TOP ACTIVATIONS
MAX = 15.679

scared of us ? â Sue suggested .
thank you â . Her family was so
taking something that doesn â t belong to you
some jelly fish ! â replied Jack happily .
of the toilet . â The little boy
to take someone else â s thing without asking
then the bees won â t be scared of
M az zy â s mom smiled .
t speed ? â Sp ike felt
after hearing her mum â s words . She
S ail ors Wanted â . Do you want
for my birthday . â S ally
â â The scale is
It â s for a special
t it beautiful ? â Mark nodded and
to break into people â s homes . Sam
about my hat ? â said Jenny , looking around
he heard a baby â s cry .
were also very persistent â so they gathered
on Ab ig ail â s bike . When

MIN ACTIVATIONS
MIN = -17.502

know the box was for charity . They thought it was
. It belongs to the charity . We provide clothes and
to take them to the charity shop , where other children
. They belong to a charity that helps poor kids .
all your toys to a charity that helps children in need
" Let 's go , mate y !" Ben said .
! They are for the charity ! I was going to
She drove away to the charity shop . L
" Ar rr , mate y , let 's sail
You can be the first mate today ." They
It needs to find a mate and lay eggs . Then
, " Ah oy , mate y . I 'm Captain
" Ar rr , mate y , give me your
, you are my best mate !" Tom said . He
" Ar rr , mate y , this is our
this noise to find a mate . It only comes out
say ' Ah oy , mate y !' and ' Land
, " Ar rr , mate y !" "
shouting " Ah oy , mate y !" and " Sh
and you 'll be the mate . We 'll sail across

INTERVAL 7.384 - 15.679
CONTAINS 3.941%

Max â s mom was very
there . Mom my and Sarah danced together until
saw the person again . But she never forgot that night
At the end of the day , the cat went home
regret wearing this belt . It got me stuck on the

INTERVAL -0.911 - 7.384
CONTAINS 54.587%

the marble was special and fragile , so he said to
down fast and laugh . They have fun on the slide
a little longer . One day , Ben went
the box again . He thought it was a terrible place
to get along and help each other in the wedding .

INTERVAL -9.206 - -0.911
CONTAINS 39.647%

to make Mom my sad or mad . She says no
upon a time , there was a thoughtful hunter . He
brave and comfortable even when her dream was far away .
hair to look pretty and different today ." The ha ird
She did not see the small stick on the leaf .

INTERVAL -17.502 - -9.206
CONTAINS 1.825%

is sorry . He wishes they never found the book .
Mia said . They ate all the corn and
Tom asked . " Of course ," dad said
too . From then on they were a happy family .
Sara says . " Thank you , Sara .
Token scared
Token ID12008
Feature activation+4.11e+00

Pos logit contributions
ves+0.179
vern+0.177
ades+0.162
 backup+0.159
keys+0.158
Neg logit contributions
 around-0.142
cy-0.139
 air-0.136
rated-0.134
et-0.128
Token of
Token ID286
Feature activation-4.15e+00

Pos logit contributions
cy+0.226
rated+0.216
 air+0.213
|+0.213
et+0.213
Neg logit contributions
ves-0.202
vern-0.201
ades-0.184
 mercy-0.184
 forgiveness-0.179
Token us
Token ID514
Feature activation+8.35e-01

Pos logit contributions
ves+0.236
vern+0.231
ades+0.211
 backup+0.208
keys+0.206
Neg logit contributions
 around-0.214
cy-0.208
 air-0.203
rated-0.202
et-0.194
Token?
Token ID30
Feature activation-1.24e+00

Pos logit contributions
cy+0.042
 air+0.041
 around+0.041
rated+0.040
et+0.039
Neg logit contributions
ves-0.046
vern-0.046
ades-0.042
keys-0.041
 mercy-0.040
Tokenâ
Token ID22940
Feature activation+1.54e+00

Pos logit contributions
ves+0.072
vern+0.072
 backup+0.066
ades+0.066
keys+0.065
Neg logit contributions
rated-0.060
 around-0.059
et-0.058
 air-0.057
cy-0.056
Token
Token ID26391
Feature activation+1.57e+01

Pos logit contributions
 around+0.056
cy+0.055
 through+0.051
 air+0.050
 down+0.049
Neg logit contributions
vern-0.098
ves-0.098
ggy-0.094
His-0.087
 mercy-0.085
Token Sue
Token ID26089
Feature activation+3.40e+00

Pos logit contributions
 around+0.855
cy+0.824
rated+0.817
 air+0.815
et+0.792
Neg logit contributions
ves-0.884
vern-0.840
ades-0.777
keys-0.756
 backup-0.726
Token suggested
Token ID5220
Feature activation-5.74e+00

Pos logit contributions
 around+0.172
rated+0.171
cy+0.171
 air+0.169
|+0.167
Neg logit contributions
ves-0.183
vern-0.172
keys-0.159
ades-0.156
 mercy-0.154
Token.
Token ID13
Feature activation+9.79e-01

Pos logit contributions
vern+0.274
ves+0.267
ades+0.251
 backup+0.238
keys+0.234
Neg logit contributions
 around-0.361
 air-0.334
cy-0.319
et-0.315
rated-0.314
Token
Token ID198
Feature activation+1.22e-01

Pos logit contributions
 around+0.046
rated+0.045
et+0.043
cy+0.043
 air+0.043
Neg logit contributions
ves-0.060
vern-0.058
ades-0.054
 backup-0.053
keys-0.052
Token
Token ID198
Feature activation+9.76e-02

Pos logit contributions
 around+0.006
cy+0.005
 air+0.005
|+0.005
rated+0.005
Neg logit contributions
ves-0.007
vern-0.007
ades-0.007
 mercy-0.007
keys-0.007
Token
Token ID129
Feature activation+2.64e+00

Pos logit contributions
 around+0.908
cy+0.878
rated+0.876
 air+0.869
et+0.844
Neg logit contributions
ves-0.817
vern-0.771
ades-0.710
keys-0.685
 backup-0.665
Token
Token ID241
Feature activation-1.14e+00

Pos logit contributions
cy+0.141
 around+0.125
rated+0.123
 air+0.118
 down+0.111
Neg logit contributions
ves-0.161
vern-0.155
ggy-0.141
ades-0.133
His-0.133
Tokenthank
Token ID40716
Feature activation+2.70e-01

Pos logit contributions
ves+0.057
vern+0.053
His+0.048
ades+0.048
Some+0.044
Neg logit contributions
 around-0.065
cy-0.064
rated-0.064
 air-0.064
et-0.063
Token you
Token ID345
Feature activation+3.29e-01

Pos logit contributions
 around+0.017
cy+0.016
rated+0.016
 air+0.016
et+0.016
Neg logit contributions
ves-0.013
vern-0.012
ades-0.011
 backup-0.011
keys-0.011
Tokenâ
Token ID22940
Feature activation+1.55e+00

Pos logit contributions
 around+0.017
cy+0.017
 air+0.016
rated+0.016
et+0.015
Neg logit contributions
ves-0.019
vern-0.018
ades-0.017
 backup-0.016
keys-0.016
Token
Token ID26391
Feature activation+1.57e+01

Pos logit contributions
 around+0.058
ening+0.051
cy+0.050
 through+0.047
 air+0.047
Neg logit contributions
ves-0.098
vern-0.096
ggy-0.093
His-0.089
 forgiveness-0.086
Token.
Token ID13
Feature activation+4.95e-01

Pos logit contributions
 around+0.908
cy+0.869
 air+0.868
rated+0.858
et+0.835
Neg logit contributions
ves-0.807
vern-0.782
ades-0.714
keys-0.692
 backup-0.688
Token Her
Token ID2332
Feature activation-1.66e+00

Pos logit contributions
rated+0.020
 around+0.020
et+0.019
cy+0.018
ening+0.018
Neg logit contributions
ves-0.032
vern-0.032
 backup-0.030
ades-0.029
His-0.029
Token family
Token ID1641
Feature activation-4.53e+00

Pos logit contributions
ves+0.091
vern+0.089
ades+0.081
 backup+0.079
keys+0.078
Neg logit contributions
 around-0.089
cy-0.087
rated-0.085
 air-0.084
et-0.082
Token was
Token ID373
Feature activation-9.29e-01

Pos logit contributions
ves+0.278
vern+0.271
ades+0.252
keys+0.246
 backup+0.244
Neg logit contributions
 around-0.205
rated-0.198
cy-0.198
 air-0.195
et-0.188
Token so
Token ID523
Feature activation+5.70e+00

Pos logit contributions
ves+0.054
vern+0.053
ades+0.049
 backup+0.048
keys+0.047
Neg logit contributions
cy-0.046
 around-0.045
rated-0.044
 air-0.043
et-0.042
Token taking
Token ID2263
Feature activation-4.54e+00

Pos logit contributions
 around+0.041
 air+0.040
cy+0.037
rated+0.036
 down+0.036
Neg logit contributions
vern-0.043
ves-0.042
ades-0.040
 backup-0.038
keys-0.037
Token something
Token ID1223
Feature activation-1.24e+01

Pos logit contributions
ves+0.224
vern+0.219
ades+0.198
 backup+0.193
keys+0.191
Neg logit contributions
 around-0.270
cy-0.261
 air-0.257
rated-0.255
et-0.248
Token that
Token ID326
Feature activation-2.85e+00

Pos logit contributions
ves+0.686
vern+0.655
ades+0.620
keys+0.598
 backup+0.591
Neg logit contributions
 around-0.723
 air-0.644
cy-0.605
 down-0.604
rated-0.599
Token doesn
Token ID1595
Feature activation+5.30e+00

Pos logit contributions
ves+0.176
vern+0.172
ades+0.157
keys+0.155
 forgiveness+0.154
Neg logit contributions
 around-0.127
cy-0.126
 air-0.119
rated-0.119
et-0.119
Tokenâ
Token ID22940
Feature activation+1.44e+00

Pos logit contributions
 around+0.321
cy+0.307
 air+0.306
rated+0.301
et+0.294
Neg logit contributions
ves-0.256
vern-0.251
ades-0.227
 backup-0.220
keys-0.219
Token
Token ID26391
Feature activation+1.57e+01

Pos logit contributions
 around+0.053
 air+0.046
cy+0.044
ening+0.043
 down+0.042
Neg logit contributions
ves-0.099
vern-0.095
 forgiveness-0.092
ggy-0.088
 mercy-0.088
Token
Token ID8151
Feature activation+1.16e+00

Pos logit contributions
 around+0.882
cy+0.843
 air+0.838
rated+0.821
et+0.800
Neg logit contributions
ves-0.816
vern-0.805
ades-0.734
 backup-0.716
 mercy-0.709
Tokent
Token ID83
Feature activation-1.33e+00

Pos logit contributions
 around+0.077
 air+0.077
rated+0.075
cy+0.074
et+0.073
Neg logit contributions
ves-0.048
vern-0.047
ades-0.042
keys-0.040
 backup-0.038
Token belong
Token ID5594
Feature activation-8.80e-01

Pos logit contributions
ves+0.075
vern+0.075
 mercy+0.067
 forgiveness+0.066
 backup+0.066
Neg logit contributions
cy-0.067
 around-0.064
 air-0.062
et-0.060
rated-0.059
Token to
Token ID284
Feature activation-2.12e+00

Pos logit contributions
ves+0.045
vern+0.044
ades+0.040
keys+0.039
 backup+0.039
Neg logit contributions
 around-0.052
cy-0.049
 air-0.048
rated-0.047
et-0.046
Token you
Token ID345
Feature activation+7.14e-01

Pos logit contributions
ves+0.115
vern+0.113
ades+0.103
 backup+0.101
keys+0.100
Neg logit contributions
 around-0.116
cy-0.110
 air-0.110
rated-0.108
et-0.105
Token some
Token ID617
Feature activation-8.77e+00

Pos logit contributions
ves+0.124
vern+0.120
ades+0.111
keys+0.111
 mercy+0.106
Neg logit contributions
 around-0.106
 air-0.098
cy-0.096
 down-0.091
et-0.090
Token jelly
Token ID27644
Feature activation-5.76e+00

Pos logit contributions
ves+0.515
vern+0.499
keys+0.457
ades+0.450
 backup+0.442
Neg logit contributions
 around-0.468
 air-0.452
cy-0.419
et-0.403
rated-0.398
Tokenfish
Token ID11084
Feature activation-6.99e+00

Pos logit contributions
vern+0.328
ves+0.326
 backup+0.299
 mercy+0.296
ades+0.293
Neg logit contributions
 around-0.317
cy-0.288
 air-0.286
et-0.278
rated-0.268
Token!
Token ID0
Feature activation+5.90e-01

Pos logit contributions
ves+0.471
vern+0.464
ades+0.432
 backup+0.424
keys+0.418
Neg logit contributions
 around-0.310
cy-0.279
 air-0.277
rated-0.263
et-0.263
Tokenâ
Token ID22940
Feature activation+1.45e+00

Pos logit contributions
rated+0.026
 around+0.026
et+0.026
cy+0.025
 air+0.025
Neg logit contributions
ves-0.036
vern-0.035
 backup-0.033
ades-0.032
keys-0.032
Token
Token ID26391
Feature activation+1.57e+01

Pos logit contributions
 around+0.056
cy+0.049
 air+0.047
 down+0.047
 through+0.047
Neg logit contributions
ves-0.087
vern-0.084
ggy-0.081
His-0.078
 forgiveness-0.074
Token replied
Token ID8712
Feature activation+8.78e-02

Pos logit contributions
 around+0.872
rated+0.849
cy+0.839
 air+0.836
et+0.815
Neg logit contributions
ves-0.860
vern-0.818
ades-0.751
keys-0.724
 backup-0.704
Token Jack
Token ID3619
Feature activation+4.24e+00

Pos logit contributions
 around+0.004
 air+0.004
cy+0.004
rated+0.004
et+0.004
Neg logit contributions
vern-0.005
ves-0.005
ades-0.005
keys-0.005
 backup-0.005
Token happily
Token ID18177
Feature activation+1.41e-01

Pos logit contributions
 around+0.207
 air+0.204
cy+0.203
rated+0.203
|+0.198
Neg logit contributions
ves-0.242
vern-0.231
ades-0.211
keys-0.208
 backup-0.206
Token.
Token ID13
Feature activation+7.08e-01

Pos logit contributions
 around+0.007
cy+0.006
 air+0.006
rated+0.006
et+0.006
Neg logit contributions
ves-0.009
vern-0.009
ades-0.008
 backup-0.008
keys-0.008
Token
Token ID220
Feature activation+3.79e+00

Pos logit contributions
rated+0.036
 around+0.036
et+0.035
 air+0.034
cy+0.034
Neg logit contributions
ves-0.039
vern-0.038
ades-0.035
 backup-0.035
His-0.035
Token of
Token ID286
Feature activation-4.11e+00

Pos logit contributions
 around+0.123
cy+0.120
 air+0.118
rated+0.116
et+0.113
Neg logit contributions
ves-0.147
vern-0.144
ades-0.133
keys-0.129
 backup-0.128
Token the
Token ID262
Feature activation+4.76e+00

Pos logit contributions
ves+0.232
vern+0.227
ades+0.211
keys+0.206
 backup+0.201
Neg logit contributions
 around-0.219
 air-0.211
cy-0.203
et-0.197
rated-0.195
Token toilet
Token ID16146
Feature activation-8.95e-01

Pos logit contributions
 around+0.233
cy+0.233
rated+0.225
et+0.216
 air+0.214
Neg logit contributions
ves-0.272
vern-0.268
ades-0.250
 backup-0.246
 forgiveness-0.240
Token.
Token ID13
Feature activation+7.58e-01

Pos logit contributions
ves+0.054
vern+0.052
ades+0.048
keys+0.047
 backup+0.047
Neg logit contributions
 around-0.043
cy-0.042
rated-0.041
 air-0.041
|-0.039
Tokenâ
Token ID22940
Feature activation+1.45e+00

Pos logit contributions
 around+0.037
rated+0.037
cy+0.035
et+0.035
 air+0.034
Neg logit contributions
ves-0.044
vern-0.043
 backup-0.040
ades-0.039
His-0.038
Token
Token ID26391
Feature activation+1.57e+01

Pos logit contributions
 around+0.053
cy+0.048
 down+0.046
 air+0.045
 through+0.043
Neg logit contributions
ves-0.096
vern-0.093
ggy-0.085
His-0.085
keys-0.081
Token
Token ID198
Feature activation-7.03e-02

Pos logit contributions
 around+0.880
cy+0.850
rated+0.844
 air+0.841
et+0.814
Neg logit contributions
ves-0.855
vern-0.813
ades-0.749
keys-0.720
 backup-0.704
Token
Token ID198
Feature activation-8.96e-02

Pos logit contributions
ves+0.004
vern+0.004
ades+0.004
keys+0.004
 backup+0.004
Neg logit contributions
 around-0.004
cy-0.003
 air-0.003
rated-0.003
et-0.003
TokenThe
Token ID464
Feature activation-1.47e+00

Pos logit contributions
ves+0.004
vern+0.004
 mercy+0.003
ades+0.003
keys+0.003
Neg logit contributions
 around-0.006
cy-0.005
 air-0.005
|-0.005
rated-0.005
Token little
Token ID1310
Feature activation-1.37e+00

Pos logit contributions
ves+0.077
vern+0.076
ades+0.068
keys+0.067
 backup+0.066
Neg logit contributions
 around-0.085
 air-0.082
cy-0.080
rated-0.078
et-0.076
Token boy
Token ID2933
Feature activation+7.41e+00

Pos logit contributions
ves+0.081
vern+0.078
 forgiveness+0.074
ades+0.074
 mercy+0.074
Neg logit contributions
 around-0.062
rated-0.061
|-0.057
et-0.057
cy-0.057
Token to
Token ID284
Feature activation-2.24e+00

Pos logit contributions
ves+0.069
vern+0.068
ades+0.063
 backup+0.061
keys+0.061
Neg logit contributions
 around-0.065
 air-0.061
cy-0.061
rated-0.059
et-0.058
Token take
Token ID1011
Feature activation-2.72e+00

Pos logit contributions
ves+0.122
vern+0.120
ades+0.110
 backup+0.107
keys+0.107
Neg logit contributions
 around-0.121
cy-0.116
 air-0.115
rated-0.113
et-0.110
Token someone
Token ID2130
Feature activation-8.99e+00

Pos logit contributions
ves+0.132
vern+0.129
 backup+0.118
ades+0.114
 mercy+0.113
Neg logit contributions
rated-0.158
cy-0.157
 around-0.154
 air-0.147
et-0.147
Token else
Token ID2073
Feature activation-9.40e+00

Pos logit contributions
ves+0.478
vern+0.461
ades+0.427
keys+0.407
 backup+0.403
Neg logit contributions
 around-0.535
cy-0.494
 air-0.487
rated-0.472
et-0.466
Tokenâ
Token ID22940
Feature activation+1.45e+00

Pos logit contributions
ves+0.572
vern+0.553
ades+0.517
keys+0.501
 backup+0.496
Neg logit contributions
 around-0.488
cy-0.447
 air-0.442
rated-0.425
et-0.411
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.050
 air+0.044
cy+0.043
ening+0.042
 down+0.039
Neg logit contributions
vern-0.091
ves-0.091
 forgiveness-0.089
 mercy-0.087
His-0.085
Token
Token ID8151
Feature activation+1.07e+00

Pos logit contributions
 around+0.873
cy+0.833
 air+0.824
rated+0.807
et+0.787
Neg logit contributions
ves-0.824
vern-0.816
ades-0.744
 backup-0.728
 mercy-0.722
Tokens
Token ID82
Feature activation-5.92e+00

