0.012
ower-0.012
apy-0.012
ikes-0.012
Token be
Token ID307
Feature activation+1.25e-02

Pos logit contributions
its+0.011
ower+0.010
apy+0.010
aged+0.010
isel+0.010
Neg logit contributions
 ranger-0.010
 years-0.009
 since-0.009
 clearing-0.009
 dentist-0.009
Token a
Token ID257
Feature activation+8.73e-03

Pos logit contributions
 ranger+0.016
 years+0.015
 clearing+0.015
 since+0.015
 café+0.014
Neg logit contributions
its-0.027
ower-0.025
apy-0.025
aged-0.024
isel-0.024
Token doctor
Token ID6253
Feature activation+9.78e-02

Pos logit contributions
 years+0.012
 ranger+0.012
 since+0.012
 café+0.011
 clearing+0.011
Neg logit contributions
its-0.017
ower-0.016
isel-0.015
apy-0.015
aged-0.015
Token and
Token ID290
Feature activation+7.84e-03

Pos logit contributions
 clearing+0.127
 years+0.118
 café+0.118
 banquet+0.117
 Tooth+0.117
Neg logit contributions
aged-0.187
its-0.187
ower-0.187
ikes-0.180
ged-0.171
Token fixed
Token ID5969
Feature activation-2.09e-02

Pos logit contributions
 ranger+0.011
 years+0.010
 clearing+0.010
 since+0.010
 café+0.010
Neg logit contributions
its-0.016
ower-0.015
apy-0.015
aged-0.015
isel-0.015
Token Billy
Token ID15890
Feature activation-8.53e-02

Pos logit contributions
its+0.048
ower+0.046
apy+0.044
isel+0.044
aged+0.043
Neg logit contributions
 ranger-0.025
 years-0.023
 since-0.023
 clearing-0.022
 Prince-0.022
Token's
Token ID338
Feature activation+2.26e-02

Pos logit contributions
its+0.246
ower+0.234
apy+0.232
isel+0.231
aged+0.226
Neg logit contributions
 ranger-0.049
 years-0.044
 since-0.043
 clearing-0.039
 café-0.036
Token broken
Token ID5445
Feature activation-1.47e-02

Pos logit contributions
 ranger+0.035
 dentist+0.034
 cave+0.033
 chest+0.033
 years+0.033
Neg logit contributions
its-0.044
apy-0.040
ikes-0.038
ower-0.037
isel-0.037
Token "
Token ID366
Feature activation-3.72e-02

Pos logit contributions
its+0.028
ower+0.027
apy+0.027
aged+0.026
isel+0.026
Neg logit contributions
 ranger-0.019
 years-0.018
 since-0.017
 café-0.017
 Tooth-0.017
TokenSo
Token ID2396
Feature activation+1.12e-03

Pos logit contributions
its+0.082
ower+0.077
apy+0.075
isel+0.075
aged+0.074
Neg logit contributions
 ranger-0.046
 years-0.043
 clearing-0.042
 since-0.042
 café-0.041
Token when
Token ID618
Feature activation-1.73e-02

Pos logit contributions
 ranger+0.001
 years+0.001
 clearing+0.001
 café+0.001
 Tooth+0.001
Neg logit contributions
its-0.002
apy-0.002
ower-0.002
isel-0.002
aged-0.002
Token the
Token ID262
Feature activation+1.92e-02

Pos logit contributions
its+0.036
ower+0.034
apy+0.034
isel+0.033
aged+0.033
Neg logit contributions
 ranger-0.023
 years-0.021
 clearing-0.021
 café-0.021
 since-0.021
Token sky
Token ID6766
Feature activation+3.38e-02

Pos logit contributions
 ranger+0.027
 since+0.026
 years+0.025
 café+0.024
 Prince+0.024
Neg logit contributions
its-0.037
ower-0.036
apy-0.034
aged-0.033
isel-0.033
Token closes
Token ID20612
Feature activation+9.74e-02

Pos logit contributions
 ranger+0.049
 years+0.046
 clearing+0.045
 since+0.045
 Tooth+0.044
Neg logit contributions
its-0.068
ower-0.062
apy-0.061
aged-0.060
isel-0.060
Token,
Token ID11
Feature activation-4.67e-03

Pos logit contributions
 ranger+0.129
 years+0.117
 clearing+0.114
 café+0.114
 Tooth+0.113
Neg logit contributions
its-0.207
ower-0.194
apy-0.191
aged-0.187
isel-0.187
Token I
Token ID314
Feature activation+2.64e-02

Pos logit contributions
its+0.010
ower+0.009
apy+0.009
isel+0.009
aged+0.009
Neg logit contributions
 ranger-0.007
 years-0.006
 clearing-0.006
 café-0.006
 since-0.006
Token won
Token ID1839
Feature activation-4.50e-03

Pos logit contributions
 ranger+0.044
 years+0.043
 clearing+0.042
 since+0.042
 Fairy+0.041
Neg logit contributions
its-0.046
ower-0.043
ikes-0.042
apy-0.041
aged-0.041
Token't
Token ID470
Feature activation+2.98e-03

Pos logit contributions
its+0.009
ower+0.009
isel+0.008
apy+0.008
aged+0.008
Neg logit contributions
 ranger-0.006
 years-0.006
 since-0.006
 clearing-0.006
 Fairy-0.006
Token be
Token ID307
Feature activation+6.82e-03

Pos logit contributions
 ranger+0.005
 years+0.005
 since+0.005
 clearing+0.005
 Tooth+0.005
Neg logit contributions
its-0.005
ower-0.004
apy-0.004
aged-0.004
ikes-0.004
Token,
Token ID11
Feature activation+5.26e-02

Pos logit contributions
its+0.020
ower+0.018
apy+0.018
isel+0.018
aged+0.018
Neg logit contributions
 ranger-0.007
 years-0.006
 since-0.006
 clearing-0.006
 café-0.006
Token there
Token ID612
Feature activation-1.18e-02

Pos logit contributions
 ranger+0.041
 clearing+0.039
 since+0.039
 years+0.037
 nowhere+0.036
Neg logit contributions
its-0.142
ower-0.133
isel-0.131
ikes-0.130
aged-0.129
Token was
Token ID373
Feature activation+5.52e-02

Pos logit contributions
its+0.030
ower+0.029
isel+0.029
ikes+0.028
aged+0.028
Neg logit contributions
 ranger-0.010
 years-0.010
 clearing-0.010
 since-0.009
 café-0.009
Token an
Token ID281
Feature activation+5.18e-02

Pos logit contributions
 ranger+0.078
 years+0.068
 since+0.068
 café+0.067
 clearing+0.066
Neg logit contributions
its-0.111
apy-0.107
ower-0.104
aged-0.101
ikes-0.101
Token old
Token ID1468
Feature activation+3.01e-02

Pos logit contributions
 ranger+0.081
 clearing+0.076
 since+0.075
 years+0.075
 café+0.073
Neg logit contributions
its-0.095
ower-0.090
isel-0.085
aged-0.085
apy-0.085
Token lady
Token ID10846
Feature activation+1.04e-01