Pos logit contributions
 around+0.065
 air+0.064
rated+0.063
cy+0.062
et+0.061
Neg logit contributions
ves-0.050
vern-0.049
ades-0.044
keys-0.042
 backup-0.042
Token thing
Token ID1517
Feature activation+1.27e+00

Pos logit contributions
ves+0.346
vern+0.340
ades+0.312
 backup+0.306
keys+0.303
Neg logit contributions
 around-0.293
cy-0.283
 air-0.278
rated-0.275
et-0.267
Token without
Token ID1231
Feature activation-3.00e+00

Pos logit contributions
 around+0.068
cy+0.063
 air+0.062
rated+0.060
et+0.060
Neg logit contributions
ves-0.072
vern-0.071
ades-0.065
 backup-0.064
keys-0.063
Token asking
Token ID4737
Feature activation-3.90e+00

Pos logit contributions
ves+0.169
vern+0.164
ades+0.158
keys+0.148
 backup+0.139
Neg logit contributions
 around-0.163
 air-0.158
et-0.147
cy-0.145
ening-0.144
Token then
Token ID788
Feature activation+2.15e+00

Pos logit contributions
 around+0.129
 air+0.122
cy+0.121
rated+0.118
et+0.115
Neg logit contributions
ves-0.125
vern-0.124
ades-0.113
 backup-0.109
keys-0.108
Token the
Token ID262
Feature activation+4.97e+00

Pos logit contributions
 around+0.119
 air+0.113
cy+0.112
rated+0.108
et+0.105
Neg logit contributions
vern-0.117
ves-0.117
ades-0.107
 backup-0.102
keys-0.101
Token bees
Token ID17002
Feature activation-5.25e-01

Pos logit contributions
 around+0.250
cy+0.241
rated+0.235
 air+0.233
et+0.226
Neg logit contributions
ves-0.288
vern-0.281
ades-0.260
keys-0.255
 backup-0.254
Token won
Token ID1839
Feature activation+4.89e+00

Pos logit contributions
ves+0.030
vern+0.028
ades+0.027
keys+0.027
 backup+0.026
Neg logit contributions
cy-0.025
 around-0.025
rated-0.024
 air-0.024
et-0.024
Tokenâ
Token ID22940
Feature activation+1.48e+00

Pos logit contributions
 around+0.294
cy+0.284
 air+0.282
rated+0.278
et+0.271
Neg logit contributions
ves-0.238
vern-0.233
ades-0.210
 backup-0.203
keys-0.203
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.054
cy+0.049
 air+0.046
ening+0.045
 down+0.043
Neg logit contributions
ves-0.106
vern-0.104
ggy-0.095
His-0.093
 mercy-0.093
Token
Token ID8151
Feature activation+1.04e+00

Pos logit contributions
 around+0.983
cy+0.944
 air+0.940
rated+0.924
et+0.904
Neg logit contributions
ves-0.716
vern-0.703
ades-0.631
 backup-0.612
keys-0.607
Tokent
Token ID83
Feature activation-1.54e+00

Pos logit contributions
 around+0.068
 air+0.067
cy+0.066
rated+0.066
et+0.064
Neg logit contributions
ves-0.044
vern-0.043
ades-0.039
keys-0.037
 backup-0.036
Token be
Token ID307
Feature activation-2.97e+00

Pos logit contributions
ves+0.087
vern+0.085
ades+0.080
 backup+0.078
keys+0.076
Neg logit contributions
 around-0.084
rated-0.076
 air-0.076
cy-0.075
et-0.072
Token scared
Token ID12008
Feature activation+4.11e+00

Pos logit contributions
ves+0.179
vern+0.177
ades+0.162
 backup+0.159
keys+0.158
Neg logit contributions
 around-0.142
cy-0.139
 air-0.136
rated-0.134
et-0.128
Token of
Token ID286
Feature activation-4.15e+00

Pos logit contributions
cy+0.226
rated+0.216
 air+0.213
|+0.213
et+0.213
Neg logit contributions
ves-0.202
vern-0.201
ades-0.184
 mercy-0.184
 forgiveness-0.179
Token
Token ID198
Feature activation-5.21e-01

Pos logit contributions
ves+0.028
vern+0.027
ades+0.025
 backup+0.024
keys+0.024
Neg logit contributions
 around-0.026
cy-0.025
 air-0.025
rated-0.024
et-0.024
TokenM
Token ID44
Feature activation-6.60e+00

Pos logit contributions
ves+0.023
vern+0.023
 mercy+0.021
ades+0.020
keys+0.020
Neg logit contributions
 around-0.032
cy-0.031
|-0.030
 air-0.030
amp-0.029
Tokenaz
Token ID1031
Feature activation+1.49e+01

Pos logit contributions
ves+0.320
vern+0.313
ades+0.282
 backup+0.276
keys+0.272
Neg logit contributions
 around-0.396
cy-0.383
 air-0.382
rated-0.374
et-0.367
Tokenzy
Token ID7357
Feature activation+1.11e+01

Pos logit contributions
 air+0.610
 around+0.596
cy+0.595
rated+0.563
 down+0.531
Neg logit contributions
ves-1.040
vern-0.933
ades-0.900
ggy-0.870
keys-0.865
Tokenâ
Token ID22940
Feature activation+1.35e+00

Pos logit contributions
 around+0.590
 air+0.567
rated+0.566
cy+0.565
|+0.544
Neg logit contributions
ves-0.600
vern-0.547
keys-0.528
ades-0.522
 mercy-0.493
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.052
 down+0.042
cy+0.041
 through+0.041
 air+0.040
Neg logit contributions
vern-0.081
His-0.077
ves-0.076
 forgiveness-0.074
ggy-0.073
Token
Token ID8151
Feature activation+1.09e+00

Pos logit contributions
 around+0.867
 air+0.827
cy+0.826
rated+0.819
et+0.790
Neg logit contributions
ves-0.844
vern-0.821
ades-0.753
keys-0.730
 backup-0.724
Tokens
Token ID82
Feature activation-6.04e+00

Pos logit contributions
 air+0.054
 around+0.054
rated+0.053
cy+0.051
ening+0.050
Neg logit contributions
ves-0.064
vern-0.061
ades-0.058
keys-0.053
 backup-0.053
Token mom
Token ID1995
Feature activation-3.16e+00

Pos logit contributions
ves+0.271
vern+0.269
ades+0.235
 backup+0.229
keys+0.227
Neg logit contributions
 around-0.397
 air-0.378
cy-0.367
et-0.356
rated-0.355
Token smiled
Token ID13541
Feature activation-2.26e+00

Pos logit contributions
ves+0.180
vern+0.170
ades+0.164
keys+0.160
 mercy+0.157
Neg logit contributions
 around-0.154
rated-0.149
cy-0.149
 air-0.147
|-0.145
Token.
Token ID13
Feature activation+5.50e-01

Pos logit contributions
ves+0.143
vern+0.142
ades+0.132
 backup+0.128
keys+0.128
Neg logit contributions
 around-0.100
cy-0.096
 air-0.095
rated-0.093
et-0.090
Token
Token ID8151
Feature activation+1.09e+00

Pos logit contributions
 around+0.877
cy+0.837
 air+0.831
rated+0.814
et+0.795
Neg logit contributions
ves-0.799
vern-0.795
ades-0.722
 backup-0.706
 mercy-0.702
Tokent
Token ID83
Feature activation-1.47e+00

Pos logit contributions
 around+0.071
 air+0.070
rated+0.068
cy+0.068
et+0.067
Neg logit contributions
ves-0.048
vern-0.046
ades-0.042
keys-0.040
 backup-0.039
Token speed
Token ID2866
Feature activation+1.49e+00

Pos logit contributions
ves+0.085
vern+0.083
ades+0.076
keys+0.074
 backup+0.074
Neg logit contributions
 around-0.075
cy-0.073
 air-0.072
rated-0.070
et-0.069
Token?
Token ID30
Feature activation-1.22e+00

Pos logit contributions
cy+0.071
rated+0.070
 air+0.069
 around+0.068
|+0.066
Neg logit contributions
ves-0.086
vern-0.084
ades-0.079
 backup-0.075
 mercy-0.074
Tokenâ
Token ID22940
Feature activation+1.55e+00

Pos logit contributions
vern+0.077
ves+0.077
 backup+0.072
ades+0.070
keys+0.070
Neg logit contributions
rated-0.052
 around-0.051
et-0.050
 air-0.048
cy-0.048
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.054
cy+0.051
 through+0.048
 air+0.047
ening+0.046
Neg logit contributions
ves-0.101
vern-0.098
ggy-0.095
His-0.090
 forgiveness-0.086
Token
Token ID198
Feature activation+1.96e-01

Pos logit contributions
 around+0.875
rated+0.842
cy+0.842
 air+0.835
et+0.812
Neg logit contributions
ves-0.861
vern-0.814
ades-0.755
keys-0.730
 backup-0.708
Token
Token ID198
Feature activation+1.60e-01

Pos logit contributions
 around+0.010
cy+0.010
 air+0.010
rated+0.009
et+0.009
Neg logit contributions
ves-0.011
vern-0.011
ades-0.010
 backup-0.010
keys-0.010
TokenSp
Token ID4561
Feature activation-1.57e+00

Pos logit contributions
 around+0.010
cy+0.010
 air+0.009
|+0.009
rated+0.009
Neg logit contributions
ves-0.007
vern-0.007
 mercy-0.006
ades-0.006
 backup-0.006
Tokenike
Token ID522
Feature activation+1.81e+00

Pos logit contributions
ves+0.073
vern+0.071
ades+0.064
keys+0.061
 backup+0.060
Neg logit contributions
 around-0.099
 air-0.096
cy-0.095
rated-0.094
et-0.091
Token felt
Token ID2936
Feature activation+2.66e+00

Pos logit contributions
 around+0.092
cy+0.089
rated+0.088
 air+0.088
et+0.084
Neg logit contributions
ves-0.104
vern-0.097
ades-0.091
keys-0.090
 backup-0.088
Token after
Token ID706
Feature activation+9.49e-01

Pos logit contributions
 around+0.045
 air+0.041
cy+0.041
rated+0.040
et+0.038
Neg logit contributions
ves-0.067
vern-0.065
ades-0.062
keys-0.060
 backup-0.059
Token hearing
Token ID4854
Feature activation-1.53e+00

Pos logit contributions
 around+0.049
 air+0.047
cy+0.043
et+0.042
rated+0.042
Neg logit contributions
ves-0.054
vern-0.054
ades-0.051
 backup-0.048
keys-0.048
Token her
Token ID607
Feature activation-1.34e+00

Pos logit contributions
ves+0.088
vern+0.086
ades+0.079
 backup+0.077
keys+0.077
Neg logit contributions
 around-0.079
cy-0.076
 air-0.075
rated-0.074
et-0.072
Token mum
Token ID25682
Feature activation-5.79e+00

Pos logit contributions
ves+0.067
vern+0.063
ades+0.060
 backup+0.059
keys+0.057
Neg logit contributions
 around-0.081
 air-0.077
rated-0.072
cy-0.071
 night-0.069
Tokenâ
Token ID22940
Feature activation+1.45e+00

Pos logit contributions
ves+0.316
vern+0.299
keys+0.285
 forgiveness+0.274
ades+0.274
Neg logit contributions
cy-0.293
rated-0.289
 around-0.289
 air-0.284
|-0.279
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.054
 air+0.045
 down+0.044
 through+0.041
ening+0.041
Neg logit contributions
vern-0.097
ves-0.092
 forgiveness-0.089
His-0.087
 mercy-0.087
Token
Token ID8151
Feature activation+1.07e+00

Pos logit contributions
 around+0.891
cy+0.853
 air+0.842
rated+0.823
et+0.804
Neg logit contributions
ves-0.800
vern-0.793
ades-0.719
 backup-0.709
 mercy-0.703
Tokens
Token ID82
Feature activation-6.04e+00

Pos logit contributions
 around+0.055
 air+0.054
rated+0.053
cy+0.052
et+0.050
Neg logit contributions
ves-0.061
vern-0.060
ades-0.055
keys-0.053
 backup-0.053
Token words
Token ID2456
Feature activation-5.64e+00

Pos logit contributions
ves+0.314
vern+0.307
ades+0.283
keys+0.274
 backup+0.274
Neg logit contributions
 around-0.348
 air-0.330
cy-0.324
rated-0.321
et-0.313
Token.
Token ID13
Feature activation+4.80e-01

Pos logit contributions
ves+0.345
vern+0.340
ades+0.313
 backup+0.305
keys+0.304
Neg logit contributions
 around-0.264
cy-0.256
 air-0.251
rated-0.248
et-0.239
Token She
Token ID1375
Feature activation+5.87e+00

Pos logit contributions
rated+0.019
 around+0.019
et+0.019
cy+0.018
 air+0.017
Neg logit contributions
vern-0.032
ves-0.031
 backup-0.029
ades-0.029
His-0.028
TokenS
Token ID50
Feature activation-7.10e+00

Pos logit contributions
ves+0.018
vern+0.017
ades+0.016
keys+0.015
 backup+0.015
Neg logit contributions
 around-0.016
cy-0.016
 air-0.015
rated-0.015
|-0.015
Tokenail
Token ID603
Feature activation+5.12e-01

Pos logit contributions
ves+0.319
vern+0.315
ades+0.300
 backup+0.277
keys+0.270
Neg logit contributions
 around-0.449
rated-0.419
 air-0.402
ening-0.399
cy-0.393
Tokenors
Token ID669
Feature activation+5.53e+00

Pos logit contributions
cy+0.024
rated+0.023
 around+0.023
|+0.023
 air+0.022
Neg logit contributions
ves-0.031
vern-0.028
ades-0.027
keys-0.027
 mercy-0.025
Token Wanted
Token ID41536
Feature activation-1.91e-01

Pos logit contributions
 around+0.244
cy+0.244
rated+0.242
 air+0.238
|+0.231
Neg logit contributions
ves-0.328
vern-0.308
ades-0.295
keys-0.286
 mercy-0.277
Tokenâ
Token ID22940
Feature activation+1.49e+00

Pos logit contributions
ves+0.011
vern+0.011
ades+0.010
 backup+0.010
keys+0.010
Neg logit contributions
 around-0.010
cy-0.009
 air-0.009
rated-0.009
et-0.009
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.053
ening+0.045
cy+0.044
 air+0.043
 down+0.041
Neg logit contributions
ves-0.103
vern-0.099
ggy-0.094
His-0.093
 forgiveness-0.087
Token
Token ID8151
Feature activation+1.36e+00

Pos logit contributions
 around+0.874
cy+0.836
 air+0.833
rated+0.821
et+0.798
Neg logit contributions
ves-0.832
vern-0.811
ades-0.743
 backup-0.719
keys-0.718
Token.
Token ID13
Feature activation+9.86e-01

Pos logit contributions
 around+0.082
 air+0.081
rated+0.079
cy+0.078
et+0.076
Neg logit contributions
ves-0.066
vern-0.063
ades-0.059
keys-0.055
 backup-0.053
Token Do
Token ID2141
Feature activation+3.28e+00

Pos logit contributions
 around+0.043
rated+0.043
et+0.041
cy+0.040
 air+0.040
Neg logit contributions
ves-0.062
vern-0.060
ades-0.056
 backup-0.056
keys-0.055
Token you
Token ID345
Feature activation+3.29e-01

Pos logit contributions
 around+0.164
 air+0.158
|+0.146
et+0.146
cy+0.145
Neg logit contributions
vern-0.180
ves-0.176
ades-0.168
 backup-0.166
 mercy-0.163
Token want
Token ID765
Feature activation+3.39e+00

Pos logit contributions
cy+0.014
 around+0.014
 air+0.014
rated+0.014
ening+0.013
Neg logit contributions
vern-0.021
ves-0.020
 backup-0.018
ades-0.018
 mercy-0.018
Token for
Token ID329
Feature activation+2.07e+00

Pos logit contributions
ves+0.457
vern+0.450
ades+0.417
 backup+0.406
keys+0.406
Neg logit contributions
 around-0.340
cy-0.325
 air-0.323
rated-0.317
et-0.306
Token my
Token ID616
Feature activation-1.99e+00

Pos logit contributions
 around+0.100
 air+0.098
et+0.088
cy+0.088
|+0.084
Neg logit contributions
ves-0.124
vern-0.123
ades-0.116
keys-0.112
 backup-0.105
Token birthday
Token ID10955
Feature activation-3.54e+00

Pos logit contributions
ves+0.088
vern+0.085
ades+0.077
 backup+0.074
keys+0.073
Neg logit contributions
 around-0.129
cy-0.124
 air-0.124
rated-0.121
et-0.119
Token.
Token ID13
Feature activation+9.36e-01

Pos logit contributions
ves+0.214
vern+0.210
ades+0.194
 backup+0.189
keys+0.189
Neg logit contributions
 around-0.171
cy-0.162
 air-0.161
rated-0.158
et-0.153
Tokenâ
Token ID22940
Feature activation+1.57e+00

Pos logit contributions
 around+0.041
rated+0.040
et+0.039
cy+0.039
 air+0.038
Neg logit contributions
ves-0.058
vern-0.058
 backup-0.054
ades-0.053
keys-0.052
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.055
cy+0.054
 air+0.050
 through+0.049
ening+0.048
Neg logit contributions
vern-0.097
ves-0.096
His-0.092
ggy-0.090
 forgiveness-0.084
Token
Token ID220
Feature activation+3.93e+00

Pos logit contributions
 around+0.843
rated+0.814
cy+0.813
 air+0.808
et+0.785
Neg logit contributions
ves-0.885
vern-0.844
ades-0.778
keys-0.750
 backup-0.737
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
 around+0.209
cy+0.202
 air+0.202
rated+0.200
et+0.197
Neg logit contributions
ves-0.218
vern-0.215
ades-0.198
 backup-0.188
keys-0.187
Token
Token ID198
Feature activation+9.41e-02

Pos logit contributions
 around+0.007
cy+0.007
 air+0.007
rated+0.007
|+0.007
Neg logit contributions
ves-0.008
vern-0.008
ades-0.008
keys-0.007
 mercy-0.007
TokenS
Token ID50
Feature activation-7.00e+00

Pos logit contributions
 around+0.006
|+0.005
cy+0.005
 air+0.005
amp+0.005
Neg logit contributions
ves-0.004
vern-0.004
 mercy-0.004
ades-0.004
keys-0.004
Tokenally
Token ID453
Feature activation+3.66e+00

Pos logit contributions
ves+0.322
vern+0.320
ades+0.309
 backup+0.278
keys+0.275
Neg logit contributions
 around-0.444
 air-0.411
rated-0.406
ening-0.388
cy-0.385
Tokenâ
Token ID22940
Feature activation+1.42e+00

Pos logit contributions
ves+0.100
vern+0.099
keys+0.092
ades+0.092
 backup+0.091
Neg logit contributions
 around-0.063
rated-0.063
et-0.061
 air-0.059
cy-0.058
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.052
cy+0.049
 through+0.045
 air+0.042
 down+0.042
Neg logit contributions
vern-0.092
ves-0.091
ggy-0.085
 forgiveness-0.081
His-0.081
Token
Token ID198
Feature activation-3.76e-03

Pos logit contributions
 around+0.855
cy+0.819
 air+0.816
rated+0.811
et+0.790
Neg logit contributions
ves-0.854
vern-0.824
ades-0.760
keys-0.737
 backup-0.724
Token
Token ID198
Feature activation-4.04e-02

Pos logit contributions
ves+0.000
vern+0.000
ades+0.000
 backup+0.000
keys+0.000
Neg logit contributions
 around-0.000
cy-0.000
 air-0.000
rated-0.000
et-0.000
Tokenâ
Token ID22940
Feature activation+1.47e+00