Pos logit contributions
 years+0.040
 since+0.040
 ranger+0.038
 clearing+0.037
THE+0.036
Neg logit contributions
ower-0.059
its-0.055
apy-0.054
aged-0.053
ikes-0.052
Token.
Token ID13
Feature activation+3.80e-02

Pos logit contributions
 ranger+0.142
 clearing+0.137
 grizz+0.137
 Prince+0.135
 Tooth+0.134
Neg logit contributions
its-0.192
aged-0.191
ower-0.190
ot-0.178
iggle-0.174
Token She
Token ID1375
Feature activation+4.95e-02

Pos logit contributions
 ranger+0.053
 years+0.051
 clearing+0.050
 Tooth+0.049
 since+0.049
Neg logit contributions
its-0.072
ower-0.068
apy-0.068
aged-0.066
ikes-0.065
Token was
Token ID373
Feature activation+1.29e-02

Pos logit contributions
 clearing+0.082
 ranger+0.082
 enclosure+0.081
 since+0.078
 Prince+0.078
Neg logit contributions
its-0.079
ower-0.075
aged-0.075
apy-0.073
ikes-0.068
Token very
Token ID845
Feature activation+2.51e-02

Pos logit contributions
 ranger+0.018
 years+0.017
 since+0.017
 clearing+0.016
 café+0.016
Neg logit contributions
its-0.026
ower-0.024
aged-0.024
apy-0.024
isel-0.023
Token old
Token ID1468
Feature activation+1.82e-02

Pos logit contributions
 ranger+0.035
 years+0.033
 café+0.030
 Princess+0.030
 Prince+0.030
Neg logit contributions
its-0.054
ikes-0.051
isel-0.051
ower-0.048
apy-0.048
Token So
Token ID1406
Feature activation-9.99e-03

Pos logit contributions
 ranger+0.018
 clearing+0.017
 years+0.017
 banquet+0.016
 enclosure+0.016
Neg logit contributions
its-0.026
apy-0.025
aged-0.025
ower-0.025
ikes-0.024
Token,
Token ID11
Feature activation-3.05e-02

Pos logit contributions
apy+0.020
aged+0.019
its+0.019
ower+0.018
iggle+0.017
Neg logit contributions
 ranger-0.015
 clearing-0.014
 enclosure-0.014
 dentist-0.013
 café-0.013
Token they
Token ID484
Feature activation+1.43e-02

Pos logit contributions
apy+0.050
its+0.048
aged+0.047
ower+0.045
ikes+0.044
Neg logit contributions
 ranger-0.053
 clearing-0.051
 enclosure-0.050
 years-0.050
 banquet-0.048
Token looked
Token ID3114
Feature activation-3.06e-03

Pos logit contributions
 ranger+0.021
 years+0.020
 since+0.020
 clearing+0.020
 café+0.019
Neg logit contributions
its-0.028
ower-0.026
apy-0.025
ikes-0.025
isel-0.025
Token around
Token ID1088
Feature activation-3.90e-02

Pos logit contributions
its+0.005
isel+0.005
aged+0.005
apy+0.005
ower+0.005
Neg logit contributions
 ranger-0.005
 Tooth-0.005
 café-0.005
 dentist-0.005
 years-0.005
Token and
Token ID290
Feature activation+1.37e-02

Pos logit contributions
its+0.074
apy+0.070
ower+0.070
aged+0.070
ged+0.069
Neg logit contributions
 ranger-0.053
 Tooth-0.049
 enclosure-0.049
 café-0.049
 banquet-0.048
Token found
Token ID1043
Feature activation-3.93e-02

Pos logit contributions
 ranger+0.019
 years+0.018
 clearing+0.017
 café+0.017
 Tooth+0.017
Neg logit contributions
its-0.028
ower-0.026
apy-0.026
aged-0.026
isel-0.026
Token a
Token ID257
Feature activation+1.58e-02

Pos logit contributions
its+0.099
ower+0.096
ikes+0.091
isel+0.091
aged+0.089
Neg logit contributions
 ranger-0.037
 clearing-0.034
 years-0.033
 since-0.033
 Prince-0.033
Token new
Token ID649
Feature activation+5.76e-02

Pos logit contributions
 ranger+0.027
 years+0.027
 since+0.026
 clearing+0.025
 café+0.025
Neg logit contributions
its-0.026
ower-0.024
apy-0.024
isel-0.023
aged-0.023
Token spoon
Token ID24556
Feature activation-1.99e-02

Pos logit contributions
 ranger+0.095
 years+0.091
 since+0.087
 clearing+0.086
 Prince+0.085
Neg logit contributions
its-0.102
ower-0.095
apy-0.093
isel-0.091
aged-0.090
Token that
Token ID326
Feature activation-2.86e-02

Pos logit contributions
its+0.043
ower+0.041
aged+0.040
apy+0.040
ikes+0.039
Neg logit contributions
 ranger-0.025
 years-0.024
 clearing-0.023
 Tooth-0.023
 café-0.023
Token "
Token ID366
Feature activation-7.44e-03

Pos logit contributions
 ranger+0.013
 years+0.012
 clearing+0.012
 since+0.012
 café+0.011
Neg logit contributions
its-0.019
ower-0.018
apy-0.018
isel-0.017
aged-0.017
TokenHello
Token ID15496
Feature activation+4.00e-02

Pos logit contributions
its+0.019
ower+0.018
apy+0.017
ikes+0.017
aged+0.017
Neg logit contributions
 ranger-0.007
 years-0.006
 clearing-0.006
 since-0.006
 café-0.006
Token,
Token ID11
Feature activation+1.54e-02

Pos logit contributions
 ranger+0.056
 years+0.052
 clearing+0.051
 Tooth+0.050
 dentist+0.050
Neg logit contributions
its-0.076
ower-0.073
ikes-0.069
apy-0.068
aged-0.066
Token c
Token ID269
Feature activation+4.24e-02

Pos logit contributions
 ranger+0.024
 years+0.023
 clearing+0.022
 since+0.022
 café+0.021
Neg logit contributions
its-0.029
ower-0.027
apy-0.026
ikes-0.025
isel-0.025
Tokenactus
Token ID34144
Feature activation+1.48e-02

Pos logit contributions
 ranger+0.048
 years+0.046
 clearing+0.044
 since+0.043
 café+0.043
Neg logit contributions
its-0.097
apy-0.090
ower-0.090
isel-0.090
aged-0.089
Token!
Token ID0
Feature activation-4.90e-03

Pos logit contributions
 clearing+0.021
 amusement+0.021
 Tooth+0.021
 dentist+0.021
 ranger+0.021
Neg logit contributions
its-0.027
ower-0.026
iggle-0.024
apy-0.023
ikes-0.023
Token Can
Token ID1680
Feature activation+1.77e-02

Pos logit contributions
apy+0.009
its+0.009
ower+0.008
ikes+0.008
isel+0.008
Neg logit contributions
 years-0.007
 ranger-0.007
 dentist-0.007
 clearing-0.006
 café-0.006
Token I
Token ID314
Feature activation+3.29e-02