Pos logit contributions
ves+0.002
vern+0.002
 mercy+0.002
ades+0.002
 backup+0.002
Neg logit contributions
 around-0.002
cy-0.002
 air-0.002
|-0.002
rated-0.002
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.053
cy+0.051
 through+0.044
 down+0.044
 air+0.043
Neg logit contributions
ves-0.094
vern-0.094
ggy-0.089
His-0.086
keys-0.083
Token
Token ID129
Feature activation+2.60e+00

Pos logit contributions
 around+0.867
cy+0.828
 air+0.825
rated+0.817
et+0.794
Neg logit contributions
ves-0.847
vern-0.821
ades-0.753
keys-0.729
 backup-0.725
Token
Token ID241
Feature activation-1.02e+00

Pos logit contributions
cy+0.144
rated+0.122
 around+0.121
 air+0.120
|+0.114
Neg logit contributions
ves-0.156
vern-0.151
ggy-0.135
ades-0.130
His-0.126
TokenThe
Token ID464
Feature activation-1.37e+00

Pos logit contributions
ves+0.053
vern+0.051
ades+0.046
keys+0.044
 backup+0.044
Neg logit contributions
 around-0.058
 air-0.056
cy-0.056
rated-0.055
et-0.055
Token scale
Token ID5046
Feature activation-2.52e+00

Pos logit contributions
ves+0.073
vern+0.072
ades+0.066
 backup+0.064
keys+0.064
Neg logit contributions
 around-0.076
cy-0.073
 air-0.072
rated-0.071
et-0.069
Token is
Token ID318
Feature activation+2.02e+00

Pos logit contributions
ves+0.167
vern+0.163
ades+0.153
keys+0.150
 backup+0.149
Neg logit contributions
 around-0.104
cy-0.100
 air-0.097
rated-0.097
et-0.092
Token
Token ID26391
Feature activation+1.55e+01

Pos logit contributions
 around+0.179
cy+0.175
rated+0.165
 down+0.156
 air+0.155
Neg logit contributions
ves-0.249
vern-0.247
ggy-0.222
ades-0.220
His-0.220
Token
Token ID129
Feature activation+2.62e+00

Pos logit contributions
 around+0.899
cy+0.861
 air+0.857
rated+0.855
et+0.825
Neg logit contributions
ves-0.811
vern-0.780
ades-0.716
keys-0.687
 backup-0.680
Token
Token ID241
Feature activation-1.04e+00

Pos logit contributions
cy+0.147
 around+0.126
rated+0.125
 air+0.121
|+0.115
Neg logit contributions
ves-0.155
vern-0.149
ggy-0.131
ades-0.129
His-0.127
TokenIt
Token ID1026
Feature activation+2.73e+00

Pos logit contributions
ves+0.053
vern+0.050
ades+0.045
 backup+0.043
His+0.043
Neg logit contributions
 around-0.060
 air-0.058
cy-0.058
rated-0.057
et-0.057
Tokenâ
Token ID22940
Feature activation+1.58e+00

Pos logit contributions
 around+0.119
cy+0.116
 air+0.113
rated+0.112
et+0.108
Neg logit contributions
ves-0.176
vern-0.171
ades-0.158
keys-0.155
 backup-0.154
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.059
cy+0.053
ening+0.051
 through+0.047
 down+0.047
Neg logit contributions
ves-0.100
vern-0.097
His-0.089
ggy-0.089
 forgiveness-0.087
Token
Token ID8151
Feature activation+1.17e+00

Pos logit contributions
 around+0.900
cy+0.860
rated+0.858
 air+0.857
et+0.829
Neg logit contributions
ves-0.821
vern-0.787
ades-0.725
keys-0.698
 backup-0.692
Tokens
Token ID82
Feature activation-5.96e+00

Pos logit contributions
 air+0.074
 around+0.073
rated+0.072
ening+0.070
et+0.070
Neg logit contributions
ves-0.053
vern-0.050
ades-0.048
keys-0.043
 backup-0.041
Token for
Token ID329
Feature activation+1.95e+00

Pos logit contributions
ves+0.349
vern+0.341
ades+0.308
 backup+0.305
keys+0.304
Neg logit contributions
cy-0.295
 around-0.281
rated-0.271
et-0.261
|-0.259
Token a
Token ID257
Feature activation-3.81e+00

Pos logit contributions
 around+0.103
 air+0.101
et+0.091
cy+0.089
rated+0.087
Neg logit contributions
vern-0.109
ves-0.109
ades-0.103
keys-0.100
 backup-0.091
Token special
Token ID2041
Feature activation-3.91e+00

Pos logit contributions
ves+0.212
vern+0.207
ades+0.192
keys+0.187
 mercy+0.184
Neg logit contributions
 around-0.203
cy-0.193
 air-0.193
rated-0.188
et-0.182
Tokent
Token ID83
Feature activation-1.44e+00

Pos logit contributions
 air+0.048
 around+0.046
ening+0.046
rated+0.045
cy+0.045
Neg logit contributions
ves-0.036
vern-0.033
ades-0.032
keys-0.028
 else-0.028
Token it
Token ID340
Feature activation+4.72e+00

Pos logit contributions
ves+0.082
vern+0.081
 mercy+0.072
ades+0.072
keys+0.071
Neg logit contributions
cy-0.073
 around-0.068
 air-0.067
et-0.065
rated-0.065
Token beautiful
Token ID4950
Feature activation+7.59e-01

Pos logit contributions
 around+0.221
cy+0.218
 air+0.212
rated+0.206
et+0.201
Neg logit contributions
ves-0.287
vern-0.280
ades-0.259
keys-0.249
 mercy-0.249
Token?
Token ID30
Feature activation-1.63e+00

Pos logit contributions
cy+0.037
 around+0.037
rated+0.035
 air+0.035
|+0.034
Neg logit contributions
ves-0.044
vern-0.042
ades-0.039
 forgiveness-0.038
keys-0.037
Tokenâ
Token ID22940
Feature activation+1.48e+00

Pos logit contributions
ves+0.103
vern+0.103
ades+0.095
 backup+0.095
keys+0.094
Neg logit contributions
rated-0.069
 around-0.068
et-0.066
 air-0.065
cy-0.064
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.057
cy+0.055
 down+0.050
 through+0.048
 air+0.047
Neg logit contributions
vern-0.093
ves-0.091
ggy-0.088
His-0.083
 forgiveness-0.081
Token
Token ID198
Feature activation-1.00e-01

Pos logit contributions
 around+0.830
rated+0.802
cy+0.802
 air+0.797
et+0.769
Neg logit contributions
ves-0.899
vern-0.852
ades-0.788
keys-0.766
 backup-0.737
Token
Token ID198
Feature activation-1.65e-01

Pos logit contributions
ves+0.006
vern+0.006
ades+0.005
 backup+0.005
keys+0.005
Neg logit contributions
 around-0.005
cy-0.005
 air-0.005
rated-0.005
et-0.005
TokenMark
Token ID9704
Feature activation+2.18e+00

Pos logit contributions
ves+0.007
vern+0.007
ades+0.006
 mercy+0.006
keys+0.006
Neg logit contributions
 around-0.010
cy-0.010
 air-0.010
|-0.010
rated-0.010
Token nodded
Token ID14464
Feature activation-1.38e+00

Pos logit contributions
 around+0.111
 air+0.110
cy+0.109
rated+0.107
|+0.104
Neg logit contributions
ves-0.117
vern-0.105
keys-0.100
ades-0.100
 mercy-0.098
Token and
Token ID290
Feature activation+1.76e+00

Pos logit contributions
ves+0.087
vern+0.086
ades+0.079
keys+0.078
 backup+0.077
Neg logit contributions
 around-0.067
 air-0.061
cy-0.060
rated-0.059
et-0.058
Token to
Token ID284
Feature activation-3.29e+00

Pos logit contributions
vern+0.426
ves+0.426
ades+0.387
keys+0.379
 backup+0.379
Neg logit contributions
 around-0.377
 air-0.351
cy-0.344
et-0.339
rated-0.331
Token break
Token ID2270
Feature activation-2.46e+00

Pos logit contributions
vern+0.190
ves+0.189
ades+0.174
keys+0.168
 backup+0.158
Neg logit contributions
 around-0.176
 air-0.164
cy-0.159
et-0.156
 down-0.152
Token into
Token ID656
Feature activation+3.46e-01

Pos logit contributions
ves+0.135
vern+0.131
ades+0.121
 backup+0.118
 mercy+0.116
Neg logit contributions
 around-0.127
cy-0.125
rated-0.125
 air-0.122
|-0.119
Token people
Token ID661
Feature activation-1.27e+00

Pos logit contributions
 around+0.017
 air+0.016
cy+0.015
et+0.014
 down+0.014
Neg logit contributions
ves-0.022
vern-0.021
ades-0.020
keys-0.020
 backup-0.019
Tokenâ
Token ID22940
Feature activation+1.37e+00

Pos logit contributions
ves+0.073
vern+0.072
ades+0.066
keys+0.065
 backup+0.064
Neg logit contributions
cy-0.061
 around-0.060
rated-0.060
 air-0.060
et-0.057
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.056
cy+0.049
 air+0.047
ening+0.043
ishy+0.043
Neg logit contributions
vern-0.083
ves-0.082
 mercy-0.080
 forgiveness-0.078
 backup-0.077
Token
Token ID8151
Feature activation+8.87e-01

Pos logit contributions
 around+0.834
cy+0.801
 air+0.798
rated+0.789
et+0.766
Neg logit contributions
ves-0.875
vern-0.846
ades-0.779
keys-0.757
 backup-0.750
Tokens
Token ID82
Feature activation-6.11e+00

Pos logit contributions
 around+0.053
 air+0.052
cy+0.051
rated+0.051
et+0.049
Neg logit contributions
ves-0.043
vern-0.042
ades-0.039
keys-0.037
 backup-0.036
Token homes
Token ID5682
Feature activation-1.83e+00

Pos logit contributions
ves+0.356
vern+0.349
ades+0.322
 backup+0.314
keys+0.312
Neg logit contributions
 around-0.308
cy-0.294
 air-0.291
rated-0.287
et-0.278
Token.
Token ID13
Feature activation+5.20e-01

Pos logit contributions
ves+0.109
vern+0.108
ades+0.099
 backup+0.097
keys+0.096
Neg logit contributions
 around-0.086
cy-0.084
 air-0.083
rated-0.081
et-0.079
Token Sam
Token ID3409
Feature activation+4.80e+00

Pos logit contributions
 around+0.022
rated+0.022
et+0.021
cy+0.021
 air+0.021
Neg logit contributions
ves-0.033
vern-0.032
 backup-0.031
ades-0.030
keys-0.030
Token about
Token ID546
Feature activation+2.05e+00

Pos logit contributions
ves+0.041
vern+0.040
ades+0.037
 backup+0.037
keys+0.036
Neg logit contributions
 around-0.034
 air-0.032
cy-0.032
rated-0.031
et-0.030
Token my
Token ID616
Feature activation-2.01e+00

Pos logit contributions
 around+0.104
 air+0.098
cy+0.097
rated+0.092
et+0.092
Neg logit contributions
ves-0.121
vern-0.121
ades-0.111
 backup-0.108
keys-0.107
Token hat
Token ID6877
Feature activation-5.02e+00

Pos logit contributions
ves+0.110
vern+0.108
ades+0.099
keys+0.096
 backup+0.096
Neg logit contributions
 around-0.109
 air-0.104
cy-0.104
rated-0.101
et-0.099
Token?
Token ID30
Feature activation-1.28e+00

Pos logit contributions
ves+0.283
vern+0.276
ades+0.256
keys+0.249
 backup+0.248
Neg logit contributions
 around-0.256
cy-0.248
 air-0.245
rated-0.243
et-0.233
Tokenâ
Token ID22940
Feature activation+1.57e+00

Pos logit contributions
ves+0.089
vern+0.088
ades+0.082
 backup+0.082
keys+0.081
Neg logit contributions
 around-0.048
rated-0.047
cy-0.045
 air-0.045
et-0.044
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.057
cy+0.055
 through+0.050
 down+0.048
ening+0.047
Neg logit contributions
ves-0.100
vern-0.099
ggy-0.092
His-0.086
ades-0.086
Token said
Token ID531
Feature activation-4.37e-01

Pos logit contributions
 around+0.868
rated+0.830
cy+0.829
 air+0.825
et+0.805
Neg logit contributions
ves-0.857
vern-0.820
ades-0.764
keys-0.731
 backup-0.717
Token Jenny
Token ID28437
Feature activation+5.91e+00

Pos logit contributions
vern+0.026
ves+0.026
ades+0.024
keys+0.024
 backup+0.024
Neg logit contributions
 around-0.021
 air-0.020
cy-0.019
rated-0.019
et-0.019
Token,
Token ID11
Feature activation-5.07e-01

Pos logit contributions
 around+0.306
 air+0.302
cy+0.301
rated+0.297
|+0.283
Neg logit contributions
ves-0.333
vern-0.316
ades-0.289
keys-0.285
 backup-0.273
Token looking
Token ID2045
Feature activation+1.15e+00

Pos logit contributions
ves+0.025
vern+0.024
ades+0.022
 backup+0.022
keys+0.022
Neg logit contributions
 around-0.029
cy-0.029
 air-0.028
rated-0.028
et-0.027
Token around
Token ID1088
Feature activation+1.36e+01

Pos logit contributions
cy+0.047
|+0.047
rated+0.046
 air+0.043
et+0.042
Neg logit contributions
ves-0.072
vern-0.072
ades-0.069
 backup-0.067
 else-0.065
Token he
Token ID339
Feature activation-8.66e+00

Pos logit contributions
vern+0.121
ves+0.115
ades+0.107
keys+0.100
 backup+0.098
Neg logit contributions
 around-0.168
 air-0.159
cy-0.155
 down-0.150
rated-0.149
Token heard
Token ID2982
Feature activation-1.43e+00

Pos logit contributions
ves+0.495
vern+0.470
ades+0.439
keys+0.431
 backup+0.427
Neg logit contributions
 around-0.438
cy-0.424
 air-0.421
rated-0.418
et-0.398
Token a
Token ID257
Feature activation-4.03e+00

Pos logit contributions
vern+0.075
ves+0.072
ades+0.066
keys+0.065
 backup+0.062
Neg logit contributions
 around-0.085
 air-0.081
et-0.076
rated-0.074
 down-0.073
Token baby
Token ID5156
Feature activation-4.57e-01

Pos logit contributions
ves+0.235
vern+0.234
ades+0.210
 backup+0.203
keys+0.199
Neg logit contributions
 around-0.204
 air-0.201
rated-0.186
cy-0.182
 down-0.175
Tokenâ
Token ID22940
Feature activation+1.33e+00

Pos logit contributions
ves+0.026
vern+0.026
ades+0.024
 backup+0.023
keys+0.023
Neg logit contributions
 around-0.024
cy-0.023
 air-0.023
rated-0.022
et-0.021
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.049
 air+0.041
ained+0.040
 down+0.038
cy+0.038
Neg logit contributions
His-0.080
vern-0.080
ves-0.080
ggy-0.079
 mercy-0.076
Token
Token ID8151
Feature activation+1.05e+00

Pos logit contributions
 around+0.866
cy+0.827
 air+0.819
rated+0.803
et+0.783
Neg logit contributions
ves-0.828
vern-0.819
ades-0.746
 backup-0.730
 mercy-0.723
Tokens
Token ID82
Feature activation-6.23e+00

Pos logit contributions
 around+0.059
 air+0.058
rated+0.057
cy+0.057
et+0.055
Neg logit contributions
ves-0.054
vern-0.053
ades-0.048
keys-0.047
 backup-0.046
Token cry
Token ID3960
Feature activation+8.18e-01

Pos logit contributions
ves+0.366
vern+0.360
ades+0.331
 backup+0.322
keys+0.321
Neg logit contributions
 around-0.323
 air-0.302
cy-0.292
rated-0.289
et-0.282
Token.
Token ID13
Feature activation+7.34e-01

Pos logit contributions
 around+0.040
cy+0.040
 air+0.039
rated+0.038
|+0.037
Neg logit contributions
ves-0.047
vern-0.045
ades-0.042
 mercy-0.041
keys-0.041
Token
Token ID198
Feature activation-2.12e-01

Pos logit contributions
 around+0.034
rated+0.033
et+0.033
cy+0.032
 air+0.031
Neg logit contributions
ves-0.044
vern-0.043
 backup-0.040
His-0.040
ades-0.040
Token were
Token ID547
Feature activation-1.48e+00

Pos logit contributions
ves+0.736
vern+0.704
ades+0.657
keys+0.651
 backup+0.645
Neg logit contributions
 around-0.565
cy-0.559
 air-0.555
rated-0.544
et-0.524
Token also
Token ID635
Feature activation-6.57e-01

Pos logit contributions
ves+0.085
vern+0.084
ades+0.077
 backup+0.076
keys+0.075
Neg logit contributions
 around-0.074
cy-0.072
 air-0.071
rated-0.070
et-0.068
Token very
Token ID845
Feature activation+5.19e+00

Pos logit contributions
ves+0.038
vern+0.038
ades+0.035
 backup+0.034
keys+0.033
Neg logit contributions
 around-0.034
 air-0.032
cy-0.032
et-0.030
rated-0.030
Token persistent
Token ID16218
Feature activation+3.82e-01

Pos logit contributions
 around+0.272
cy+0.251
 air+0.249
rated+0.241
et+0.232
Neg logit contributions
ves-0.300
vern-0.296
ades-0.274
 backup-0.266
 mercy-0.264
Tokenâ
Token ID22940
Feature activation+1.53e+00

Pos logit contributions
 around+0.018
cy+0.017
 air+0.017
rated+0.017
et+0.016
Neg logit contributions
ves-0.024
vern-0.023
ades-0.021
 backup-0.021
keys-0.021
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.058
 air+0.052
 down+0.049
ening+0.045
cy+0.044
Neg logit contributions
vern-0.102
ves-0.102
keys-0.091
ggy-0.091
His-0.090
Token
Token ID447
Feature activation-5.47e+00

Pos logit contributions
 around+0.911
cy+0.871
 air+0.857
rated+0.839
et+0.821
Neg logit contributions
ves-0.773
vern-0.770
ades-0.696
 backup-0.688
 mercy-0.685
Token
Token ID251
Feature activation+5.26e+00

Pos logit contributions
ves+0.285
vern+0.281
ades+0.261
keys+0.252
 backup+0.247
Neg logit contributions
 around-0.314
rated-0.299
 air-0.291
et-0.287
cy-0.284
Tokenso
Token ID568
Feature activation+2.45e+00

Pos logit contributions
 around+0.256
cy+0.242
 air+0.241
rated+0.234
et+0.228
Neg logit contributions
ves-0.317
vern-0.313
ades-0.289
 backup-0.282
keys-0.280
Token they
Token ID484
Feature activation-9.02e+00

Pos logit contributions
 around+0.152
cy+0.140
rated+0.138
 air+0.134
et+0.133
Neg logit contributions
vern-0.116
ades-0.111
ves-0.111
 backup-0.107
 mercy-0.101
Token gathered
Token ID9272
Feature activation-1.65e+00

Pos logit contributions
ves+0.496
vern+0.488
ades+0.446
 backup+0.434
keys+0.432
Neg logit contributions
 around-0.485
cy-0.463
 air-0.461
rated-0.452
et-0.440
Token on
Token ID319
Feature activation+7.79e+00

Pos logit contributions
ves+0.076
vern+0.075
ades+0.070
 backup+0.069
keys+0.067
Neg logit contributions
 around-0.038
cy-0.037
rated-0.036
 air-0.036
et-0.034
Token Ab
Token ID2275
Feature activation+4.61e+00