Pos logit contributions
 ranger+0.026
 clearing+0.025
 café+0.025
 years+0.024
 cafe+0.024
Neg logit contributions
its-0.033
apy-0.032
ower-0.030
ikes-0.030
aged-0.030
Token sit
Token ID1650
Feature activation+3.50e-02

Pos logit contributions
 ranger+0.061
 years+0.059
 clearing+0.058
 since+0.057
 café+0.057
Neg logit contributions
its-0.051
ower-0.046
apy-0.045
isel-0.044
aged-0.043
Token on
Token ID319
Feature activation-2.01e-02

Pos logit contributions
 ranger+0.058
 clearing+0.053
 café+0.052
 dentist+0.052
 Tooth+0.052
Neg logit contributions
its-0.059
ower-0.059
aged-0.055
apy-0.054
ikes-0.054
Token you
Token ID345
Feature activation+5.59e-03

Pos logit contributions
its+0.036
apy+0.035
ower+0.033
ikes+0.032
iggle+0.031
Neg logit contributions
 ranger-0.031
 clearing-0.027
 café-0.027
 since-0.026
 banquet-0.026
Token by
Token ID416
Feature activation+2.52e-02

Pos logit contributions
its+0.080
ower+0.073
aged+0.073
apy+0.071
ikes+0.070
Neg logit contributions
 Tooth-0.066
 ranger-0.063
 years-0.063
 clearing-0.062
 Fairy-0.062
Token heard
Token ID2982
Feature activation+4.67e-02

Pos logit contributions
 ranger+0.031
 years+0.029
 clearing+0.029
 since+0.029
 Tooth+0.029
Neg logit contributions
its-0.055
ower-0.051
apy-0.050
aged-0.050
isel-0.049
Token Tom
Token ID4186
Feature activation+1.56e-02

Pos logit contributions
 ranger+0.070
 clearing+0.069
 years+0.066
 since+0.066
 Tooth+0.066
Neg logit contributions
its-0.089
apy-0.078
ower-0.076
ikes-0.075
aged-0.075
Token's
Token ID338
Feature activation+5.62e-02

Pos logit contributions
 ranger+0.013
 years+0.012
 since+0.011
 clearing+0.011
 café+0.010
Neg logit contributions
its-0.041
ower-0.039
apy-0.039
isel-0.039
aged-0.038
Token cries
Token ID24691
Feature activation+1.73e-02

Pos logit contributions
 ranger+0.075
 years+0.070
 clearing+0.067
 since+0.066
 café+0.066
Neg logit contributions
its-0.121
ower-0.113
apy-0.111
isel-0.110
aged-0.109
Token.
Token ID13
Feature activation+4.63e-03

Pos logit contributions
 ranger+0.019
 years+0.018
 clearing+0.017
 since+0.017
 café+0.016
Neg logit contributions
its-0.041
ower-0.038
apy-0.038
isel-0.037
aged-0.037
Token He
Token ID679
Feature activation+3.06e-03

Pos logit contributions
 years+0.007
 tale+0.007
 Tooth+0.007
 banquet+0.007
 clearing+0.007
Neg logit contributions
its-0.009
apy-0.008
ower-0.008
aged-0.008
isel-0.008
Token came
Token ID1625
Feature activation-3.51e-03

Pos logit contributions
 since+0.005
 Tooth+0.005
 ranger+0.005
 years+0.005
 Prince+0.005
Neg logit contributions
its-0.005
aged-0.005
apy-0.005
isel-0.004
ower-0.004
Token to
Token ID284
Feature activation+4.15e-02

Pos logit contributions
its+0.007
ower+0.007
apy+0.006
isel+0.006
aged+0.006
Neg logit contributions
 ranger-0.005
 years-0.005
 clearing-0.005
 since-0.005
 café-0.005
Token see
Token ID766
Feature activation+5.28e-02

Pos logit contributions
 ranger+0.060
 years+0.058
 since+0.056
 clearing+0.056
 café+0.055
Neg logit contributions
its-0.080
ower-0.073
apy-0.073
isel-0.072
aged-0.071
Token what
Token ID644
Feature activation+1.43e-02

Pos logit contributions
 ranger+0.078
 years+0.075
 clearing+0.074
 since+0.072
 café+0.072
Neg logit contributions
its-0.104
apy-0.093
ower-0.092
isel-0.091
aged-0.091
Token with
Token ID351
Feature activation+1.70e-02

Pos logit contributions
 Tooth+0.012
 ranger+0.012
 dentist+0.012
 Fairy+0.011
 Prince+0.011
Neg logit contributions
its-0.015
ower-0.014
apy-0.014
ikes-0.014
iggle-0.013
Token Be
Token ID1355
Feature activation+3.42e-02

Pos logit contributions
 ranger+0.026
 years+0.025
 clearing+0.024
 since+0.024
 café+0.023
Neg logit contributions
its-0.033
ower-0.031
apy-0.030
isel-0.030
aged-0.030
Tokencca
Token ID13227
Feature activation+6.41e-03

Pos logit contributions
 years+0.055
 ranger+0.053
 since+0.050
 clearing+0.050
 café+0.048
Neg logit contributions
its-0.065
apy-0.060
ower-0.059
isel-0.059
ikes-0.058
Token,
Token ID11
Feature activation-9.34e-03

Pos logit contributions
 ranger+0.008
 Tooth+0.008
 clearing+0.008
 years+0.007
 café+0.007
Neg logit contributions
its-0.013
ower-0.013
aged-0.013
apy-0.012
ikes-0.012
Token but
Token ID475
Feature activation+1.93e-02

Pos logit contributions
its+0.018
aged+0.018
ower+0.018
apy+0.017
ikes+0.017
Neg logit contributions
 ranger-0.012
 years-0.011
 banquet-0.011
 Tooth-0.011
 clearing-0.011
Token Be
Token ID1355
Feature activation+3.26e-02

Pos logit contributions
 café+0.026
 years+0.025
 ranger+0.025
 banquet+0.025
 Tooth+0.025
Neg logit contributions
aged-0.036
apy-0.036
its-0.035
ower-0.034
isel-0.033
Tokencca
Token ID13227
Feature activation+1.08e-02

Pos logit contributions
 ranger+0.051
 years+0.051
 since+0.048
 clearing+0.048
 café+0.046
Neg logit contributions
its-0.061
ower-0.056
apy-0.055
ikes-0.055
isel-0.054
Token was
Token ID373
Feature activation+1.50e-03

Pos logit contributions
 ranger+0.015
 clearing+0.014
 years+0.014
 Tooth+0.014
 since+0.013
Neg logit contributions
its-0.022
ower-0.021
apy-0.020
aged-0.020
isel-0.020
Token scared
Token ID12008
Feature activation+2.49e-02

Pos logit contributions
 ranger+0.002
 café+0.002
 Tooth+0.002
 Prince+0.002
 since+0.002
Neg logit contributions
its-0.003
aged-0.003
apy-0.003
ower-0.003
isel-0.003
Token so
Token ID523
Feature activation-3.99e-02