Pos logit contributions
 around+0.425
 air+0.402
cy+0.401
rated+0.383
et+0.380
Neg logit contributions
ves-0.429
vern-0.423
ades-0.385
keys-0.379
 backup-0.372
Tokenig
Token ID328
Feature activation+1.29e+01

Pos logit contributions
 around+0.237
rated+0.230
 air+0.224
|+0.208
cy+0.205
Neg logit contributions
ves-0.254
vern-0.244
ades-0.240
 backup-0.229
keys-0.221
Tokenail
Token ID603
Feature activation+3.69e-01

Pos logit contributions
 around+0.754
 down+0.659
cy+0.636
et+0.629
 air+0.604
Neg logit contributions
vern-0.694
 mercy-0.668
 forgiveness-0.663
 backup-0.649
 charity-0.635
Tokenâ
Token ID22940
Feature activation+1.52e+00

Pos logit contributions
 around+0.017
cy+0.017
rated+0.017
 air+0.017
et+0.016
Neg logit contributions
ves-0.022
vern-0.021
ades-0.020
keys-0.019
 backup-0.019
Token
Token ID26391
Feature activation+1.56e+01

Pos logit contributions
 around+0.055
ening+0.045
cy+0.045
 air+0.044
rated+0.044
Neg logit contributions
vern-0.093
ves-0.092
His-0.088
ggy-0.085
 backup-0.083
Token
Token ID8151
Feature activation+1.04e+00

Pos logit contributions
 around+0.877
cy+0.839
 air+0.836
rated+0.822
et+0.801
Neg logit contributions
ves-0.824
vern-0.806
ades-0.737
 backup-0.714
keys-0.712
Tokens
Token ID82
Feature activation-6.01e+00

Pos logit contributions
 around+0.058
 air+0.056
cy+0.055
rated+0.055
et+0.053
Neg logit contributions
ves-0.055
vern-0.054
ades-0.049
 backup-0.048
keys-0.047
Token bike
Token ID7161
Feature activation-1.33e+00

Pos logit contributions
ves+0.346
vern+0.341
ades+0.316
keys+0.312
 backup+0.301
Neg logit contributions
 around-0.323
 air-0.298
cy-0.287
et-0.277
rated-0.276
Token.
Token ID13
Feature activation+7.71e-01

Pos logit contributions
ves+0.083
vern+0.082
ades+0.075
 backup+0.074
keys+0.074
Neg logit contributions
 around-0.063
cy-0.059
 air-0.059
rated-0.057
et-0.056
Token When
Token ID1649
Feature activation+6.16e+00

Pos logit contributions
rated+0.033
 around+0.033
et+0.032
 air+0.031
cy+0.031
Neg logit contributions
ves-0.049
vern-0.047
ades-0.045
 backup-0.045
His-0.043
Token know
Token ID760
Feature activation-1.31e+00

Pos logit contributions
vern+0.462
 mercy+0.435
ves+0.430
 backup+0.419
 forgiveness+0.402
Neg logit contributions
cy-0.474
 around-0.457
amp-0.455
 air-0.443
ening-0.442
Token the
Token ID262
Feature activation+4.03e+00

Pos logit contributions
vern+0.064
ves+0.062
ades+0.057
 backup+0.055
keys+0.053
Neg logit contributions
 around-0.083
 air-0.077
cy-0.073
et-0.073
ening-0.071
Token box
Token ID3091
Feature activation-2.10e-01

Pos logit contributions
 around+0.244
 air+0.237
cy+0.229
rated+0.224
et+0.219
Neg logit contributions
ves-0.201
vern-0.193
ades-0.177
keys-0.176
 backup-0.169
Token was
Token ID373
Feature activation-1.54e+00

Pos logit contributions
ves+0.013
vern+0.013
ades+0.012
 backup+0.012
keys+0.012
Neg logit contributions
 around-0.010
cy-0.009
 air-0.009
rated-0.009
et-0.008
Token for
Token ID329
Feature activation+1.18e+00

Pos logit contributions
ves+0.083
vern+0.082
ades+0.076
keys+0.073
 backup+0.073
Neg logit contributions
 around-0.086
 air-0.081
cy-0.081
rated-0.079
et-0.078
Token charity
Token ID11016
Feature activation-1.74e+01

Pos logit contributions
 around+0.061
 air+0.059
cy+0.053
et+0.053
 down+0.052
Neg logit contributions
vern-0.068
ves-0.067
ades-0.062
keys-0.060
 mercy-0.059
Token.
Token ID13
Feature activation+5.53e-02

Pos logit contributions
ves+1.037
vern+1.017
ades+0.935
 backup+0.920
keys+0.916
Neg logit contributions
 around-0.832
cy-0.811
rated-0.805
 air-0.797
et-0.762
Token They
Token ID1119
Feature activation+1.50e+00

Pos logit contributions
rated+0.002
et+0.002
 around+0.002
cy+0.002
ening+0.002
Neg logit contributions
ves-0.004
vern-0.003
 backup-0.003
ades-0.003
 forgiveness-0.003
Token thought
Token ID1807
Feature activation+1.82e+00

Pos logit contributions
 around+0.067
cy+0.063
 air+0.063
rated+0.060
et+0.059
Neg logit contributions
ves-0.098
vern-0.097
ades-0.090
 backup-0.088
keys-0.087
Token it
Token ID340
Feature activation+4.00e+00

Pos logit contributions
 around+0.102
 air+0.094
et+0.087
cy+0.086
rated+0.085
Neg logit contributions
vern-0.099
ves-0.095
ades-0.091
keys-0.088
 mercy-0.087
Token was
Token ID373
Feature activation-1.58e+00

Pos logit contributions
 air+0.213
 around+0.210
rated+0.210
cy+0.209
|+0.199
Neg logit contributions
ves-0.213
vern-0.193
ades-0.181
keys-0.174
 mercy-0.173
Token.
Token ID13
Feature activation+1.24e-01

Pos logit contributions
ves+0.009
vern+0.009
ades+0.008
 backup+0.008
keys+0.008
Neg logit contributions
 around-0.008
cy-0.007
 air-0.007
rated-0.007
et-0.007
Token It
Token ID632
Feature activation+9.37e+00

Pos logit contributions
 around+0.006
rated+0.005
cy+0.005
et+0.005
 air+0.005
Neg logit contributions
ves-0.008
vern-0.008
 backup-0.007
keys-0.007
 mercy-0.007
Token belongs
Token ID14448
Feature activation+1.02e-03

Pos logit contributions
 around+0.422
cy+0.404
 air+0.398
rated+0.395
et+0.381
Neg logit contributions
ves-0.592
vern-0.569
keys-0.529
ades-0.527
 mercy-0.513
Token to
Token ID284
Feature activation-2.91e+00

Pos logit contributions
 around+0.000
cy+0.000
 air+0.000
rated+0.000
et+0.000
Neg logit contributions
ves-0.000
vern-0.000
ades-0.000
keys-0.000
 backup-0.000
Token the
Token ID262
Feature activation+4.14e+00

Pos logit contributions
vern+0.170
ves+0.168
ades+0.157
 backup+0.147
keys+0.146
Neg logit contributions
 around-0.150
 air-0.143
cy-0.135
et-0.132
rated-0.130
Token charity
Token ID11016
Feature activation-1.73e+01

Pos logit contributions
 around+0.210
cy+0.200
 air+0.198
rated+0.195
et+0.190
Neg logit contributions
ves-0.241
vern-0.237
ades-0.218
 backup-0.213
keys-0.212
Token.
Token ID13
Feature activation+1.30e-01

Pos logit contributions
ves+0.912
vern+0.888
ades+0.817
keys+0.805
 backup+0.789
Neg logit contributions
 around-0.940
cy-0.923
rated-0.923
 air-0.902
et-0.881
Token We
Token ID775
Feature activation-9.14e-01

Pos logit contributions
 around+0.005
rated+0.005
cy+0.005
et+0.005
 air+0.005
Neg logit contributions
ves-0.009
vern-0.009
 backup-0.008
keys-0.008
ades-0.008
Token provide
Token ID2148
Feature activation-6.81e+00

Pos logit contributions
ves+0.053
vern+0.052
keys+0.048
 backup+0.047
ades+0.047
Neg logit contributions
rated-0.042
 air-0.042
 around-0.041
ening-0.041
et-0.040
Token clothes
Token ID8242
Feature activation-7.00e+00

Pos logit contributions
vern+0.412
ves+0.408
ades+0.384
keys+0.365
 backup+0.350
Neg logit contributions
 around-0.353
 air-0.328
cy-0.303
et-0.293
 down-0.293
Token and
Token ID290
Feature activation+1.41e+00

Pos logit contributions
ves+0.469
vern+0.464
ades+0.429
 backup+0.427
 mercy+0.423
Neg logit contributions
 around-0.320
cy-0.279
 air-0.275
 down-0.257
et-0.257
Token to
Token ID284
Feature activation-2.90e+00

Pos logit contributions
 around+0.109
 air+0.101
cy+0.100
et+0.096
 down+0.095
Neg logit contributions
ves-0.084
vern-0.083
keys-0.074
ades-0.073
 mercy-0.070
Token take
Token ID1011
Feature activation-3.56e+00

Pos logit contributions
ves+0.188
vern+0.179
ades+0.177
keys+0.172
sters+0.160
Neg logit contributions
 around-0.130
 air-0.128
|-0.118
cy-0.117
 night-0.113
Token them
Token ID606
Feature activation-4.42e+00

Pos logit contributions
ves+0.174
vern+0.168
 backup+0.154
ades+0.154
 mercy+0.147
Neg logit contributions
 around-0.208
rated-0.205
cy-0.204
 air-0.199
et-0.194
Token to
Token ID284
Feature activation-2.91e+00

Pos logit contributions
ves+0.284
vern+0.275
ades+0.258
keys+0.255
 mercy+0.248
Neg logit contributions
 around-0.213
cy-0.192
 air-0.190
et-0.180
rated-0.180
Token the
Token ID262
Feature activation+4.20e+00

Pos logit contributions
ves+0.199
vern+0.192
ades+0.188
keys+0.187
sters+0.173
Neg logit contributions
 around-0.121
 air-0.116
cy-0.106
|-0.104
 night-0.103
Token charity
Token ID11016
Feature activation-1.73e+01

Pos logit contributions
 around+0.202
 air+0.199
cy+0.189
 night+0.175
et+0.175
Neg logit contributions
ves-0.271
vern-0.257
keys-0.244
ades-0.242
 mercy-0.217
Token shop
Token ID6128
Feature activation-4.52e+00

Pos logit contributions
ves+0.864
vern+0.842
ades+0.776
 backup+0.773
keys+0.746
Neg logit contributions
rated-0.973
 around-0.965
cy-0.945
 air-0.927
et-0.899
Token,
Token ID11
Feature activation-1.19e+00

Pos logit contributions
ves+0.291
vern+0.287
ades+0.265
keys+0.258
 backup+0.256
Neg logit contributions
 around-0.208
cy-0.196
 air-0.192
rated-0.184
et-0.181
Token where
Token ID810
Feature activation-5.85e+00

Pos logit contributions
ves+0.079
vern+0.079
ades+0.074
keys+0.072
 mercy+0.069
Neg logit contributions
 around-0.054
 air-0.050
cy-0.048
et-0.047
rated-0.045
Token other
Token ID584
Feature activation-6.83e-01

Pos logit contributions
vern+0.224
ves+0.219
ades+0.194
 backup+0.183
keys+0.181
Neg logit contributions
 around-0.423
 air-0.400
cy-0.398
rated-0.387
et-0.379
Token children
Token ID1751
Feature activation+7.95e-01

Pos logit contributions
vern+0.043
ves+0.042
ades+0.038
keys+0.037
 backup+0.037
Neg logit contributions
 around-0.034
 air-0.032
cy-0.031
et-0.028
rated-0.028
Token.
Token ID13
Feature activation+2.69e-01

Pos logit contributions
ves+0.350
vern+0.344
ades+0.317
 backup+0.311
keys+0.309
Neg logit contributions
 around-0.265
cy-0.257
 air-0.253
rated-0.250
et-0.241
Token They
Token ID1119
Feature activation+1.67e+00

Pos logit contributions
 around+0.011
cy+0.010
 air+0.010
rated+0.010
et+0.010
Neg logit contributions
ves-0.018
vern-0.018
ades-0.017
 backup-0.016
keys-0.016
Token belong
Token ID5594
Feature activation-1.76e+00

Pos logit contributions
 around+0.069
cy+0.065
 air+0.065
rated+0.063
et+0.060
Neg logit contributions
ves-0.113
vern-0.112
ades-0.104
 backup-0.102
keys-0.101
Token to
Token ID284
Feature activation-2.83e+00

Pos logit contributions
ves+0.102
vern+0.098
ades+0.091
keys+0.088
 backup+0.086
Neg logit contributions
 around-0.098
cy-0.091
 air-0.088
 down-0.084
et-0.083
Token a
Token ID257
Feature activation-4.47e+00

Pos logit contributions
ves+0.166
vern+0.165
ades+0.151
 backup+0.147
keys+0.146
Neg logit contributions
 around-0.142
 air-0.135
cy-0.135
rated-0.130
et-0.128
Token charity
Token ID11016
Feature activation-1.73e+01

Pos logit contributions
ves+0.249
vern+0.242
ades+0.225
keys+0.216
 mercy+0.215
Neg logit contributions
 around-0.243
 air-0.232
cy-0.230
rated-0.216
|-0.210
Token that
Token ID326
Feature activation-3.41e+00

Pos logit contributions
ves+0.925
vern+0.906
ades+0.832
 backup+0.819
keys+0.811
Neg logit contributions
 around-0.914
rated-0.906
cy-0.897
 air-0.874
et-0.849
Token helps
Token ID5419
Feature activation-4.39e+00

Pos logit contributions
ves+0.208
vern+0.202
ades+0.186
 backup+0.184
keys+0.184
Neg logit contributions
 around-0.158
cy-0.153
rated-0.151
 air-0.150
et-0.145
Token poor
Token ID3595
Feature activation-1.53e+00

Pos logit contributions
vern+0.261
ves+0.260
ades+0.240
keys+0.231
 backup+0.230
Neg logit contributions
 around-0.222
 air-0.207
cy-0.201
rated-0.197
et-0.194
Token kids
Token ID3988
Feature activation+9.02e-01

Pos logit contributions
vern+0.092
ves+0.091
ades+0.084
 backup+0.082
keys+0.080
Neg logit contributions
 around-0.075
 air-0.074
cy-0.069
rated-0.067
et-0.065
Token.
Token ID13
Feature activation+3.33e-01

Pos logit contributions
 around+0.043
cy+0.040
 air+0.040
rated+0.039
et+0.038
Neg logit contributions
ves-0.056
vern-0.055
ades-0.051
 backup-0.050
 mercy-0.049
Token all
Token ID477
Feature activation+1.91e+00

Pos logit contributions
ves+0.414
vern+0.408
ades+0.377
keys+0.369
 backup+0.350
Neg logit contributions
 around-0.404
 air-0.381
cy-0.362
et-0.353
 down-0.342
Token your
Token ID534
Feature activation-2.41e+00

Pos logit contributions
 around+0.098
 air+0.093
cy+0.087
et+0.084
 down+0.081
Neg logit contributions
ves-0.116
vern-0.114
ades-0.106
keys-0.104
 backup-0.100
Token toys
Token ID14958
Feature activation-6.36e+00

Pos logit contributions
ves+0.121
vern+0.115
ades+0.106
keys+0.104
 mercy+0.097
Neg logit contributions
 around-0.148
 air-0.144
cy-0.138
et-0.132
 down-0.127
Token to
Token ID284
Feature activation-2.96e+00

Pos logit contributions
ves+0.414
vern+0.402
ades+0.380
keys+0.368
 mercy+0.367
Neg logit contributions
 around-0.303
cy-0.267
 air-0.267
et-0.252
 down-0.247
Token a
Token ID257
Feature activation-4.40e+00

Pos logit contributions
ves+0.177
vern+0.175
ades+0.165
keys+0.157
 mercy+0.151
Neg logit contributions
 around-0.147
 air-0.138
cy-0.131
et-0.126
|-0.125
Token charity
Token ID11016
Feature activation-1.72e+01

Pos logit contributions
ves+0.248
vern+0.236
ades+0.219
keys+0.213
 mercy+0.205
Neg logit contributions
 around-0.242
 air-0.228
cy-0.224
 night-0.211
 down-0.208
Token that
Token ID326
Feature activation-3.45e+00

Pos logit contributions
ves+0.997
vern+0.978
ades+0.903
 backup+0.888
keys+0.886
Neg logit contributions
 around-0.815
rated-0.814
cy-0.808
 air-0.786
et-0.753
Token helps
Token ID5419
Feature activation-4.31e+00

Pos logit contributions
ves+0.220
vern+0.214
ades+0.198
 backup+0.195
keys+0.195
Neg logit contributions
 around-0.150
cy-0.144
rated-0.144
 air-0.142
et-0.137
Token children
Token ID1751
Feature activation+1.01e+00

Pos logit contributions
vern+0.257
ves+0.256
ades+0.236
keys+0.227
 backup+0.227
Neg logit contributions
 around-0.218
 air-0.202
cy-0.195
rated-0.191
et-0.189
Token in
Token ID287
Feature activation+6.15e+00

Pos logit contributions
 around+0.048
cy+0.044
 air+0.043
rated+0.041
et+0.041
Neg logit contributions
ves-0.064
vern-0.063
ades-0.059
 mercy-0.057
 backup-0.057
Token need
Token ID761
Feature activation+9.04e-01

Pos logit contributions
 around+0.286
 air+0.269
cy+0.264
rated+0.251
et+0.246
Neg logit contributions
ves-0.392
vern-0.381
ades-0.358
keys-0.352
 backup-0.342
Token"
Token ID1
Feature activation-1.22e+01

Pos logit contributions
cy+0.297
et+0.283
 around+0.281
 air+0.279
rated+0.277
Neg logit contributions
ves-0.261
vern-0.255
keys-0.223
 mercy-0.220
ades-0.219
TokenLet
Token ID5756
Feature activation+2.28e+00

Pos logit contributions
vern+0.756
ves+0.719
ades+0.690
 backup+0.675
 mercy+0.650
Neg logit contributions
cy-0.590
 around-0.583
 air-0.562
|-0.533
ny-0.512
Token's
Token ID338
Feature activation-3.08e+00

Pos logit contributions
 around+0.101
cy+0.095
 air+0.095
rated+0.091
et+0.090
Neg logit contributions
ves-0.149
vern-0.148
ades-0.137
 backup-0.134
keys-0.133
Token go
Token ID467
Feature activation-1.23e+00

Pos logit contributions
vern+0.195
ves+0.193
ades+0.177
 backup+0.171
keys+0.168
Neg logit contributions
 around-0.150
cy-0.137
 air-0.137
rated-0.128
 down-0.126
Token,
Token ID11
Feature activation-1.20e+00

Pos logit contributions
ves+0.076
vern+0.075
ades+0.069
keys+0.068
 backup+0.067
Neg logit contributions
 around-0.060
cy-0.057
 air-0.056
rated-0.054
et-0.053
Token mate
Token ID16133
Feature activation-1.71e+01

Pos logit contributions
vern+0.074
ves+0.073
ades+0.068
 backup+0.064
keys+0.064
Neg logit contributions
 around-0.060
 air-0.056
cy-0.055
 down-0.052
rated-0.051
Tokeny
Token ID88
Feature activation+4.82e+00

Pos logit contributions
ves+1.182
vern+1.157
ades+1.098
keys+1.059
 backup+1.052
Neg logit contributions
 around-0.645
 air-0.626
cy-0.602
rated-0.590
et-0.572
Token!"
Token ID2474
Feature activation+1.17e+00

Pos logit contributions
 around+0.228
 air+0.214
cy+0.214
rated+0.207
et+0.201
Neg logit contributions
ves-0.299
vern-0.297
ades-0.274
 backup-0.267
keys-0.265
Token Ben
Token ID3932
Feature activation+3.28e+00

Pos logit contributions
 around+0.069
 air+0.064
cy+0.063
 down+0.059
|+0.057
Neg logit contributions
vern-0.065
ves-0.061
ades-0.057
 backup-0.054
 mercy-0.054
Token said
Token ID531
Feature activation-1.50e+00

Pos logit contributions
 around+0.161
 air+0.150
cy+0.148
rated+0.142
et+0.140
Neg logit contributions
ves-0.201
vern-0.200
ades-0.184
 backup-0.181
keys-0.179
Token.
Token ID13
Feature activation+2.57e-01

Pos logit contributions
ves+0.105
vern+0.104
ades+0.100
keys+0.098
 backup+0.097
Neg logit contributions
 around-0.065
 down-0.053
cy-0.051
 air-0.050
rated-0.049
Token!
Token ID0
Feature activation+1.57e-01

Pos logit contributions
ves+0.015
vern+0.015
ades+0.014
 backup+0.014
keys+0.014
Neg logit contributions
 around-0.010
 air-0.009
cy-0.009
rated-0.009
et-0.009
Token They
Token ID1119
Feature activation+1.75e+00

Pos logit contributions
 around+0.006
rated+0.006
et+0.005
 air+0.005
cy+0.005
Neg logit contributions
ves-0.011
vern-0.011
 backup-0.010
ades-0.010
keys-0.010
Token are
Token ID389
Feature activation-9.13e-01

Pos logit contributions
 around+0.076
rated+0.073
cy+0.073
 air+0.070
et+0.069
Neg logit contributions
ves-0.111
vern-0.110
ades-0.101
 backup-0.100
keys-0.100
Token for
Token ID329
Feature activation+1.34e+00

Pos logit contributions
ves+0.048
vern+0.047
ades+0.043
 backup+0.042
keys+0.042
Neg logit contributions
 around-0.051
cy-0.049
 air-0.048
rated-0.048
et-0.047
Token the
Token ID262
Feature activation+4.29e+00

Pos logit contributions
 around+0.066
 air+0.063
 down+0.055
 night+0.055
cy+0.055
Neg logit contributions
ves-0.082
vern-0.082
ades-0.075
keys-0.072
His-0.071
Token charity
Token ID11016
Feature activation-1.71e+01

Pos logit contributions
 around+0.246
cy+0.235
 air+0.234
rated+0.230
et+0.224
Neg logit contributions
ves-0.222
vern-0.218
ades-0.198
 backup-0.192
keys-0.191
Token!
Token ID0
Feature activation+1.44e-01

Pos logit contributions
ves+0.977
vern+0.960
ades+0.881
 backup+0.871
keys+0.865
Neg logit contributions
rated-0.836
 around-0.830
cy-0.814
 air-0.791
|-0.773
Token I
Token ID314
Feature activation-1.72e+00

Pos logit contributions
 around+0.006
rated+0.005
et+0.005
cy+0.005
 air+0.005
Neg logit contributions
ves-0.010
vern-0.010
 backup-0.009
ades-0.009
keys-0.009
Token was
Token ID373
Feature activation-1.45e+00

Pos logit contributions
ves+0.108
vern+0.106
ades+0.097
 backup+0.097
 mercy+0.095
Neg logit contributions
 around-0.076
 air-0.074
rated-0.072
cy-0.071
et-0.070
Token going
Token ID1016
Feature activation+1.72e+00

Pos logit contributions
ves+0.084
vern+0.082
ades+0.076
 backup+0.074
keys+0.074
Neg logit contributions
 around-0.074
cy-0.071
 air-0.070
rated-0.069
et-0.067
Token to
Token ID284
Feature activation-2.85e+00

Pos logit contributions
 around+0.111
cy+0.106
 air+0.106
rated+0.103
et+0.101
Neg logit contributions
ves-0.077
vern-0.076
ades-0.068
keys-0.066
 backup-0.065
Token She
Token ID1375
Feature activation+5.13e+00

Pos logit contributions
rated+0.010
cy+0.009
et+0.009
 around+0.009
ening+0.009
Neg logit contributions
ves-0.015
vern-0.014
 backup-0.014
ades-0.013
His-0.013
Token drove
Token ID10357
Feature activation-3.96e+00

Pos logit contributions
 around+0.218
cy+0.198
 air+0.196
et+0.191
 down+0.160
Neg logit contributions
vern-0.372
ves-0.333
ades-0.324
 backup-0.322
keys-0.319
Token away
Token ID1497
Feature activation+5.83e+00

Pos logit contributions
ves+0.204
vern+0.187
 backup+0.183
ades+0.173
 mercy+0.169
Neg logit contributions
rated-0.218
cy-0.217
|-0.206
 air-0.205
et-0.199
Token to
Token ID284
Feature activation-2.86e+00

Pos logit contributions
 around+0.275
cy+0.260
 air+0.259
rated+0.253
et+0.245
Neg logit contributions
ves-0.363
vern-0.357
ades-0.331
 backup-0.322
keys-0.322
Token the
Token ID262
Feature activation+4.23e+00

Pos logit contributions
ves+0.171
vern+0.169
ades+0.155
 backup+0.153
keys+0.150
Neg logit contributions
 around-0.140
cy-0.134
 air-0.133
rated-0.131
et-0.127
Token charity
Token ID11016
Feature activation-1.71e+01

Pos logit contributions
 around+0.203
cy+0.192
 air+0.191
rated+0.187
et+0.181
Neg logit contributions
ves-0.260
vern-0.256
ades-0.236
 backup-0.230
keys-0.230
Token shop
Token ID6128
Feature activation-4.35e+00

Pos logit contributions
ves+0.881
vern+0.858
 backup+0.795
ades+0.793
keys+0.748
Neg logit contributions
rated-0.945
 around-0.900
cy-0.898
|-0.863
 air-0.862
Token.
Token ID13
Feature activation+1.88e-01

Pos logit contributions
ves+0.281
vern+0.277
ades+0.257
 backup+0.250
keys+0.250
Neg logit contributions
 around-0.195
cy-0.183
 air-0.182
rated-0.176
et-0.172
Token
Token ID198
Feature activation-9.37e-01

Pos logit contributions
rated+0.010
et+0.010
 around+0.009
cy+0.009
ening+0.009
Neg logit contributions
ves-0.010
vern-0.010
 backup-0.009
His-0.009
ades-0.009
Token
Token ID198
Feature activation-9.46e-01

Pos logit contributions
vern+0.057
ves+0.057
ades+0.053
keys+0.053
 mercy+0.052
Neg logit contributions
 around-0.045
 air-0.041
cy-0.041
rated-0.038
|-0.038
TokenL
Token ID43
Feature activation-4.24e+00

Pos logit contributions
vern+0.048
 mercy+0.046
ves+0.045
keys+0.044
 forgiveness+0.044
Neg logit contributions
 around-0.054
 air-0.050
cy-0.050
amp-0.049
|-0.049
Token
Token ID198
Feature activation-9.62e-01

Pos logit contributions
vern+0.061
ves+0.060
 mercy+0.057
keys+0.057
 backup+0.057
Neg logit contributions
 around-0.043
 air-0.039
cy-0.038
|-0.036
rated-0.035
Token"
Token ID1
Feature activation-9.74e+00

Pos logit contributions
vern+0.050
 forgiveness+0.049
 mercy+0.049
 instincts+0.044
 backup+0.043
Neg logit contributions
 around-0.058
 air-0.052
cy-0.051
ny-0.049
|-0.048
TokenAr
Token ID3163
Feature activation-1.06e+01

Pos logit contributions
vern+0.805
ves+0.786
ades+0.730
 backup+0.728
 mercy+0.726
Neg logit contributions
cy-0.269
 air-0.261
 around-0.248
|-0.222
rated-0.219
Tokenrr
Token ID21062
Feature activation-2.10e+00

Pos logit contributions
ves+0.633
vern+0.611
 forgiveness+0.565
ades+0.561
 mercy+0.558
Neg logit contributions
 around-0.464
cy-0.453
et-0.437
|-0.426
 air-0.417
Token,
Token ID11
Feature activation-1.31e+00

Pos logit contributions
ves+0.131
vern+0.130
ades+0.119
 backup+0.118
 mercy+0.118
Neg logit contributions
 around-0.096
cy-0.091
 air-0.090
rated-0.088
et-0.087
Token mate
Token ID16133
Feature activation-1.68e+01

Pos logit contributions
vern+0.060
ves+0.059
ades+0.055
keys+0.046
His+0.045
Neg logit contributions
 around-0.089
 air-0.085
cy-0.078
 down-0.077
 night-0.077
Tokeny
Token ID88
Feature activation+4.56e+00

Pos logit contributions
ves+1.196
vern+1.162
ades+1.117
keys+1.075
 mercy+1.065
Neg logit contributions
 around-0.608
 air-0.576
rated-0.541
cy-0.539
et-0.518
Token,
Token ID11
Feature activation-1.30e+00

Pos logit contributions
 around+0.211
 air+0.200
cy+0.200
rated+0.193
et+0.188
Neg logit contributions
ves-0.286
vern-0.285
ades-0.262
 backup-0.257
keys-0.254
Token let
Token ID1309
Feature activation-1.10e+00

Pos logit contributions
vern+0.055
ves+0.055
ades+0.049
keys+0.043
 mercy+0.041
Neg logit contributions
 around-0.091
 air-0.087
cy-0.081
 down-0.080
et-0.080
Token's
Token ID338
Feature activation-2.71e+00

Pos logit contributions
ves+0.068
vern+0.066
ades+0.061
 backup+0.060
keys+0.060
Neg logit contributions
 around-0.052
cy-0.050
 air-0.049
rated-0.048
et-0.046
Token sail
Token ID14936
Feature activation-6.58e+00

Pos logit contributions
ves+0.160
vern+0.158
ades+0.145
 backup+0.141
keys+0.140
Neg logit contributions
 around-0.137
cy-0.130
 air-0.129
rated-0.126
et-0.123
Token You
Token ID921
Feature activation+7.75e+00

Pos logit contributions
 around+0.001
rated+0.001
cy+0.001
et+0.001
 air+0.001
Neg logit contributions
ves-0.002
vern-0.001
 backup-0.001
 mercy-0.001
 forgiveness-0.001
Token can
Token ID460
Feature activation+4.57e+00

Pos logit contributions
 around+0.328
rated+0.317
cy+0.315
 air+0.307
et+0.303
Neg logit contributions
ves-0.503
vern-0.501
 backup-0.465
ades-0.461
keys-0.457
Token be
Token ID307
Feature activation-4.03e+00

Pos logit contributions
 around+0.205
cy+0.194
 air+0.188
et+0.180
rated+0.177
Neg logit contributions
ves-0.299
vern-0.294
ades-0.272
keys-0.268
 backup-0.264
Token the
Token ID262
Feature activation+3.89e+00

Pos logit contributions
vern+0.166
ves+0.165
 backup+0.146
ades+0.145
 mercy+0.139
Neg logit contributions
rated-0.263
cy-0.262
 around-0.262
 air-0.252
|-0.246
Token first
Token ID717
Feature activation+2.90e+00

Pos logit contributions
 around+0.252
 air+0.248
cy+0.241
et+0.235
rated+0.229
Neg logit contributions
ves-0.182
vern-0.166
ades-0.151
keys-0.147
 mercy-0.137
Token mate
Token ID16133
Feature activation-1.68e+01

Pos logit contributions
 around+0.174
 air+0.165
cy+0.163
rated+0.160
et+0.158
Neg logit contributions
vern-0.147
ves-0.144
ades-0.131
keys-0.127
 backup-0.125
Token today
Token ID1909
Feature activation+6.18e-01

Pos logit contributions
ves+0.967
vern+0.944
ades+0.887
keys+0.865
 backup+0.848
Neg logit contributions
 air-0.787
 around-0.778
rated-0.775
cy-0.745
ening-0.726
Token."
Token ID526
Feature activation+2.84e+00

Pos logit contributions
rated+0.031
cy+0.031
 around+0.031
 air+0.030
ening+0.030
Neg logit contributions
ves-0.034
vern-0.032
ades-0.030
keys-0.030
 backup-0.029
Token
Token ID198
Feature activation-1.03e+00

Pos logit contributions
 around+0.127
 air+0.121
cy+0.121
rated+0.109
|+0.107
Neg logit contributions
ves-0.186
vern-0.184
ades-0.169
keys-0.169
 backup-0.165
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
vern+0.067
ves+0.067
keys+0.064
 backup+0.063
 mercy+0.062
Neg logit contributions
 around-0.045
 air-0.041
cy-0.040
|-0.037
 down-0.036
TokenThey
Token ID2990
Feature activation-1.07e+01

Pos logit contributions
vern+0.052
 backup+0.049
 mercy+0.048
ves+0.047
keys+0.047
Neg logit contributions
cy-0.056
 around-0.054
 air-0.053
ny-0.051
he-0.048
Token It
Token ID632
Feature activation+9.20e+00

Pos logit contributions
 around+0.009
rated+0.008
cy+0.008
et+0.008
 air+0.008
Neg logit contributions
ves-0.018
vern-0.018
 backup-0.017
keys-0.017
 forgiveness-0.017
Token needs
Token ID2476
Feature activation+3.44e-01

Pos logit contributions
 around+0.363
rated+0.359
cy+0.350
 air+0.340
et+0.329
Neg logit contributions
ves-0.620
vern-0.596
keys-0.558
ades-0.549
 backup-0.547
Token to
Token ID284
Feature activation-3.11e+00

Pos logit contributions
 air+0.019
 around+0.019
 night+0.016
 down+0.015
 through+0.015
Neg logit contributions
ves-0.020
ades-0.019
vern-0.019
keys-0.019
sters-0.017
Token find
Token ID1064
Feature activation-1.74e+00

Pos logit contributions
vern+0.192
ves+0.192
ades+0.187
keys+0.176
 backup+0.166
Neg logit contributions
 around-0.143
 air-0.143
cy-0.127
et-0.127
|-0.126
Token a
Token ID257
Feature activation-4.72e+00

Pos logit contributions
vern+0.081
ves+0.081
ades+0.075
keys+0.072
 backup+0.066
Neg logit contributions
 around-0.114
 air-0.112
et-0.101
 down-0.100
cy-0.100
Token mate
Token ID16133
Feature activation-1.68e+01

Pos logit contributions
ves+0.305
vern+0.295
ades+0.284
keys+0.274
 mercy+0.265
Neg logit contributions
 around-0.210
 air-0.206
cy-0.197
 night-0.189
 down-0.181
Token and
Token ID290
Feature activation+1.33e+00

Pos logit contributions
ves+1.019
vern+0.998
ades+0.928
keys+0.902
 backup+0.896
Neg logit contributions
 around-0.777
 air-0.757
cy-0.747
rated-0.734
et-0.709
Token lay
Token ID3830
Feature activation+1.30e+00

Pos logit contributions
 around+0.073
 air+0.071
 down+0.064
cy+0.060
 night+0.060
Neg logit contributions
vern-0.079
ves-0.078
ades-0.076
keys-0.067
 backup-0.063
Token eggs
Token ID9653
Feature activation-5.29e+00

Pos logit contributions
rated+0.058
|+0.057
cy+0.057
 air+0.054
amp+0.054
Neg logit contributions
ves-0.078
vern-0.073
ades-0.070
 mercy-0.068
 backup-0.067
Token.
Token ID13
Feature activation+2.64e-01

Pos logit contributions
ves+0.330
vern+0.324
ades+0.299
keys+0.294
 backup+0.291
Neg logit contributions
 around-0.232
cy-0.230
 air-0.226
rated-0.226
et-0.214
Token Then
Token ID3244
Feature activation+4.19e+00

Pos logit contributions
 around+0.011
cy+0.010
rated+0.010
et+0.010
 air+0.010
Neg logit contributions
ves-0.018
vern-0.018
 backup-0.016
ades-0.016
keys-0.016
Token,
Token ID11
Feature activation-1.29e+00

Pos logit contributions
vern+0.106
ves+0.104
keys+0.102
ades+0.099
 mercy+0.097
Neg logit contributions
 around-0.052
 down-0.044
 air-0.039
 through-0.035
et-0.034
Token "
Token ID366
Feature activation-4.16e+00

Pos logit contributions
vern+0.078
ves+0.075
ades+0.070
 mercy+0.070
keys+0.068
Neg logit contributions
 around-0.067
 air-0.061
 down-0.058
cy-0.056
et-0.056
TokenAh
Token ID10910
Feature activation-3.07e+00

Pos logit contributions
ves+0.243
vern+0.237
ades+0.218
 backup+0.214
keys+0.212
Neg logit contributions
 around-0.213
cy-0.199
 air-0.198
rated-0.197
et-0.191
Tokenoy
Token ID726
Feature activation-6.44e+00

Pos logit contributions
vern+0.199
ves+0.196
ades+0.191
keys+0.182
 mercy+0.177
Neg logit contributions
 around-0.123
et-0.123
 air-0.122
cy-0.117
rated-0.106
Token,
Token ID11
Feature activation-1.28e+00

Pos logit contributions
ves+0.413
vern+0.409
ades+0.373
 mercy+0.361
keys+0.361
Neg logit contributions
 around-0.295
cy-0.283
 air-0.274
et-0.264
rated-0.255
Token mate
Token ID16133
Feature activation-1.68e+01

Pos logit contributions
vern+0.059
ves+0.058
ades+0.054
keys+0.048
 mercy+0.044
Neg logit contributions
 around-0.085
 air-0.082
et-0.078
cy-0.077
 down-0.075
Tokeny
Token ID88
Feature activation+4.56e+00

Pos logit contributions
ves+1.131
vern+1.102
ades+1.063
 backup+1.009
 mercy+1.005
Neg logit contributions
 around-0.644
 air-0.611
rated-0.597
cy-0.568
|-0.553
Token.
Token ID13
Feature activation+1.54e-01

Pos logit contributions
 around+0.214
cy+0.203
 air+0.203
rated+0.197
et+0.192
Neg logit contributions
ves-0.283
vern-0.280
ades-0.258
 backup-0.252
keys-0.251
Token I
Token ID314
Feature activation-1.88e+00

Pos logit contributions
 around+0.007
cy+0.007
 air+0.007
rated+0.006
et+0.006
Neg logit contributions
ves-0.010
vern-0.010
ades-0.009
 backup-0.009
keys-0.009
Token'm
Token ID1101
Feature activation-1.79e+00

Pos logit contributions
ves+0.121
vern+0.119
ades+0.110
 backup+0.109
keys+0.107
Neg logit contributions
 around-0.082
 air-0.078
cy-0.077
rated-0.077
et-0.074
Token Captain
Token ID8599
Feature activation-6.13e+00

Pos logit contributions
ves+0.092
vern+0.091
 backup+0.083
ades+0.081
keys+0.079
Neg logit contributions
cy-0.101
rated-0.099
 around-0.098
 air-0.095
et-0.092
Token
Token ID198
Feature activation-1.37e+00

Pos logit contributions
ves+0.091
vern+0.089
ades+0.082
keys+0.080
 backup+0.080
Neg logit contributions
 around-0.082
cy-0.078
 air-0.078
rated-0.075
et-0.074
Token"
Token ID1
Feature activation-1.01e+01