Pos logit contributions
 ranger+0.035
 clearing+0.033
 Tooth+0.033
 café+0.032
 years+0.032
Neg logit contributions
its-0.050
ower-0.047
apy-0.045
aged-0.045
ikes-0.045
Token Joe
Token ID5689
Feature activation-4.34e-02

Pos logit contributions
its+0.092
ower+0.087
isel+0.085
ikes+0.084
aged+0.084
Neg logit contributions
 ranger-0.046
 years-0.043
 since-0.041
 clearing-0.040
 café-0.039
Token very
Token ID845
Feature activation-6.58e-03

Pos logit contributions
its+0.030
isel+0.028
ower+0.028
ikes+0.027
apy+0.026
Neg logit contributions
 ranger-0.023
 years-0.022
 since-0.022
-0.021
 café-0.021
Token scared
Token ID12008
Feature activation-7.85e-04

Pos logit contributions
ikes+0.013
isel+0.013
ower+0.013
its+0.013
ged+0.013
Neg logit contributions
 years-0.008
 ranger-0.008
-0.007
 more-0.007
 too-0.007
Token and
Token ID290
Feature activation+9.25e-03

Pos logit contributions
its+0.002
ower+0.002
aged+0.002
ikes+0.002
apy+0.002
Neg logit contributions
 ranger-0.001
 clearing-0.001
 Tooth-0.001
 café-0.001
 banquet-0.001
Token she
Token ID673
Feature activation+2.75e-02

Pos logit contributions
 ranger+0.013
 years+0.012
 since+0.012
 Prince+0.011
 Tooth+0.011
Neg logit contributions
its-0.020
ower-0.019
ikes-0.018
isel-0.018
apy-0.017
Token started
Token ID2067
Feature activation-1.03e-02

Pos logit contributions
 ranger+0.044
 years+0.041
 since+0.040
 clearing+0.040
 café+0.039
Neg logit contributions
its-0.052
ower-0.048
isel-0.046
ikes-0.046
apy-0.046
Token to
Token ID284
Feature activation+3.45e-03

Pos logit contributions
its+0.023
ower+0.022
apy+0.021
aged+0.021
isel+0.021
Neg logit contributions
 ranger-0.012
 years-0.011
 clearing-0.011
 since-0.011
 Tooth-0.011
Token cry
Token ID3960
Feature activation+2.36e-02

Pos logit contributions
 ranger+0.006
 years+0.006
 café+0.006
 clearing+0.006
 since+0.006
Neg logit contributions
its-0.005
ower-0.005
apy-0.005
ikes-0.005
isel-0.005
Token.
Token ID13
Feature activation-2.97e-04

Pos logit contributions
 ranger+0.023
 years+0.021
 since+0.021
 clearing+0.020
 Tooth+0.019
Neg logit contributions
its-0.059
ower-0.055
isel-0.055
apy-0.054
aged-0.053
Token
Token ID198
Feature activation+6.98e-03

Pos logit contributions
its+0.001
ower+0.001
apy+0.001
isel+0.001
aged+0.001
Neg logit contributions
 ranger-0.000
 years-0.000
 since-0.000
 clearing-0.000
 café-0.000
Token
Token ID198
Feature activation+1.60e-02

Pos logit contributions
 ranger+0.005
 years+0.004
 since+0.004
 clearing+0.004
 café+0.004
Neg logit contributions
its-0.019
ower-0.019
isel-0.018
apy-0.018
aged-0.018
TokenHer
Token ID9360
Feature activation+9.85e-03

Pos logit contributions
 ranger+0.019
 years+0.018
 since+0.018
 clearing+0.017
 café+0.017
Neg logit contributions
its-0.036
ower-0.034
apy-0.033
isel-0.033
aged-0.033
Token come
Token ID1282
Feature activation+9.07e-03

Pos logit contributions
 ranger+0.032
 since+0.031
 clearing+0.031
 years+0.030
 Fairy+0.030
Neg logit contributions
its-0.047
aged-0.044
apy-0.044
ower-0.043
isel-0.043
Token home
Token ID1363
Feature activation+2.92e-02

Pos logit contributions
 ranger+0.012
 years+0.012
 clearing+0.012
 Tooth+0.011
 since+0.011
Neg logit contributions
its-0.018
ower-0.017
apy-0.017
aged-0.017
isel-0.017
Token early
Token ID1903
Feature activation+1.13e-01

Pos logit contributions
 clearing+0.039
 ranger+0.038
 Prince+0.038
 Tooth+0.037
 Fairy+0.037
Neg logit contributions
its-0.057
ower-0.054
aged-0.053
apy-0.051
iggle-0.049
Token from
Token ID422
Feature activation+2.85e-02

Pos logit contributions
 Fairy+0.165
 clearing+0.165
 Prince+0.162
 ranger+0.162
 Tooth+0.161
Neg logit contributions
its-0.192
ower-0.186
aged-0.177
ikes-0.170
ged-0.170
Token work
Token ID670
Feature activation+5.59e-03

Pos logit contributions
 ranger+0.039
 years+0.037
 clearing+0.036
 since+0.035
 café+0.034
Neg logit contributions
its-0.062
ower-0.058
apy-0.057
ikes-0.056
isel-0.056
Token.
Token ID13
Feature activation-1.35e-02

Pos logit contributions
 ranger+0.006
 years+0.006
 clearing+0.006
 since+0.006
 café+0.006
Neg logit contributions
its-0.013
ower-0.012
apy-0.012
aged-0.012
isel-0.012
Token He
Token ID679
Feature activation-8.58e-03

Pos logit contributions
its+0.029
ower+0.027
apy+0.027
isel+0.026
aged+0.026
Neg logit contributions
 years-0.017
 ranger-0.016
 since-0.016
 clearing-0.016
 banquet-0.015
Token sees
Token ID7224
Feature activation+3.25e-03

Pos logit contributions
its+0.015
 exc+0.011
aged+0.011
apy+0.011
isel+0.010
Neg logit contributions
 since-0.016
 ranger-0.015
 clearing-0.015
 Tooth-0.015
THE-0.014
Token the
Token ID262
Feature activation+2.85e-02

Pos logit contributions
 ranger+0.004
 years+0.004
 since+0.003
 clearing+0.003
 café+0.003
Neg logit contributions
its-0.007
ower-0.007
apy-0.007
isel-0.007
aged-0.007
Token smoke
Token ID7523
Feature activation+5.29e-02

Pos logit contributions
 ranger+0.035
 since+0.033
 years+0.032
 clearing+0.032
 café+0.031
Neg logit contributions
its-0.064
ower-0.059
apy-0.057
aged-0.057
isel-0.057
Token and
Token ID290
Feature activation+4.57e-03

Pos logit contributions
 ranger+0.061
 years+0.058
 clearing+0.057
 since+0.057
 Tooth+0.057
Neg logit contributions
its-0.121
ower-0.111
apy-0.109
aged-0.107
isel-0.106
Token true
Token ID2081
Feature activation+8.80e-03

Pos logit contributions
 ranger+0.003
 since+0.003
 years+0.003
 clearing+0.003
 Prince+0.002
Neg logit contributions
its-0.006
ower-0.005
isel-0.005
apy-0.005
aged-0.005
Token and
Token ID290
Feature activation+1.77e-02