Pos logit contributions
ves+0.059
vern+0.057
 mercy+0.054
ades+0.052
keys+0.051
Neg logit contributions
 around-0.087
cy-0.085
|-0.083
 air-0.082
amp-0.079
TokenAr
Token ID3163
Feature activation-1.07e+01

Pos logit contributions
vern+0.687
ves+0.678
ades+0.632
 backup+0.612
 mercy+0.607
Neg logit contributions
cy-0.428
 around-0.419
 air-0.412
et-0.383
rated-0.379
Tokenrr
Token ID21062
Feature activation-2.15e+00

Pos logit contributions
ves+0.628
vern+0.598
ades+0.558
keys+0.534
 forgiveness+0.532
Neg logit contributions
 around-0.527
et-0.489
cy-0.487
 air-0.486
rated-0.471
Token,
Token ID11
Feature activation-1.47e+00

Pos logit contributions
ves+0.133
vern+0.130
ades+0.120
 backup+0.118
keys+0.117
Neg logit contributions
 around-0.102
cy-0.096
 air-0.096
rated-0.093
et-0.092
Token mate
Token ID16133
Feature activation-1.68e+01

Pos logit contributions
ves+0.088
vern+0.088
ades+0.081
keys+0.073
 mercy+0.070
Neg logit contributions
 around-0.078
 air-0.073
cy-0.070
 down-0.067
et-0.065
Tokeny
Token ID88
Feature activation+4.68e+00

Pos logit contributions
ves+1.043
vern+1.005
ades+0.965
keys+0.916
 mercy+0.912
Neg logit contributions
 around-0.729
 air-0.709
cy-0.682
rated-0.675
et-0.654
Token,
Token ID11
Feature activation-1.26e+00

Pos logit contributions
 around+0.225
cy+0.214
 air+0.213
rated+0.209
et+0.202
Neg logit contributions
ves-0.283
vern-0.278
ades-0.257
 backup-0.251
keys-0.250
Token give
Token ID1577
Feature activation-8.28e+00

Pos logit contributions
ves+0.070
vern+0.069
ades+0.063
keys+0.057
His+0.053
Neg logit contributions
 around-0.073
 air-0.068
cy-0.065
 down-0.063
et-0.062
Token me
Token ID502
Feature activation+1.05e+00

Pos logit contributions
ves+0.613
vern+0.611
ades+0.562
keys+0.554
 backup+0.546
Neg logit contributions
 around-0.319
 air-0.289
cy-0.281
et-0.263
rated-0.258
Token your
Token ID534
Feature activation-2.49e+00

Pos logit contributions
 around+0.057
 air+0.051
et+0.051
cy+0.049
 down+0.049
Neg logit contributions
ves-0.062
vern-0.061
ades-0.056
keys-0.054
 forgiveness-0.051
Token,
Token ID11
Feature activation-1.43e+00

Pos logit contributions
|+0.292
 around+0.284
cy+0.281
rated+0.280
amp+0.280
Neg logit contributions
vern-0.206
ves-0.204
 mercy-0.185
 forgiveness-0.174
keys-0.171
Token you
Token ID345
Feature activation-3.27e-01

Pos logit contributions
ves+0.081
vern+0.081
ades+0.076
 backup+0.068
 mercy+0.068
Neg logit contributions
 around-0.079
 air-0.073
et-0.069
cy-0.067
 down-0.066
Token are
Token ID389
Feature activation-9.48e-01

Pos logit contributions
vern+0.020
 backup+0.019
ves+0.019
ades+0.018
 mercy+0.018
Neg logit contributions
rated-0.015
 around-0.015
cy-0.015
ening-0.015
et-0.014
Token my
Token ID616
Feature activation-2.84e+00

Pos logit contributions
vern+0.053
ves+0.049
 backup+0.046
 mercy+0.045
keys+0.044
Neg logit contributions
rated-0.052
cy-0.052
 around-0.049
|-0.048
ening-0.047
Token best
Token ID1266
Feature activation+2.54e+00

Pos logit contributions
ves+0.141
vern+0.129
ades+0.121
keys+0.115
 mercy+0.109
Neg logit contributions
 around-0.175
cy-0.172
 air-0.171
et-0.160
rated-0.157
Token mate
Token ID16133
Feature activation-1.68e+01

Pos logit contributions
 around+0.166
cy+0.155
 air+0.153
 down+0.146
et+0.144
Neg logit contributions
ves-0.119
vern-0.114
ades-0.103
 backup-0.096
keys-0.096
Token!"
Token ID2474
Feature activation+1.12e+00

Pos logit contributions
ves+1.020
vern+1.000
ades+0.927
keys+0.905
 mercy+0.897
Neg logit contributions
 around-0.782
 air-0.755
cy-0.744
rated-0.734
et-0.707
Token Tom
Token ID4186
Feature activation+5.84e+00

Pos logit contributions
 around+0.045
 air+0.042
cy+0.040
et+0.037
 down+0.036
Neg logit contributions
vern-0.081
ves-0.081
ades-0.076
keys-0.074
 backup-0.072
Token said
Token ID531
Feature activation-1.35e+00

Pos logit contributions
 around+0.351
cy+0.338
 air+0.336
rated+0.333
et+0.323
Neg logit contributions
ves-0.284
vern-0.277
ades-0.251
keys-0.243
 backup-0.243
Token.
Token ID13
Feature activation+8.32e-03

Pos logit contributions
ves+0.093
vern+0.092
ades+0.087
keys+0.086
 backup+0.084
Neg logit contributions
 around-0.059
 air-0.049
cy-0.049
 down-0.048
rated-0.047
Token He
Token ID679
Feature activation+1.27e+00

Pos logit contributions
 around+0.000
 air+0.000
cy+0.000
rated+0.000
 down+0.000
Neg logit contributions
vern-0.001
ves-0.000
keys-0.000
ades-0.000
 mercy-0.000
Token
Token ID198
Feature activation-6.91e-01

Pos logit contributions
vern+0.044
ves+0.043
 mercy+0.042
keys+0.041
 backup+0.041
Neg logit contributions
 around-0.032
cy-0.029
 air-0.028
|-0.027
rated-0.027
Token"
Token ID1
Feature activation-9.55e+00

Pos logit contributions
vern+0.033
 mercy+0.032
 forgiveness+0.031
 backup+0.029
ves+0.029
Neg logit contributions
 around-0.042
cy-0.042
ny-0.039
 air-0.039
et-0.038
TokenAr
Token ID3163
Feature activation-1.06e+01

Pos logit contributions
vern+0.613
ves+0.594
ades+0.546
 backup+0.541
 mercy+0.537
Neg logit contributions
cy-0.452
 around-0.449
 air-0.430
rated-0.410
et-0.403
Tokenrr
Token ID21062
Feature activation-1.94e+00

Pos logit contributions
ves+0.628
vern+0.602
 mercy+0.555
 forgiveness+0.549
ades+0.545
Neg logit contributions
 around-0.479
cy-0.469
et-0.441
|-0.439
rated-0.423
Token,
Token ID11
Feature activation-9.96e-01

Pos logit contributions
ves+0.118
vern+0.116
ades+0.107
 backup+0.104
keys+0.104
Neg logit contributions
 around-0.095
cy-0.090
 air-0.089
rated-0.087
et-0.085
Token mate
Token ID16133
Feature activation-1.67e+01

Pos logit contributions
ves+0.059
vern+0.059
ades+0.055
keys+0.048
 mercy+0.048
Neg logit contributions
 around-0.054
 air-0.050
cy-0.047
 down-0.045
 through-0.044
Tokeny
Token ID88
Feature activation+4.62e+00

Pos logit contributions
ves+1.155
vern+1.124
ades+1.103
 mercy+1.040
keys+1.031
Neg logit contributions
 around-0.579
 air-0.568
rated-0.511
et-0.494
|-0.491
Token,
Token ID11
Feature activation-9.81e-01

Pos logit contributions
 around+0.229
cy+0.219
 air+0.216
rated+0.214
et+0.206
Neg logit contributions
ves-0.271
vern-0.263
ades-0.243
keys-0.239
 backup-0.237
Token this
Token ID428
Feature activation-2.40e+00

Pos logit contributions
ves+0.054
vern+0.054
ades+0.050
keys+0.045
 mercy+0.044
Neg logit contributions
 around-0.057
 air-0.052
cy-0.050
et-0.048
 down-0.048
Token is
Token ID318
Feature activation+1.18e+00

Pos logit contributions
ves+0.167
vern+0.166
ades+0.154
 backup+0.152
keys+0.151
Neg logit contributions
 around-0.094
 air-0.089
cy-0.088
rated-0.085
et-0.083
Token our
Token ID674
Feature activation-5.76e+00

Pos logit contributions
 around+0.068
 air+0.064
cy+0.063
rated+0.063
et+0.062
Neg logit contributions
ves-0.062
vern-0.060
ades-0.056
keys-0.053
 backup-0.052
Token this
Token ID428
Feature activation-2.49e+00

Pos logit contributions
 around+0.018
 air+0.018
cy+0.017
et+0.016
rated+0.016
Neg logit contributions
vern-0.021
ves-0.021
ades-0.020
 backup-0.019
keys-0.019
Token noise
Token ID7838
Feature activation-6.09e-01

Pos logit contributions
ves+0.137
vern+0.133
ades+0.121
keys+0.119
 backup+0.118
Neg logit contributions
 around-0.133
cy-0.129
 air-0.125
rated-0.124
et-0.121
Token to
Token ID284
Feature activation-3.02e+00

Pos logit contributions
ves+0.039
vern+0.039
ades+0.036
keys+0.035
 backup+0.035
Neg logit contributions
 around-0.026
cy-0.026
 air-0.025
rated-0.025
et-0.024
Token find
Token ID1064
Feature activation-1.65e+00

Pos logit contributions
ves+0.164
vern+0.160
ades+0.146
 backup+0.143
keys+0.142
Neg logit contributions
 around-0.164
cy-0.157
 air-0.156
rated-0.154
et-0.149
Token a
Token ID257
Feature activation-4.57e+00

Pos logit contributions
ves+0.089
vern+0.088
ades+0.082
keys+0.079
 backup+0.076
Neg logit contributions
 around-0.095
 air-0.091
cy-0.085
et-0.085
 down-0.082
Token mate
Token ID16133
Feature activation-1.67e+01

Pos logit contributions
ves+0.249
vern+0.244
ades+0.229
keys+0.220
 mercy+0.213
Neg logit contributions
 around-0.248
 air-0.245
cy-0.237
rated-0.224
et-0.222
Token.
Token ID13
Feature activation+2.53e-01

Pos logit contributions
ves+1.061
vern+1.040
ades+0.971
keys+0.948
 backup+0.938
Neg logit contributions
 around-0.735
 air-0.706
cy-0.702
rated-0.684
et-0.662
Token It
Token ID632
Feature activation+9.29e+00

Pos logit contributions
 around+0.008
cy+0.008
 air+0.008
rated+0.007
et+0.007
Neg logit contributions
ves-0.019
vern-0.019
ades-0.018
 backup-0.018
keys-0.017
Token only
Token ID691
Feature activation+4.51e+00

Pos logit contributions
 around+0.347
cy+0.325
 air+0.322
rated+0.313
et+0.301
Neg logit contributions
ves-0.665
vern-0.656
ades-0.613
 backup-0.601
keys-0.599
Token comes
Token ID2058
Feature activation-2.16e-01

Pos logit contributions
 around+0.200
cy+0.195
rated+0.191
 air+0.188
et+0.182
Neg logit contributions
ves-0.282
vern-0.274
ades-0.254
 backup-0.252
keys-0.251
Token out
Token ID503
Feature activation-3.10e-03

Pos logit contributions
ves+0.013
vern+0.013
ades+0.012
keys+0.011
 backup+0.011
Neg logit contributions
 around-0.011
cy-0.010
 air-0.010
rated-0.010
et-0.010
Token say
Token ID910
Feature activation-1.25e-01

Pos logit contributions
 around+0.233
 air+0.210
cy+0.209
et+0.199
 down+0.195
Neg logit contributions
ves-0.278
vern-0.276
ades-0.254
 backup-0.247
keys-0.244
Token '
Token ID705
Feature activation-6.55e+00

Pos logit contributions
vern+0.006
ves+0.006
ades+0.006
keys+0.005
 backup+0.005
Neg logit contributions
 around-0.007
 air-0.007
 down-0.007
et-0.006
cy-0.006
TokenAh
Token ID10910
Feature activation-2.98e+00

Pos logit contributions
ves+0.365
vern+0.335
ades+0.329
keys+0.328
 backup+0.303
Neg logit contributions
 around-0.340
rated-0.328
 air-0.328
zie-0.311
ening-0.309
Tokenoy
Token ID726
Feature activation-6.29e+00

Pos logit contributions
vern+0.162
ves+0.153
 mercy+0.146
ades+0.146
 backup+0.143
Neg logit contributions
et-0.150
 around-0.149
 air-0.142
cy-0.139
ening-0.133
Token,
Token ID11
Feature activation-1.22e+00

Pos logit contributions
ves+0.356
vern+0.351
ades+0.316
 backup+0.308
 mercy+0.308
Neg logit contributions
 around-0.333
cy-0.319
 air-0.312
rated-0.301
et-0.300
Token mate
Token ID16133
Feature activation-1.67e+01

Pos logit contributions
vern+0.056
ves+0.056
ades+0.050
 mercy+0.045
keys+0.045
Neg logit contributions
 around-0.081
 air-0.076
cy-0.075
et-0.073
 down-0.071
Tokeny
Token ID88
Feature activation+4.68e+00

Pos logit contributions
ves+1.295
vern+1.275
ades+1.212
keys+1.182
 backup+1.172
Neg logit contributions
 around-0.506
 air-0.473
cy-0.454
rated-0.449
et-0.426
Token!'
Token ID13679
Feature activation-1.01e+00

Pos logit contributions
 around+0.232
cy+0.221
 air+0.221
rated+0.213
et+0.209
Neg logit contributions
ves-0.277
vern-0.275
ades-0.251
 backup-0.246
keys-0.242
Token and
Token ID290
Feature activation+1.47e+00

Pos logit contributions
ves+0.071
vern+0.070
ades+0.065
keys+0.065
 backup+0.062
Neg logit contributions
 around-0.042
 air-0.040
cy-0.037
 down-0.035
et-0.034
Token '
Token ID705
Feature activation-6.52e+00

Pos logit contributions
 around+0.079
cy+0.075
 air+0.075
rated+0.073
et+0.071
Neg logit contributions
ves-0.082
vern-0.080
ades-0.074
 backup-0.072
keys-0.071
TokenLand
Token ID22342
Feature activation-2.32e+00

Pos logit contributions
ves+0.345
vern+0.332
ades+0.315
keys+0.307
 backup+0.301
Neg logit contributions
 around-0.357
rated-0.342
 air-0.340
cy-0.331
et-0.323
Token,
Token ID11
Feature activation-1.26e+00

Pos logit contributions
vern+0.094
keys+0.093
ves+0.093
 mercy+0.089
ades+0.088
Neg logit contributions
 around-0.049
 down-0.040
 air-0.037
 through-0.033
et-0.032
Token "
Token ID366
Feature activation-4.10e+00

Pos logit contributions
vern+0.076
ves+0.075
ades+0.069
 mercy+0.068
 backup+0.067
Neg logit contributions
 around-0.067
 air-0.060
 down-0.059
et-0.056
cy-0.056
TokenAr
Token ID3163
Feature activation-1.06e+01

Pos logit contributions
vern+0.235
ves+0.230
 mercy+0.210
 backup+0.205
ades+0.204
Neg logit contributions
 around-0.219
cy-0.215
 air-0.212
|-0.196
rated-0.196
Tokenrr
Token ID21062
Feature activation-2.02e+00

Pos logit contributions
ves+0.623
vern+0.594
ades+0.551
 mercy+0.548
 forgiveness+0.547
Neg logit contributions
 around-0.499
cy-0.485
et-0.473
 air-0.455
|-0.445
Token,
Token ID11
Feature activation-1.26e+00

Pos logit contributions
ves+0.126
vern+0.126
 mercy+0.116
 forgiveness+0.115
ades+0.114
Neg logit contributions
 around-0.092
cy-0.087
 air-0.086
et-0.084
rated-0.082
Token mate
Token ID16133
Feature activation-1.67e+01

Pos logit contributions
vern+0.065
ves+0.063
ades+0.058
keys+0.052
 mercy+0.050
Neg logit contributions
 around-0.078
 air-0.074
 down-0.067
et-0.067
cy-0.066
Tokeny
Token ID88
Feature activation+4.75e+00

Pos logit contributions
ves+1.183
vern+1.156
ades+1.113
 backup+1.059
keys+1.054
Neg logit contributions
 around-0.593
 air-0.558
rated-0.540
cy-0.522
et-0.503
Token!"
Token ID2474
Feature activation+1.10e+00

Pos logit contributions
 around+0.214
 air+0.204
cy+0.202
rated+0.193
et+0.191
Neg logit contributions
vern-0.304
ves-0.303
ades-0.279
 backup-0.273
keys-0.273
Token
Token ID198
Feature activation-1.03e+00

Pos logit contributions
 around+0.045
 air+0.042
 down+0.037
cy+0.037
|+0.034
Neg logit contributions
vern-0.077
ves-0.077
keys-0.074
ades-0.071
 mercy-0.069
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
vern+0.068
ves+0.067
keys+0.065
 mercy+0.062
ades+0.062
Neg logit contributions
 around-0.044
 air-0.039
cy-0.038
|-0.036
 down-0.035
Token"
Token ID1
Feature activation-9.75e+00

Pos logit contributions
vern+0.057
keys+0.052
ves+0.052
sters+0.050
ades+0.050
Neg logit contributions
 around-0.059
ny-0.056
cy-0.054
 air-0.054
 down-0.050
Token shouting
Token ID19642
Feature activation-2.10e+00

Pos logit contributions
ves+0.069
vern+0.068
ades+0.063
 backup+0.061
keys+0.061
Neg logit contributions
 around-0.059
cy-0.056
 air-0.056
rated-0.054
et-0.053
Token "
Token ID366
Feature activation-3.97e+00

Pos logit contributions
ves+0.137
vern+0.137
ades+0.125
 backup+0.123
keys+0.123
Neg logit contributions
 around-0.094
 air-0.086
cy-0.085
rated-0.083
et-0.081
TokenAh
Token ID10910
Feature activation-2.91e+00

Pos logit contributions
ves+0.214
vern+0.198
ades+0.196
keys+0.187
 backup+0.181
Neg logit contributions
 around-0.217
 air-0.205
rated-0.202
cy-0.201
ening-0.194
Tokenoy
Token ID726
Feature activation-6.23e+00

Pos logit contributions
vern+0.138
ves+0.124
 forgiveness+0.122
 mercy+0.120
ades+0.116
Neg logit contributions
et-0.177
 around-0.169
 air-0.167
cy-0.160
ening-0.156
Token,
Token ID11
Feature activation-1.17e+00

Pos logit contributions
ves+0.367
vern+0.363
ades+0.332
 backup+0.322
 mercy+0.321
Neg logit contributions
 around-0.313
cy-0.299
 air-0.296
rated-0.286
et-0.283
Token mate
Token ID16133
Feature activation-1.67e+01

Pos logit contributions
vern+0.060
ves+0.059
ades+0.053
keys+0.050
 forgiveness+0.049
Neg logit contributions
 around-0.070
 air-0.067
cy-0.065
et-0.064
rated-0.062
Tokeny
Token ID88
Feature activation+4.62e+00

Pos logit contributions
ves+1.148
vern+1.113
ades+1.077
keys+1.027
 backup+1.021
Neg logit contributions
 around-0.630
 air-0.598
rated-0.574
cy-0.557
|-0.538
Token!"
Token ID2474
Feature activation+1.23e+00

Pos logit contributions
 around+0.213
cy+0.202
 air+0.201
rated+0.196
et+0.191
Neg logit contributions
ves-0.289
vern-0.285
ades-0.263
 backup-0.257
keys-0.256
Token and
Token ID290
Feature activation+1.60e+00

Pos logit contributions
rated+0.050
cy+0.047
 around+0.047
et+0.046
ening+0.046
Neg logit contributions
ves-0.082
ades-0.075
vern-0.074
keys-0.072
 backup-0.071
Token "
Token ID366
Feature activation-3.98e+00

Pos logit contributions
 around+0.084
cy+0.080
 air+0.080
rated+0.078
et+0.076
Neg logit contributions
ves-0.091
vern-0.089
ades-0.082
 backup-0.080
keys-0.079
TokenSh
Token ID2484
Feature activation-9.02e+00

Pos logit contributions
ves+0.205
vern+0.199
ades+0.184
keys+0.178
 backup+0.178
Neg logit contributions
 around-0.227
cy-0.217
 air-0.216
rated-0.214
et-0.207
Token and
Token ID290
Feature activation+1.47e+00

Pos logit contributions
ves+0.746
vern+0.736
ades+0.679
 backup+0.665
 mercy+0.652
Neg logit contributions
 around-0.629
cy-0.590
 air-0.587
rated-0.567
et-0.559
Token you
Token ID345
Feature activation-3.67e-01

Pos logit contributions
 around+0.068
 air+0.062
 down+0.060
cy+0.057
 through+0.053
Neg logit contributions
ves-0.103
vern-0.103
ades-0.097
keys-0.088
ggy-0.082
Token'll
Token ID1183
Feature activation+4.24e+00

Pos logit contributions
ves+0.023
vern+0.023
ades+0.021
 backup+0.021
keys+0.021
Neg logit contributions
 around-0.016
cy-0.016
 air-0.016
rated-0.015
et-0.015
Token be
Token ID307
Feature activation-3.97e+00

Pos logit contributions
 around+0.206
 air+0.193
cy+0.187
et+0.185
rated+0.179
Neg logit contributions
ves-0.260
vern-0.254
ades-0.241
keys-0.233
 mercy-0.225
Token the
Token ID262
Feature activation+4.00e+00

Pos logit contributions
vern+0.184
ves+0.184
 backup+0.165
ades+0.164
keys+0.158
Neg logit contributions
rated-0.235
cy-0.235
 around-0.228
 air-0.225
|-0.219
Token mate
Token ID16133
Feature activation-1.67e+01

Pos logit contributions
 around+0.269
 air+0.263
cy+0.256
et+0.251
rated+0.245
Neg logit contributions
ves-0.175
vern-0.164
ades-0.148
keys-0.137
 mercy-0.134
Token.
Token ID13
Feature activation+1.97e-01

Pos logit contributions
ves+1.027
vern+1.011
ades+0.935
 backup+0.913
keys+0.909
Neg logit contributions
 around-0.788
cy-0.748
 air-0.742
rated-0.727
et-0.705
Token We
Token ID775
Feature activation-1.07e+00

Pos logit contributions
 around+0.009
cy+0.009
rated+0.009
et+0.009
ening+0.008
Neg logit contributions
ves-0.011
vern-0.011
 backup-0.011
 mercy-0.011
keys-0.010
Token'll
Token ID1183
Feature activation+4.25e+00

Pos logit contributions
ves+0.066
vern+0.065
 backup+0.061
keys+0.059
ades+0.059
Neg logit contributions
rated-0.046
 around-0.045
 air-0.044
ening-0.044
cy-0.043
Token sail
Token ID14936
Feature activation-6.52e+00

Pos logit contributions
 around+0.212
 air+0.201
cy+0.196
et+0.191
rated+0.185
Neg logit contributions
ves-0.257
vern-0.249
ades-0.237
keys-0.227
 mercy-0.219
Token across
Token ID1973
Feature activation+3.61e+00

Pos logit contributions
ves+0.399
vern+0.383
ades+0.365
 backup+0.355
keys+0.347
Neg logit contributions
rated-0.295
 around-0.291
cy-0.290
 air-0.285
et-0.271
Token
Token ID220
Feature activation+3.38e+00

Pos logit contributions
rated+0.020
 around+0.020
cy+0.019
et+0.019
 air+0.019
Neg logit contributions
ves-0.025
vern-0.024
 backup-0.022
ades-0.022
keys-0.022
Token
Token ID198
Feature activation-4.74e-01

Pos logit contributions
 around+0.180
cy+0.174
 air+0.173
rated+0.173
et+0.168
Neg logit contributions
ves-0.188
vern-0.185
ades-0.169
 backup-0.163
keys-0.162
Token
Token ID198
Feature activation-4.87e-01

Pos logit contributions
ves+0.029
vern+0.029
ades+0.027
 mercy+0.027
 backup+0.027
Neg logit contributions
 around-0.022
cy-0.021
 air-0.020
rated-0.019
|-0.019
TokenMax
Token ID11518
Feature activation+2.02e+00

Pos logit contributions
sters+0.025
vern+0.025
 mercy+0.024
ves+0.023
ades+0.023
Neg logit contributions
 around-0.027
|-0.025
cy-0.023
 air-0.023
he-0.023
Tokenâ
Token ID22940
Feature activation+9.65e-01

Pos logit contributions
 around+0.099
cy+0.095
 air+0.094
rated+0.093
et+0.089
Neg logit contributions
ves-0.120
vern-0.118
ades-0.109
keys-0.106
 backup-0.106
Token
Token ID26391
Feature activation+1.52e+01

Pos logit contributions
 around+0.044
 down+0.039
 air+0.035
ening+0.035
 through+0.034
Neg logit contributions
vern-0.058
ves-0.055
His-0.053
 forgiveness-0.052
 mercy-0.050
Token
Token ID8151
Feature activation+7.79e-01

Pos logit contributions
 around+0.779
cy+0.742
 air+0.733
rated+0.709
et+0.697
Neg logit contributions
ves-0.868
vern-0.857
ades-0.787
 backup-0.774
 mercy-0.771
Tokens
Token ID82
Feature activation-6.49e+00

Pos logit contributions
 around+0.035
 air+0.034
rated+0.033
cy+0.033
et+0.031
Neg logit contributions
ves-0.050
vern-0.049
ades-0.045
 backup-0.044
keys-0.043
Token mom
Token ID1995
Feature activation-3.54e+00

Pos logit contributions
ves+0.273
vern+0.270
ades+0.240
keys+0.232
 backup+0.225
Neg logit contributions
 around-0.448
 air-0.427
cy-0.418
et-0.404
rated-0.402
Token was
Token ID373
Feature activation-1.03e+00

Pos logit contributions
ves+0.203
vern+0.198
ades+0.183
keys+0.178
 backup+0.178
Neg logit contributions
 around-0.181
cy-0.173
 air-0.173
rated-0.171
et-0.164
Token very
Token ID845
Feature activation+5.34e+00

Pos logit contributions
ves+0.069
vern+0.068
ades+0.063
 backup+0.062
keys+0.062
Neg logit contributions
 around-0.043
cy-0.041
 air-0.040
rated-0.040
et-0.038
Token there
Token ID612
Feature activation+1.31e+00

Pos logit contributions
 around+0.420
cy+0.410
rated+0.409
 air+0.408
et+0.389
Neg logit contributions
ves-0.529
vern-0.520
ades-0.475
 backup-0.470
keys-0.467
Token.
Token ID13
Feature activation+4.43e-01

Pos logit contributions
 around+0.063
cy+0.060
 air+0.060
rated+0.059
et+0.057
Neg logit contributions
ves-0.079
vern-0.077
ades-0.071
 backup-0.069
keys-0.069
Token
Token ID198
Feature activation-5.81e-01

Pos logit contributions
rated+0.023
et+0.023
 around+0.022
cy+0.022
ening+0.021
Neg logit contributions
ves-0.024
vern-0.024
 backup-0.022
ades-0.022
 forgiveness-0.022
Token
Token ID198
Feature activation-6.03e-01

Pos logit contributions
ves+0.034
vern+0.034
keys+0.032
ades+0.031
 backup+0.031
Neg logit contributions
 around-0.029
cy-0.026
 air-0.026
|-0.025
rated-0.025
TokenMom
Token ID29252
Feature activation-3.06e+00

Pos logit contributions
vern+0.028
ves+0.028
 mercy+0.027
sters+0.026
 backup+0.026
Neg logit contributions
 around-0.036
cy-0.033
 air-0.033
|-0.032
rated-0.032
Tokenmy
Token ID1820
Feature activation+8.88e+00

Pos logit contributions
ves+0.237
vern+0.232
ades+0.225
 backup+0.218
 mercy+0.217
Neg logit contributions
 around-0.081
rated-0.078
 air-0.076
cy-0.071
|-0.070
Token and
Token ID290
Feature activation+1.66e+00

Pos logit contributions
 around+0.470
cy+0.443
 air+0.438
et+0.423
rated+0.419
Neg logit contributions
vern-0.507
ves-0.504
ades-0.460
 backup-0.453
 mercy-0.443
Token Sarah
Token ID10490
Feature activation+6.19e+00

Pos logit contributions
 around+0.087
cy+0.082
 air+0.082
rated+0.081
et+0.078
Neg logit contributions
ves-0.095
vern-0.094
ades-0.086
 backup-0.084
keys-0.084
Token danced
Token ID39480
Feature activation+1.06e+00

Pos logit contributions
 around+0.311
 air+0.300
rated+0.299
cy+0.296
et+0.281
Neg logit contributions
ves-0.352
vern-0.342
ades-0.316
keys-0.311
 backup-0.306
Token together
Token ID1978
Feature activation-2.79e+00

Pos logit contributions
rated+0.042
cy+0.042
 air+0.041
 around+0.039
et+0.039
Neg logit contributions
ves-0.072
vern-0.069
ades-0.065
 backup-0.063
keys-0.061
Token until
Token ID1566
Feature activation+3.41e+00

Pos logit contributions
ves+0.167
vern+0.160
ades+0.147
 backup+0.145
keys+0.144
Neg logit contributions
cy-0.131
rated-0.131
 air-0.128
 around-0.127
et-0.122
Token saw
Token ID2497
Feature activation+5.56e-01

Pos logit contributions
vern+0.003
ves+0.003
 mercy+0.003
 backup+0.003
 forgiveness+0.003
Neg logit contributions
 around-0.003
cy-0.003
 air-0.003
et-0.003
amp-0.003
Token the
Token ID262
Feature activation+4.36e+00

Pos logit contributions
rated+0.030
cy+0.030
 around+0.030
 air+0.029
|+0.028
Neg logit contributions
ves-0.029
vern-0.028
ades-0.026
 backup-0.026
 forgiveness-0.025
Token person
Token ID1048
Feature activation-4.69e+00

Pos logit contributions
 around+0.241
cy+0.236
rated+0.233
 air+0.227
et+0.226
Neg logit contributions
ves-0.225
vern-0.223
ades-0.202
 backup-0.201
 mercy-0.196
Token again
Token ID757
Feature activation+4.70e-01

Pos logit contributions
ves+0.266
vern+0.261
ades+0.240
keys+0.236
 backup+0.235
Neg logit contributions
 around-0.236
 air-0.229
cy-0.229
rated-0.227
et-0.217
Token.
Token ID13
Feature activation+4.64e-01

Pos logit contributions
 around+0.021
cy+0.019
 air+0.019
rated+0.018
et+0.018
Neg logit contributions
ves-0.031
vern-0.031
ades-0.029
 backup-0.028
keys-0.028
Token But
Token ID887
Feature activation+7.97e+00

Pos logit contributions
rated+0.024
 around+0.024
et+0.024
ening+0.023
cy+0.023
Neg logit contributions
vern-0.025
ves-0.024
 backup-0.023
 forgiveness-0.022
 charity-0.022
Token she
Token ID673
Feature activation-5.51e+00

Pos logit contributions
 around+0.515
cy+0.491
 air+0.490
rated+0.475
et+0.467
Neg logit contributions
ves-0.361
vern-0.357
ades-0.327
 backup-0.307
keys-0.307
Token never
Token ID1239
Feature activation-8.77e-02

Pos logit contributions
ves+0.324
vern+0.320
ades+0.297
 backup+0.289
keys+0.285
Neg logit contributions
 around-0.278
cy-0.264
 air-0.261
rated-0.256
et-0.250
Token forgot
Token ID16453
Feature activation-1.17e+00

Pos logit contributions
ves+0.004
vern+0.004
 mercy+0.004
 backup+0.004
keys+0.004
Neg logit contributions
 around-0.005
 air-0.005
cy-0.005
rated-0.005
et-0.005
Token that
Token ID326
Feature activation-3.27e+00

Pos logit contributions
ves+0.072
vern+0.071
ades+0.067
keys+0.065
 backup+0.064
Neg logit contributions
 around-0.058
 air-0.053
cy-0.051
et-0.049
rated-0.049
Token night
Token ID1755
Feature activation+1.34e+01

Pos logit contributions
ves+0.216
vern+0.213
 forgiveness+0.195
ades+0.193
 backup+0.193
Neg logit contributions
 around-0.133
cy-0.132
rated-0.128
 air-0.125
et-0.123
Token At
Token ID1629
Feature activation+5.86e+00

Pos logit contributions
cy+0.007
rated+0.007
et+0.007
 around+0.006
ening+0.006
Neg logit contributions
ves-0.010
vern-0.009
keys-0.009
ades-0.009
 mercy-0.009
Token the
Token ID262
Feature activation+4.20e+00

Pos logit contributions
rated+0.280
 around+0.278
cy+0.272
 air+0.265
et+0.257
Neg logit contributions
ves-0.344
vern-0.336
 backup-0.317
 mercy-0.312
ades-0.304
Token end
Token ID886
Feature activation-3.17e+00

Pos logit contributions
 around+0.202
cy+0.192
rated+0.191
 air+0.184
et+0.181
Neg logit contributions
ves-0.253
vern-0.250
 backup-0.232
ades-0.228
 mercy-0.225
Token of
Token ID286
Feature activation-5.21e+00

Pos logit contributions
vern+0.188
ves+0.183
ades+0.169
 mercy+0.167
 backup+0.165
Neg logit contributions
 around-0.167
 air-0.154
cy-0.153
|-0.137
 down-0.136
Token the
Token ID262
Feature activation+4.22e+00

Pos logit contributions
ves+0.291
vern+0.278
 backup+0.258
 mercy+0.258
 forgiveness+0.253
Neg logit contributions
rated-0.276
 around-0.262
cy-0.256
 air-0.251
et-0.247
Token day
Token ID1110
Feature activation+1.23e+01

Pos logit contributions
 around+0.107
cy+0.099
rated+0.096
et+0.095
 air+0.088
Neg logit contributions
ves-0.352
vern-0.345
ades-0.324
 backup-0.324
keys-0.320
Token,
Token ID11
Feature activation-1.17e+00

Pos logit contributions
rated+0.686
 around+0.663
cy+0.650
et+0.650
 air+0.625
Neg logit contributions
ves-0.657
vern-0.619
ades-0.580
keys-0.571
 backup-0.566
Token the
Token ID262
Feature activation+4.20e+00

Pos logit contributions
ves+0.067
vern+0.064
keys+0.060
ades+0.060
 mercy+0.058
Neg logit contributions
 around-0.058
cy-0.056
rated-0.056
 air-0.056
et-0.056
Token cat
Token ID3797
Feature activation+3.25e+00

Pos logit contributions
 around+0.197
 air+0.191
cy+0.185
rated+0.177
et+0.173
Neg logit contributions
ves-0.264
vern-0.261
ades-0.243
keys-0.234
 backup-0.233
Token went
Token ID1816
Feature activation+2.54e+00

Pos logit contributions
 around+0.159
cy+0.152
 air+0.151
rated+0.148
et+0.143
Neg logit contributions
ves-0.193
vern-0.190
ades-0.175
 backup-0.171
keys-0.170
Token home
Token ID1363
Feature activation+4.38e+00

Pos logit contributions
 around+0.100
cy+0.093
 air+0.093
rated+0.089
et+0.087
Neg logit contributions
ves-0.179
vern-0.176
ades-0.164
keys-0.161
 backup-0.160
Token regret
Token ID13721
Feature activation+1.87e+00

Pos logit contributions
 around+0.049
cy+0.047
 air+0.046
rated+0.045
et+0.044
Neg logit contributions
ves-0.061
vern-0.060
ades-0.055
 backup-0.054
keys-0.054
Token wearing
Token ID5762
Feature activation+2.73e+00

Pos logit contributions
 around+0.107
cy+0.104
 air+0.103
rated+0.102
et+0.099
Neg logit contributions
ves-0.096
vern-0.094
ades-0.084
 backup-0.083
keys-0.082
Token this
Token ID428
Feature activation-2.38e+00

Pos logit contributions
 around+0.145
 air+0.138
cy+0.135
rated+0.132
et+0.131
Neg logit contributions
ves-0.154
vern-0.151
ades-0.140
keys-0.136
 backup-0.134
Token belt
Token ID10999
Feature activation-4.90e-01

Pos logit contributions
ves+0.104
vern+0.101
ades+0.092
keys+0.090
 mercy+0.087
Neg logit contributions
 around-0.157
 air-0.151
cy-0.148
rated-0.146
et-0.145
Token.
Token ID13
Feature activation+3.81e-01

Pos logit contributions
ves+0.027
vern+0.027
ades+0.024
 backup+0.024
keys+0.023
Neg logit contributions
cy-0.025
 air-0.024
rated-0.023
 around-0.023
|-0.023
Token It
Token ID632
Feature activation+9.52e+00

Pos logit contributions
et+0.021
rated+0.020
 around+0.020
cy+0.019
ening+0.019
Neg logit contributions
ves-0.019
vern-0.019
 forgiveness-0.018
 backup-0.018
keys-0.018
Token got
Token ID1392
Feature activation-2.58e+00

Pos logit contributions
cy+0.483
 around+0.479
et+0.464
rated+0.462
 air+0.454
Neg logit contributions
ves-0.513
vern-0.497
keys-0.455
 mercy-0.453
ades-0.440
Token me
Token ID502
Feature activation+9.12e-01

Pos logit contributions
ves+0.142
vern+0.142
 backup+0.130
ades+0.128
 mercy+0.127
Neg logit contributions
cy-0.132
 around-0.131
rated-0.128
 air-0.126
et-0.123
Token stuck
Token ID7819
Feature activation+1.39e+00

Pos logit contributions
cy+0.039
rated+0.038
 around+0.038
 air+0.038
et+0.036
Neg logit contributions
vern-0.058
ves-0.057
 backup-0.052
ades-0.051
 mercy-0.051
Token on
Token ID319
Feature activation+7.26e+00

Pos logit contributions
rated+0.069
cy+0.069
|+0.066
 air+0.066
zie+0.062
Neg logit contributions
vern-0.069
ves-0.067
 backup-0.063
 mercy-0.061
ades-0.060
Token the
Token ID262
Feature activation+4.29e+00

Pos logit contributions
cy+0.402
rated+0.396
 around+0.392
 air+0.367
et+0.364
Neg logit contributions
ves-0.385
vern-0.369
 backup-0.337
ades-0.332
 mercy-0.326
Token the
Token ID262
Feature activation+4.37e+00

Pos logit contributions
vern+0.186
ves+0.185
ades+0.166
keys+0.164
 backup+0.162
Neg logit contributions
 around-0.191
 air-0.178
cy-0.176
rated-0.169
et-0.165
Token marble
Token ID30623
Feature activation-1.70e+00