Pos logit contributions
 ranger+0.011
 clearing+0.011
 café+0.010
 Tooth+0.010
 grizz+0.010
Neg logit contributions
its-0.018
ower-0.017
ikes-0.017
aged-0.017
isel-0.016
Token he
Token ID339
Feature activation+1.82e-03

Pos logit contributions
 ranger+0.024
 years+0.022
 since+0.022
 clearing+0.022
 café+0.021
Neg logit contributions
its-0.038
ower-0.036
apy-0.034
isel-0.034
aged-0.034
Token was
Token ID373
Feature activation-1.90e-02

Pos logit contributions
 ranger+0.003
 clearing+0.002
 years+0.002
 Tooth+0.002
 café+0.002
Neg logit contributions
its-0.004
ower-0.003
apy-0.003
aged-0.003
isel-0.003
Token playing
Token ID2712
Feature activation-6.30e-02

Pos logit contributions
its+0.036
aged+0.034
apy+0.033
ower+0.033
isel+0.033
Neg logit contributions
 ranger-0.028
 clearing-0.027
 café-0.027
 Tooth-0.026
 years-0.026
Token the
Token ID262
Feature activation-2.15e-02

Pos logit contributions
its+0.134
ower+0.124
apy+0.122
aged+0.121
isel+0.120
Neg logit contributions
 ranger-0.082
 years-0.077
 clearing-0.075
 since-0.075
 Tooth-0.074
Token best
Token ID1266
Feature activation-2.80e-02

Pos logit contributions
its+0.042
isel+0.039
apy+0.039
ower+0.038
aged+0.038
Neg logit contributions
 ranger-0.033
 clearing-0.031
 since-0.031
 years-0.031
 café-0.030
Token soccer
Token ID11783
Feature activation-5.89e-02

Pos logit contributions
its+0.056
ower+0.054
aged+0.053
isel+0.053
apy+0.052
Neg logit contributions
 ranger-0.041
 since-0.038
 years-0.037
 café-0.035
 again-0.035
Token of
Token ID286
Feature activation-8.87e-02

Pos logit contributions
its+0.108
ower+0.101
apy+0.098
aged+0.096
ikes+0.096
Neg logit contributions
 ranger-0.088
 years-0.086
 Tooth-0.085
 clearing-0.085
 café-0.084
Token his
Token ID465
Feature activation-7.07e-02

Pos logit contributions
its+0.206
ower+0.203
ikes+0.190
isel+0.190
apy+0.189
Neg logit contributions
 ranger-0.107
 years-0.104
 nowhere-0.092
 clearing-0.092
 since-0.091
Token life
Token ID1204
Feature activation-4.74e-02

Pos logit contributions
its+0.133
isel+0.122
ower+0.120
apy+0.119
aged+0.118
Neg logit contributions
 ranger-0.115
 years-0.111
 since-0.104
 clearing-0.102
 café-0.102
Token ran
Token ID4966
Feature activation-3.75e-02

Pos logit contributions
its+0.015
ower+0.014
apy+0.014
isel+0.014
ikes+0.014
Neg logit contributions
 ranger-0.009
 years-0.008
 since-0.008
 clearing-0.008
 café-0.008
Token off
Token ID572
Feature activation-3.58e-02

Pos logit contributions
its+0.069
ower+0.064
apy+0.064
aged+0.064
isel+0.063
Neg logit contributions
 ranger-0.058
 years-0.056
 Tooth-0.055
 clearing-0.054
 since-0.053
Token to
Token ID284
Feature activation-1.57e-02

Pos logit contributions
its+0.073
apy+0.069
ower+0.069
aged+0.069
isel+0.066
Neg logit contributions
 ranger-0.047
 years-0.046
 Tooth-0.045
 clearing-0.044
 café-0.044
Token play
Token ID711
Feature activation-3.22e-02

Pos logit contributions
its+0.033
ower+0.031
ikes+0.030
aged+0.029
isel+0.029
Neg logit contributions
 ranger-0.022
 clearing-0.021
 years-0.021
 Tooth-0.020
 since-0.020
Token.
Token ID13
Feature activation-1.70e-02

Pos logit contributions
its+0.066
apy+0.063
ower+0.063
aged+0.061
isel+0.060
Neg logit contributions
 ranger-0.042
 years-0.039
 since-0.039
 Tooth-0.039
 café-0.038
Token He
Token ID679
Feature activation-1.82e-02

Pos logit contributions
its+0.040
ower+0.037
apy+0.037
isel+0.036
aged+0.036
Neg logit contributions
 ranger-0.019
 years-0.018
 since-0.017
 clearing-0.017
 café-0.017
Token never
Token ID1239
Feature activation-1.02e-02

Pos logit contributions
its+0.038
ower+0.035
apy+0.034
aged+0.034
isel+0.034
Neg logit contributions
 ranger-0.025
 years-0.024
 clearing-0.023
 since-0.023
 café-0.023
Token let
Token ID1309
Feature activation-2.07e-02

Pos logit contributions
its+0.018
ower+0.017
aged+0.017
apy+0.017
isel+0.017
Neg logit contributions
 ranger-0.016
 years-0.016
 clearing-0.016
 Tooth-0.015
 café-0.015
Token go
Token ID467
Feature activation-2.75e-02

Pos logit contributions
its+0.049
ower+0.048
apy+0.045
ikes+0.045
aged+0.044
Neg logit contributions
 ranger-0.022
 since-0.021
 Prince-0.021
 dentist-0.021
 Tooth-0.021
Token of
Token ID286
Feature activation-2.06e-02

Pos logit contributions
its+0.061
ower+0.057
apy+0.056
isel+0.055
aged+0.055
Neg logit contributions
 ranger-0.034
 years-0.032
 clearing-0.032
 since-0.031
 café-0.031
Token his
Token ID465
Feature activation-3.32e-02

Pos logit contributions
its+0.051
ower+0.049
ikes+0.047
isel+0.046
aged+0.046
Neg logit contributions
 years-0.020
 ranger-0.020
 Tooth-0.019
 clearing-0.019
 since-0.018
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
its+0.148
isel+0.138
ower+0.137
apy+0.132
ikes+0.131
Neg logit contributions
 ranger-0.093
 years-0.089
 clearing-0.086
 since-0.083
 café-0.080
Token The
Token ID383
Feature activation+1.62e-03

Pos logit contributions
its+0.029
ower+0.027
apy+0.027
aged+0.027
isel+0.027
Neg logit contributions
 ranger-0.020
 years-0.019
 clearing-0.018
 since-0.018
 Tooth-0.018
Token people
Token ID661
Feature activation-9.03e-03

Pos logit contributions
 ranger+0.002
 since+0.002
 years+0.002
 Tooth+0.002
 clearing+0.002
Neg logit contributions
its-0.003
ower-0.003
aged-0.003
apy-0.003
ikes-0.003
Token wore
Token ID12408
Feature activation-5.62e-02

Pos logit contributions
its+0.020
ower+0.019
ikes+0.018
isel+0.018
inters+0.017
Neg logit contributions
 since-0.011
 years-0.011
 ranger-0.011
 clearing-0.010
 café-0.010
Token bright
Token ID6016
Feature activation-1.81e-02

Pos logit contributions
its+0.112
ower+0.104
isel+0.101
apy+0.100
ikes+0.099
Neg logit contributions
 ranger-0.083
 years-0.079
 clearing-0.077
 since-0.076
 café-0.075
Token colours
Token ID18915
Feature activation-6.39e-02

Pos logit contributions
its+0.034
ower+0.031
ikes+0.030
isel+0.030
aged+0.030
Neg logit contributions
 years-0.028
 ranger-0.028
 clearing-0.027
 since-0.026
 café-0.026
Token and
Token ID290
Feature activation-4.08e-02

Pos logit contributions
its+0.146
ower+0.137
apy+0.137
aged+0.135
isel+0.133
Neg logit contributions
 ranger-0.072
 Tooth-0.067
 years-0.067
 clearing-0.066
 café-0.064
Token loved
Token ID6151
Feature activation-3.33e-02

Pos logit contributions
its+0.092
ower+0.085
ikes+0.083
isel+0.083
aged+0.079
Neg logit contributions
 ranger-0.053
 years-0.050
 since-0.049
 café-0.046
 clearing-0.046
Token to
Token ID284
Feature activation-2.91e-02

Pos logit contributions
its+0.073
ower+0.068
isel+0.067
apy+0.066
ikes+0.066
Neg logit contributions
 ranger-0.044
 years-0.042
 since-0.040
 clearing-0.039
 café-0.038
Token dance
Token ID9280
Feature activation+3.72e-02

Pos logit contributions
its+0.056
ower+0.054
ikes+0.052
aged+0.051
isel+0.050
Neg logit contributions
 ranger-0.044
 years-0.042
 clearing-0.041
 café-0.040
 cafe-0.040
Token.
Token ID13
Feature activation-1.23e-02

Pos logit contributions
 ranger+0.049
 clearing+0.046
 years+0.046
 Tooth+0.045
 since+0.044
Neg logit contributions
its-0.077
ower-0.073
apy-0.072
aged-0.071
ikes-0.070
Token the
Token ID262
Feature activation+1.10e-02

Pos logit contributions
its+0.050
ower+0.046
apy+0.046
isel+0.045
aged+0.045
Neg logit contributions
 ranger-0.027
 years-0.025
 clearing-0.024
 since-0.024
 café-0.024
Token air
Token ID1633
Feature activation+1.38e-02

Pos logit contributions
 ranger+0.017
 since+0.017
 years+0.016
 grizz+0.015
 Tooth+0.015
Neg logit contributions
its-0.021
apy-0.019
isel-0.019
ower-0.018
aged-0.018
Token.
Token ID13
Feature activation-9.30e-03

Pos logit contributions
 ranger+0.017
 years+0.016
 clearing+0.016
 Tooth+0.015
 café+0.015
Neg logit contributions
its-0.030
ower-0.028
aged-0.027
apy-0.027
isel-0.027
Token She
Token ID1375
Feature activation+1.56e-02

Pos logit contributions
its+0.024
ower+0.023
isel+0.022
ikes+0.022
aged+0.022
Neg logit contributions
 ranger-0.008
 Prince-0.007
 Tooth-0.007
 since-0.007
 clearing-0.007
Token said
Token ID531
Feature activation+7.08e-03

Pos logit contributions
 ranger+0.025
 years+0.024
 clearing+0.024
 since+0.024
 café+0.023
Neg logit contributions
its-0.028
apy-0.026
ower-0.026
aged-0.025
isel-0.025
Token "
Token ID366
Feature activation-1.99e-02

Pos logit contributions
 ranger+0.008
 years+0.007
 since+0.007
 Prince+0.007
 Tooth+0.007
Neg logit contributions
its-0.016
ower-0.015
ikes-0.015
isel-0.015
aged-0.015
TokenY
Token ID56
Feature activation-1.89e-02

Pos logit contributions
its+0.044
isel+0.043
ower+0.042
aged+0.042
apy+0.042
Neg logit contributions
 ranger-0.023
 years-0.021
 since-0.021
 clearing-0.021
 Tooth-0.021
Tokenay
Token ID323
Feature activation-1.12e-01

Pos logit contributions
its+0.027
isel+0.026
aged+0.026
ower+0.026
apy+0.025
Neg logit contributions
 ranger-0.035
 years-0.034
 since-0.033
 café-0.033
 clearing-0.033
Token,
Token ID11
Feature activation-4.55e-03

Pos logit contributions
its+0.272
ower+0.256
apy+0.252
aged+0.249
ikes+0.248
Neg logit contributions
 ranger-0.115
 years-0.106
 clearing-0.105
 since-0.103
 café-0.100
Token this
Token ID428
Feature activation-1.41e-02

Pos logit contributions
its+0.009
apy+0.008
ower+0.008
isel+0.008
ikes+0.008
Neg logit contributions
 ranger-0.006
 clearing-0.006
 years-0.006
 café-0.006
 since-0.006
Token is
Token ID318
Feature activation+4.61e-02

Pos logit contributions
its+0.032
ower+0.030
isel+0.030
aged+0.030
apy+0.030
Neg logit contributions
 ranger-0.016
 clearing-0.015
 years-0.015
 since-0.015
 café-0.014
Token to
Token ID284
Feature activation-4.78e-03

Pos logit contributions
its+0.014
ower+0.013
apy+0.013
aged+0.013
isel+0.013
Neg logit contributions
 ranger-0.007
 years-0.007
 clearing-0.007
 since-0.007
 café-0.006
Token colour
Token ID9568
Feature activation+1.93e-02

Pos logit contributions
its+0.010
ower+0.009
aged+0.009
isel+0.008
ikes+0.008
Neg logit contributions
 café-0.007
 ranger-0.007
 years-0.007
 banquet-0.007
 cafe-0.007
Token with
Token ID351
Feature activation+1.35e-02

Pos logit contributions
 years+0.022
 ranger+0.022
 since+0.021
 café+0.020
 clearing+0.020
Neg logit contributions
its-0.044
isel-0.041
ower-0.041
aged-0.040
apy-0.040
Token her
Token ID607
Feature activation-4.67e-03

Pos logit contributions
 years+0.019
 Prince+0.018
 Tooth+0.018
 since+0.017
 café+0.017
Neg logit contributions
its-0.028
ower-0.027
ikes-0.025
isel-0.025
aged-0.025
Token cr
Token ID1067
Feature activation+8.94e-03

Pos logit contributions
its+0.009
ower+0.008
isel+0.008
apy+0.008
aged+0.008
Neg logit contributions
 ranger-0.008
 years-0.007
 clearing-0.007
 since-0.007
 Tooth-0.007
Tokenay
Token ID323
Feature activation-1.25e-01

Pos logit contributions
 years+0.017
 ranger+0.016
 since+0.016
 Tooth+0.016
 Fairy+0.016
Neg logit contributions
its-0.013
apy-0.012
isel-0.012
ower-0.012
aged-0.012
Tokenons
Token ID684
Feature activation-2.32e-02

Pos logit contributions
its+0.224
ower+0.211
isel+0.207
apy+0.203
aged+0.198
Neg logit contributions
 years-0.206
mother-0.184
 Tooth-0.184
 since-0.182
 Fairy-0.182
Token.
Token ID13
Feature activation+1.15e-02

Pos logit contributions
its+0.043
ower+0.042
aged+0.040
ikes+0.039
apy+0.038
Neg logit contributions
 ranger-0.036
 clearing-0.034
 grizz-0.033
 café-0.033
 banquet-0.032
Token She
Token ID1375
Feature activation+2.84e-02

Pos logit contributions
 ranger+0.013
 years+0.012
 clearing+0.012
 since+0.012
 café+0.011
Neg logit contributions
its-0.027
ower-0.025
apy-0.025
isel-0.025
aged-0.025
Token used
Token ID973
Feature activation+9.99e-03

Pos logit contributions
 years+0.040
 ranger+0.040
 since+0.039
 Tooth+0.037
 clearing+0.037
Neg logit contributions
its-0.058
ower-0.054
ikes-0.053
isel-0.052
apy-0.052
Token to
Token ID284
Feature activation-2.74e-02

Pos logit contributions
 nowhere+0.011
 years+0.011
 since+0.011
 front+0.011
 more+0.010
Neg logit contributions
ower-0.023
its-0.022
ikes-0.022
oving-0.021
isel-0.020
Token.
Token ID13
Feature activation-2.07e-02

Pos logit contributions
its+0.015
ower+0.014
isel+0.014
apy+0.014
aged+0.014
Neg logit contributions
 ranger-0.006
 years-0.006
 since-0.006
 clearing-0.006
 café-0.005
Token
Token ID220
Feature activation-5.09e-02

Pos logit contributions
its+0.047
ower+0.044
apy+0.043
aged+0.043
isel+0.042
Neg logit contributions
 ranger-0.024
 years-0.023
 clearing-0.022
 since-0.022
 café-0.021
Token
Token ID198
Feature activation-8.24e-03

Pos logit contributions
its+0.149
isel+0.148
ower+0.140
apy+0.139
aged+0.137
Neg logit contributions
 ranger-0.021
 Ms-0.017
 clearing-0.017
Mrs-0.016
-0.015
Token
Token ID198
Feature activation+2.22e-03

Pos logit contributions
its+0.023
isel+0.022
ower+0.022
aged+0.022
apy+0.021
Neg logit contributions
 ranger-0.005
 clearing-0.005
 years-0.004
 since-0.004
 café-0.004
TokenThe
Token ID464
Feature activation+2.16e-02

Pos logit contributions
 ranger+0.003
 years+0.002
 clearing+0.002
 since+0.002
 café+0.002
Neg logit contributions
its-0.005
ower-0.005
apy-0.005
aged-0.005
ikes-0.005
Token little
Token ID1310
Feature activation-1.10e-01

Pos logit contributions
 ranger+0.029
 clearing+0.027
 since+0.027
 years+0.027
 enclosure+0.026
Neg logit contributions
its-0.044
ower-0.041
apy-0.040
aged-0.040
ikes-0.039
Token girl
Token ID2576
Feature activation-8.47e-03

Pos logit contributions
its+0.177
ower+0.165
aged+0.162
apy+0.160
isel+0.159
Neg logit contributions
 ranger-0.185
 enclosure-0.178
 years-0.176
 clearing-0.174
 grizz-0.172
Token was
Token ID373
Feature activation-2.14e-02

Pos logit contributions
its+0.015
aged+0.015
apy+0.014
iggle+0.013
ower+0.013
Neg logit contributions
 clearing-0.013
 ranger-0.013
 Tooth-0.013
 Prince-0.012
 banquet-0.012
Token so
Token ID523
Feature activation-5.29e-02

Pos logit contributions
aged+0.035
its+0.034
apy+0.033
ower+0.032
iggle+0.030
Neg logit contributions
 ranger-0.036
 clearing-0.035
 enclosure-0.035
 Tooth-0.035
 café-0.034
Token happy
Token ID3772
Feature activation-2.56e-02

Pos logit contributions
its+0.120
ikes+0.116
isel+0.112
ower+0.110
inters+0.109
Neg logit contributions
 years-0.064
 ranger-0.062
-0.061
 since-0.059
 cal-0.056
Token to
Token ID284
Feature activation-3.29e-02

Pos logit contributions
aged+0.042
ower+0.042
its+0.042
iggle+0.040
apy+0.040
Neg logit contributions
 clearing-0.040
 enclosure-0.040
 grizz-0.040
 Tooth-0.038
 ranger-0.038
Token and
Token ID290
Feature activation+5.32e-03

Pos logit contributions
its+0.020
ower+0.019
isel+0.018
apy+0.018
aged+0.018
Neg logit contributions
 ranger-0.012
 years-0.011
 clearing-0.011
 since-0.011
 café-0.010
Token play
Token ID711
Feature activation-4.45e-02

Pos logit contributions
 ranger+0.009
 years+0.009
 clearing+0.009
 since+0.009
 café+0.009
Neg logit contributions
its-0.009
ower-0.008
apy-0.008
isel-0.008
aged-0.008
Token with
Token ID351
Feature activation-2.54e-03

Pos logit contributions
its+0.087
apy+0.081
ower+0.081
aged+0.078
ikes+0.078
Neg logit contributions
 ranger-0.063
 years-0.059
 since-0.059
 Tooth-0.058
 café-0.057
Token the
Token ID262
Feature activation-7.02e-04

Pos logit contributions
its+0.005
ower+0.005
isel+0.005
ikes+0.005
apy+0.005
Neg logit contributions
 ranger-0.004
 years-0.003
 since-0.003
 clearing-0.003
 café-0.003
Token boss
Token ID6478
Feature activation-9.98e-03

Pos logit contributions
its+0.001
ower+0.001
apy+0.001
isel+0.001
aged+0.001
Neg logit contributions
 ranger-0.001
 years-0.001
 clearing-0.001
 since-0.001
 café-0.001
Tokeny
Token ID88
Feature activation-1.16e-01

Pos logit contributions
its+0.020
ower+0.018
apy+0.018
isel+0.017
aged+0.017
Neg logit contributions
 ranger-0.015
 years-0.014
 since-0.014
 clearing-0.014
 café-0.014
Token dog
Token ID3290
Feature activation+4.97e-03

Pos logit contributions
its+0.238
ower+0.223
apy+0.216
aged+0.214
isel+0.212
Neg logit contributions
 ranger-0.161
 years-0.154
 since-0.150
 clearing-0.149
 Tooth-0.147
Token again
Token ID757
Feature activation+6.01e-02

Pos logit contributions
 Tooth+0.006
 ranger+0.006
 clearing+0.006
 years+0.006
 dentist+0.006
Neg logit contributions
its-0.010
ower-0.009
apy-0.009
ikes-0.009
aged-0.009
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
 ranger+0.080
 dentist+0.073
 Tooth+0.073
 clearing+0.073
 grizz+0.073
Neg logit contributions
its-0.120
ower-0.115
apy-0.113
aged-0.110
ikes-0.107
Token<|endoftext|>
Token ID50256
Feature activation+3.62e-02

Pos logit contributions
its+0.025
ower+0.023
apy+0.023
aged+0.023
ikes+0.023
Neg logit contributions
 ranger-0.013
 years-0.013
 clearing-0.012
 since-0.012
 banquet-0.012
TokenOnce
Token ID7454
Feature activation-1.48e-02

Pos logit contributions
 ranger+0.050
 years+0.048
 since+0.047
 Tooth+0.046
 banquet+0.045
Neg logit contributions
its-0.072
ower-0.065
apy-0.065
ikes-0.064
aged-0.062
Token play
Token ID711
Feature activation-3.69e-02

Pos logit contributions
 ranger+0.023
 years+0.022
 since+0.021
 clearing+0.021
 Tooth+0.021
Neg logit contributions
its-0.021
ower-0.020
aged-0.019
apy-0.019
isel-0.019
Token with
Token ID351
Feature activation-6.73e-03

Pos logit contributions
its+0.087
ower+0.082
isel+0.081
apy+0.080
aged+0.080
Neg logit contributions
 ranger-0.041
 years-0.038
 clearing-0.036
 since-0.036
 Tooth-0.035
Token the
Token ID262
Feature activation-5.69e-03

Pos logit contributions
its+0.015
ower+0.014
isel+0.014
ikes+0.014
apy+0.014
Neg logit contributions
 years-0.008
 ranger-0.008
 dentist-0.007
 since-0.007
 Tooth-0.007
Token ash
Token ID12530
Feature activation+2.11e-02

Pos logit contributions
its+0.012
isel+0.011
apy+0.011
ower+0.011
ikes+0.011
Neg logit contributions
 ranger-0.008
 clearing-0.007
 dentist-0.007
 years-0.007
 cafe-0.007
Tokentr
Token ID2213
Feature activation-9.80e-03

Pos logit contributions
 ranger+0.030
 years+0.029
 clearing+0.029
 since+0.028
 café+0.028
Neg logit contributions
its-0.042
ower-0.040
ikes-0.038
apy-0.038
aged-0.037
Tokenay
Token ID323
Feature activation-1.33e-01

Pos logit contributions
its+0.015
aged+0.014
isel+0.013
ower+0.013
apy+0.013
Neg logit contributions
 ranger-0.018
 years-0.018
 since-0.017
 dentist-0.017
 Tooth-0.017
Token.
Token ID13
Feature activation-1.57e-02

Pos logit contributions
its+0.319
isel+0.314
apy+0.301
aged+0.300
ower+0.300
Neg logit contributions
 ranger-0.132
 years-0.131
 since-0.124
 dentist-0.119
 Tooth-0.116
Token It
Token ID632
Feature activation-2.88e-02

Pos logit contributions
its+0.030
ower+0.028
apy+0.028
aged+0.027
isel+0.027
Neg logit contributions
 ranger-0.024
 years-0.022
 clearing-0.022
 since-0.022
 café-0.022
Token is
Token ID318
Feature activation+3.46e-02

Pos logit contributions
its+0.062
ower+0.057
apy+0.056
aged+0.056
ikes+0.055
Neg logit contributions
 ranger-0.037
 years-0.036
 clearing-0.035
 since-0.034
 café-0.034
Token dangerous
Token ID4923
Feature activation+2.46e-02

Pos logit contributions
 ranger+0.059
 café+0.058
 clearing+0.056
 cafe+0.056
 enclosure+0.055
Neg logit contributions
its-0.058
ower-0.053
aged-0.053
apy-0.052
isel-0.050
Token.
Token ID13
Feature activation-1.44e-02

Pos logit contributions
 ranger+0.032
 clearing+0.031
 years+0.030
 café+0.029
 Tooth+0.029
Neg logit contributions
its-0.052
ower-0.048
ikes-0.047
aged-0.046
apy-0.046
Token the
Token ID262
Feature activation+1.02e-02

Pos logit contributions
its+0.027
apy+0.025
aged+0.024
ower+0.024
isel+0.024
Neg logit contributions
 ranger-0.021
 years-0.021
 since-0.021
 banquet-0.020
 Fairy-0.020
Token leaves
Token ID5667
Feature activation+1.16e-02

Pos logit contributions
 ranger+0.014
 years+0.013
 since+0.013
 clearing+0.013
 café+0.012
Neg logit contributions
its-0.021
ower-0.020
apy-0.019
aged-0.019
isel-0.019
Token and
Token ID290
Feature activation-7.73e-03

Pos logit contributions
 ranger+0.012
 years+0.012
 clearing+0.011
 Tooth+0.011
 café+0.011
Neg logit contributions
its-0.027
ower-0.026
apy-0.025
aged-0.025
isel-0.025
Token scattered
Token ID16830
Feature activation-3.86e-02

Pos logit contributions
its+0.014
apy+0.013
aged+0.013
ower+0.012
isel+0.012
Neg logit contributions
 years-0.012
 ranger-0.012
 clearing-0.011
 Tooth-0.011
 since-0.011
Token them
Token ID606
Feature activation-8.82e-02

Pos logit contributions
its+0.073
apy+0.066
ower+0.066
isel+0.065
aged+0.065
Neg logit contributions
 ranger-0.060
 years-0.057
 Tooth-0.056
 clearing-0.056
 since-0.055
Token everywhere
Token ID8347
Feature activation-1.19e-01

Pos logit contributions
its+0.191
ower+0.179
isel+0.176
apy+0.175
ikes+0.172
Neg logit contributions
 ranger-0.114
 years-0.107
 since-0.104
 clearing-0.102
 café-0.098
Token.
Token ID13
Feature activation-5.27e-03

Pos logit contributions
its+0.288
ower+0.271
isel+0.265
aged+0.264
apy+0.263
Neg logit contributions
 ranger-0.125
 years-0.116
 since-0.112
 clearing-0.110
 Tooth-0.106
Token
Token ID198
Feature activation+3.98e-03

Pos logit contributions
its+0.011
apy+0.011
ower+0.010
aged+0.010
isel+0.010
Neg logit contributions
 years-0.007
 ranger-0.006
 since-0.006
 clearing-0.006
 banquet-0.006
Token
Token ID198
Feature activation+1.25e-02

Pos logit contributions
 ranger+0.004
 years+0.003
 clearing+0.003
 since+0.003
 café+0.003
Neg logit contributions
its-0.010
ower-0.010
aged-0.009
isel-0.009
apy-0.009
TokenS
Token ID50
Feature activation-3.72e-05

Pos logit contributions
 ranger+0.017
 years+0.016
 Tooth+0.016
 Prince+0.016
 Fairy+0.016
Neg logit contributions
its-0.025
apy-0.024
ower-0.024
aged-0.023
isel-0.023
Tokenara
Token ID3301
Feature activation+2.95e-02

Pos logit contributions
its+0.000
ower+0.000
ikes+0.000
oom+0.000
isel+0.000
Neg logit contributions
 Prince-0.000
 ranger-0.000
 years-0.000
 clearing-0.000
 Fairy-0.000