Pos logit contributions
 around+0.263
rated+0.254
cy+0.253
 air+0.247
et+0.247
Neg logit contributions
ves-0.205
vern-0.203
ades-0.185
 backup-0.178
 forgiveness-0.175
Token was
Token ID373
Feature activation-1.29e+00

Pos logit contributions
ves+0.108
vern+0.107
ades+0.099
 backup+0.097
keys+0.096
Neg logit contributions
 around-0.077
cy-0.073
 air-0.072
rated-0.070
et-0.069
Token special
Token ID2041
Feature activation-4.47e+00

Pos logit contributions
ves+0.079
vern+0.077
ades+0.072
keys+0.070
 backup+0.070
Neg logit contributions
 around-0.063
 air-0.059
cy-0.058
rated-0.056
et-0.056
Token and
Token ID290
Feature activation+1.64e+00

Pos logit contributions
ves+0.283
vern+0.279
ades+0.259
 backup+0.253
keys+0.252
Neg logit contributions
 around-0.203
cy-0.193
 air-0.191
rated-0.188
et-0.181
Token fragile
Token ID21049
Feature activation+7.83e-01

Pos logit contributions
 around+0.101
 air+0.095
cy+0.093
rated+0.090
et+0.089
Neg logit contributions
vern-0.083
ves-0.081
ades-0.073
 backup-0.071
keys-0.069
Token,
Token ID11
Feature activation-1.11e+00

Pos logit contributions
rated+0.041
cy+0.041
|+0.041
 around+0.040
 air+0.039
Neg logit contributions
ves-0.041
vern-0.038
 forgiveness-0.036
 mercy-0.036
ades-0.036
Token so
Token ID523
Feature activation+5.28e+00

Pos logit contributions
ves+0.065
vern+0.064
ades+0.059
keys+0.057
 backup+0.057
Neg logit contributions
 around-0.057
 air-0.054
cy-0.053
rated-0.052
et-0.051
Token he
Token ID339
Feature activation-9.25e+00

Pos logit contributions
 around+0.346
 air+0.321
cy+0.309
rated+0.306
 down+0.302
Neg logit contributions
vern-0.250
ves-0.229
 backup-0.212
ades-0.210
 mercy-0.204
Token said
Token ID531
Feature activation-1.08e+00

Pos logit contributions
vern+0.649
ves+0.596
 backup+0.586
ades+0.571
 mercy+0.564
Neg logit contributions
 around-0.432
cy-0.361
et-0.358
 air-0.353
ny-0.329
Token to
Token ID284
Feature activation-2.90e+00

Pos logit contributions
vern+0.062
ves+0.060
ades+0.056
keys+0.053
 backup+0.052
Neg logit contributions
 around-0.060
 down-0.052
 air-0.050
et-0.046
 through-0.045
Token down
Token ID866
Feature activation+1.20e+01

Pos logit contributions
rated+0.096
|+0.087
zie+0.078
ening+0.077
gent+0.073
Neg logit contributions
ves-0.172
ades-0.158
vern-0.154
 they-0.151
 backup-0.151
Token fast
Token ID3049
Feature activation+4.78e+00

Pos logit contributions
rated+0.615
cy+0.568
 around+0.562
et+0.548
|+0.544
Neg logit contributions
ves-0.687
vern-0.668
ades-0.628
 backup-0.615
 mercy-0.588
Token and
Token ID290
Feature activation+1.33e+00

Pos logit contributions
rated+0.285
cy+0.261
|+0.261
zie+0.260
amp+0.242
Neg logit contributions
ves-0.223
vern-0.206
 backup-0.198
ades-0.195
 mercy-0.192
Token laugh
Token ID6487
Feature activation+9.67e-01

Pos logit contributions
rated+0.072
cy+0.072
oline+0.069
ained+0.069
amp+0.069
Neg logit contributions
ves-0.066
vern-0.061
 backup-0.058
 else-0.057
 mercy-0.056
Token.
Token ID13
Feature activation+2.20e-01

Pos logit contributions
cy+0.049
rated+0.048
 around+0.047
 air+0.047
|+0.046
Neg logit contributions
ves-0.055
vern-0.053
ades-0.049
keys-0.047
 backup-0.047
Token They
Token ID1119
Feature activation+1.43e+00

Pos logit contributions
rated+0.009
 around+0.009
et+0.009
cy+0.009
 air+0.008
Neg logit contributions
ves-0.015
vern-0.014
ades-0.013
 backup-0.013
keys-0.013
Token have
Token ID423
Feature activation+2.81e+00

Pos logit contributions
rated+0.078
ening+0.076
 around+0.073
cy+0.072
ained+0.072
Neg logit contributions
vern-0.073
ves-0.071
 backup-0.065
 mercy-0.063
 else-0.063
Token fun
Token ID1257
Feature activation+5.90e-01

Pos logit contributions
 around+0.152
 air+0.147
cy+0.139
et+0.136
rated+0.134
Neg logit contributions
ves-0.158
vern-0.154
ades-0.142
keys-0.141
 backup-0.137
Token on
Token ID319
Feature activation+6.85e+00

Pos logit contributions
 around+0.028
cy+0.027
 air+0.026
rated+0.026
et+0.025
Neg logit contributions
ves-0.037
vern-0.036
ades-0.033
 backup-0.032
keys-0.032
Token the
Token ID262
Feature activation+3.94e+00

Pos logit contributions
 around+0.302
 air+0.284
cy+0.283
rated+0.271
et+0.267
Neg logit contributions
ves-0.446
vern-0.443
ades-0.410
 backup-0.402
keys-0.401
Token slide
Token ID10649
Feature activation+2.45e+00

Pos logit contributions
cy+0.230
rated+0.222
 around+0.220
ening+0.208
|+0.207
Neg logit contributions
ves-0.202
vern-0.193
ades-0.182
 backup-0.165
 mercy-0.159
Token a
Token ID257
Feature activation-4.46e+00

Pos logit contributions
ves+0.143
vern+0.139
ades+0.130
 backup+0.127
 mercy+0.123
Neg logit contributions
cy-0.121
rated-0.121
 air-0.119
 around-0.114
|-0.112
Token little
Token ID1310
Feature activation-2.02e+00

Pos logit contributions
ves+0.253
vern+0.247
ades+0.228
keys+0.220
 mercy+0.217
Neg logit contributions
 around-0.240
 air-0.225
cy-0.221
rated-0.211
et-0.209
Token longer
Token ID2392
Feature activation-2.21e+00

Pos logit contributions
ves+0.110
vern+0.109
 backup+0.103
 mercy+0.101
ades+0.100
Neg logit contributions
 around-0.099
rated-0.096
cy-0.095
et-0.093
 air-0.092
Token.
Token ID13
Feature activation+3.39e-01

Pos logit contributions
ves+0.122
vern+0.117
keys+0.106
ades+0.105
 backup+0.104
Neg logit contributions
cy-0.113
 around-0.108
|-0.107
rated-0.106
 air-0.105
Token
Token ID198
Feature activation-6.74e-01

Pos logit contributions
rated+0.016
 around+0.015
cy+0.015
et+0.015
ening+0.015
Neg logit contributions
ves-0.019
vern-0.019
His-0.018
ades-0.018
 backup-0.018
Token
Token ID198
Feature activation-6.92e-01

Pos logit contributions
ves+0.040
vern+0.040
keys+0.037
 mercy+0.037
ades+0.037
Neg logit contributions
 around-0.033
cy-0.031
 air-0.030
rated-0.029
et-0.028
TokenOne
Token ID3198
Feature activation-6.89e+00

Pos logit contributions
vern+0.034
ves+0.033
 mercy+0.033
 forgiveness+0.032
keys+0.031
Neg logit contributions
 around-0.041
 air-0.038
cy-0.037
et-0.037
rated-0.037
Token day
Token ID1110
Feature activation+1.23e+01

Pos logit contributions
ves+0.524
vern+0.499
keys+0.475
 wife+0.474
 forgiveness+0.470
Neg logit contributions
 around-0.183
rated-0.179
et-0.178
 air-0.174
ening-0.169
Token,
Token ID11
Feature activation-1.13e+00

Pos logit contributions
 around+0.484
 air+0.433
cy+0.417
 down+0.396
 night+0.366
Neg logit contributions
vern-0.952
ves-0.877
keys-0.850
ades-0.849
 mercy-0.841
Token Ben
Token ID3932
Feature activation+3.58e+00

Pos logit contributions
vern+0.071
ves+0.068
ades+0.062
keys+0.062
 mercy+0.060
Neg logit contributions
 around-0.059
 air-0.055
cy-0.054
 down-0.051
rated-0.050
Token went
Token ID1816
Feature activation+2.61e+00

Pos logit contributions
 around+0.167
cy+0.159
 air+0.158
rated+0.155
et+0.150
Neg logit contributions
ves-0.220
vern-0.216
ades-0.201
 backup-0.196
keys-0.195
Token the
Token ID262
Feature activation+4.16e+00

Pos logit contributions
 around+0.301
 air+0.287
cy+0.277
et+0.261
rated+0.257
Neg logit contributions
ves-0.385
vern-0.372
ades-0.351
keys-0.348
 backup-0.326
Token box
Token ID3091
Feature activation-9.99e-03

Pos logit contributions
 around+0.222
rated+0.217
cy+0.209
et+0.205
ening+0.200
Neg logit contributions
vern-0.225
ves-0.220
 backup-0.211
ades-0.205
 forgiveness-0.203
Token again
Token ID757
Feature activation+4.17e-01

Pos logit contributions
ves+0.001
vern+0.001
ades+0.001
keys+0.001
 backup+0.001
Neg logit contributions
 around-0.000
 air-0.000
cy-0.000
et-0.000
rated-0.000
Token.
Token ID13
Feature activation+2.50e-01

Pos logit contributions
 around+0.020
cy+0.019
 air+0.019
rated+0.018
et+0.018
Neg logit contributions
ves-0.026
vern-0.025
ades-0.023
 backup-0.023
keys-0.023
Token He
Token ID679
Feature activation+1.36e+00

Pos logit contributions
 around+0.009
cy+0.009
 air+0.009
rated+0.008
et+0.008
Neg logit contributions
ves-0.018
vern-0.018
ades-0.017
 backup-0.016
keys-0.016
Token thought
Token ID1807
Feature activation+1.98e+00

Pos logit contributions
 around+0.066
cy+0.063
 air+0.062
rated+0.061
et+0.059
Neg logit contributions
ves-0.083
vern-0.082
ades-0.076
 backup-0.074
keys-0.073
Token it
Token ID340
Feature activation+4.08e+00

Pos logit contributions
 around+0.110
 air+0.091
 down+0.085
 night+0.081
 through+0.081
Neg logit contributions
vern-0.116
ades-0.110
ves-0.109
keys-0.102
sters-0.102
Token was
Token ID373
Feature activation-1.54e+00

Pos logit contributions
 air+0.219
cy+0.216
 around+0.214
rated+0.210
ening+0.205
Neg logit contributions
ves-0.218
vern-0.199
ades-0.183
keys-0.179
 forgiveness-0.176
Token a
Token ID257
Feature activation-4.56e+00

Pos logit contributions
vern+0.073
ves+0.073
 backup+0.064
ades+0.064
 mercy+0.063
Neg logit contributions
 around-0.091
cy-0.090
rated-0.088
 air-0.088
et-0.085
Token terrible
Token ID7818
Feature activation+2.27e+00

Pos logit contributions
ves+0.286
vern+0.259
ades+0.257
keys+0.250
 mercy+0.234
Neg logit contributions
 around-0.224
 air-0.216
cy-0.212
 night-0.200
et-0.192
Token place
Token ID1295
Feature activation+4.61e-01

Pos logit contributions
 around+0.105
cy+0.099
rated+0.096
 air+0.096
et+0.094
Neg logit contributions
ves-0.136
vern-0.133
 forgiveness-0.125
 backup-0.122
 mercy-0.122
Token to
Token ID284
Feature activation-3.03e+00

Pos logit contributions
 around+0.162
 air+0.154
et+0.142
cy+0.137
 down+0.135
Neg logit contributions
ves-0.165
vern-0.165
keys-0.149
ades-0.147
 mercy-0.139
Token get
Token ID651
Feature activation-2.53e+00

Pos logit contributions
ves+0.171
vern+0.166
ades+0.157
keys+0.150
 backup+0.145
Neg logit contributions
 around-0.159
 air-0.154
cy-0.148
et-0.145
rated-0.145
Token along
Token ID1863
Feature activation+3.07e+00

Pos logit contributions
ves+0.159
vern+0.156
ades+0.141
keys+0.140
 mercy+0.131
Neg logit contributions
 around-0.133
 air-0.119
cy-0.116
 down-0.113
et-0.108
Token and
Token ID290
Feature activation+1.52e+00

Pos logit contributions
 around+0.147
cy+0.138
 air+0.138
rated+0.134
et+0.130
Neg logit contributions
ves-0.188
vern-0.186
ades-0.172
 backup-0.167
keys-0.167
Token help
Token ID1037
Feature activation-6.02e+00

Pos logit contributions
 around+0.081
 air+0.074
cy+0.071
 down+0.070
rated+0.070
Neg logit contributions
vern-0.092
ves-0.091
ades-0.085
keys-0.079
 backup-0.076
Token each
Token ID1123
Feature activation+6.50e-01

Pos logit contributions
ves+0.338
vern+0.334
ades+0.306
 backup+0.297
keys+0.296
Neg logit contributions
 around-0.320
cy-0.304
 air-0.302
rated-0.296
et-0.288
Token other
Token ID584
Feature activation-4.18e-01

Pos logit contributions
 around+0.034
 air+0.033
cy+0.032
rated+0.031
et+0.030
Neg logit contributions
vern-0.039
ves-0.038
ades-0.035
keys-0.034
 backup-0.032
Token in
Token ID287
Feature activation+6.41e+00

Pos logit contributions
ves+0.026
vern+0.025
ades+0.024
 backup+0.023
keys+0.023
Neg logit contributions
 around-0.020
cy-0.019
 air-0.019
rated-0.018
et-0.018
Token the
Token ID262
Feature activation+4.45e+00

Pos logit contributions
 around+0.299
 air+0.284
cy+0.274
rated+0.259
et+0.257
Neg logit contributions
ves-0.407
vern-0.396
ades-0.376
keys-0.370
 backup-0.350
Token wedding
Token ID10614
Feature activation-5.69e+00

Pos logit contributions
 around+0.216
cy+0.209
rated+0.206
et+0.196
 air+0.195
Neg logit contributions
ves-0.260
vern-0.258
 backup-0.241
ades-0.240
 mercy-0.235
Token.
Token ID13
Feature activation+3.62e-01

Pos logit contributions
ves+0.349
vern+0.341
ades+0.316
 backup+0.308
keys+0.307
Neg logit contributions
 around-0.269
cy-0.258
 air-0.254
rated-0.251
et-0.243
Token to
Token ID284
Feature activation-2.92e+00

Pos logit contributions
 around+0.162
 air+0.154
cy+0.145
et+0.142
 down+0.138
Neg logit contributions
ves-0.145
vern-0.144
ades-0.129
keys-0.126
 backup-0.118
Token make
Token ID787
Feature activation+4.11e-01

Pos logit contributions
ves+0.162
vern+0.160
ades+0.147
 backup+0.141
keys+0.141
Neg logit contributions
 around-0.158
cy-0.151
 air-0.150
rated-0.146
et-0.143
Token Mom
Token ID11254
Feature activation+2.77e+00

Pos logit contributions
 around+0.023
cy+0.022
rated+0.022
 air+0.022
et+0.021
Neg logit contributions
ves-0.022
vern-0.021
ades-0.020
 backup-0.019
keys-0.019
Tokenmy
Token ID1820
Feature activation+8.55e+00

Pos logit contributions
 air+0.068
 around+0.068
rated+0.067
cy+0.063
et+0.058
Neg logit contributions
ves-0.216
vern-0.214
ades-0.208
keys-0.203
 forgiveness-0.200
Token sad
Token ID6507
Feature activation+5.70e+00

Pos logit contributions
 around+0.411
cy+0.384
 air+0.383
rated+0.373
et+0.365
Neg logit contributions
ves-0.529
vern-0.522
ades-0.480
 backup-0.473
keys-0.464
Token or
Token ID393
Feature activation-1.20e+00

Pos logit contributions
 around+0.258
 air+0.241
cy+0.237
rated+0.231
et+0.224
Neg logit contributions
ves-0.370
vern-0.368
ades-0.339
 backup-0.332
keys-0.330
Token mad
Token ID8805
Feature activation+3.38e+00

Pos logit contributions
ves+0.070
vern+0.069
ades+0.064
 backup+0.063
 mercy+0.062
Neg logit contributions
 around-0.058
cy-0.057
 air-0.055
rated-0.055
et-0.053
Token.
Token ID13
Feature activation+4.04e-01

Pos logit contributions
 around+0.160
cy+0.154
 air+0.152
rated+0.150
et+0.146
Neg logit contributions
ves-0.206
vern-0.202
ades-0.188
 backup-0.183
keys-0.183
Token She
Token ID1375
Feature activation+5.17e+00

Pos logit contributions
rated+0.020
et+0.020
 around+0.018
ening+0.018
cy+0.017
Neg logit contributions
vern-0.023
Her-0.022
ves-0.022
 forgiveness-0.022
 charity-0.021
Token says
Token ID1139
Feature activation+6.61e-01

Pos logit contributions
 around+0.237
cy+0.234
rated+0.226
|+0.218
 air+0.213
Neg logit contributions
ves-0.314
vern-0.301
 mercy-0.280
ades-0.280
 backup-0.279
Token no
Token ID645
Feature activation-6.16e+00

Pos logit contributions
 around+0.038
 air+0.036
 down+0.033
cy+0.032
et+0.032
Neg logit contributions
vern-0.035
ves-0.034
ades-0.032
 backup-0.030
 mercy-0.029
Token upon
Token ID2402
Feature activation-3.03e+00

Pos logit contributions
ves+0.164
vern+0.161
ades+0.146
 backup+0.142
keys+0.139
Neg logit contributions
 around-0.172
 air-0.168
cy-0.165
rated-0.165
et-0.162
Token a
Token ID257
Feature activation-4.14e+00

Pos logit contributions
ves+0.171
vern+0.168
ades+0.157
keys+0.155
 backup+0.153
Neg logit contributions
 around-0.163
 air-0.153
cy-0.146
|-0.143
rated-0.139
Token time
Token ID640
Feature activation+9.03e+00

Pos logit contributions
ves+0.319
vern+0.318
ades+0.294
 backup+0.287
keys+0.283
Neg logit contributions
 around-0.129
 air-0.120
rated-0.113
cy-0.113
ening-0.107
Token,
Token ID11
Feature activation-8.46e-01

Pos logit contributions
 around+0.417
cy+0.393
 air+0.380
rated+0.366
et+0.357
Neg logit contributions
ves-0.575
vern-0.561
ades-0.524
keys-0.514
 backup-0.513
Token there
Token ID612
Feature activation+1.30e+00

Pos logit contributions
ves+0.033
vern+0.031
His+0.028
 else+0.028
ades+0.028
Neg logit contributions
 air-0.056
rated-0.054
et-0.054
ening-0.052
 around-0.052
Token was
Token ID373
Feature activation-1.09e+00

Pos logit contributions
rated+0.084
et+0.079
 around+0.078
 air+0.078
ening+0.077
Neg logit contributions
ves-0.059
vern-0.050
ades-0.048
 else-0.047
ggy-0.046
Token a
Token ID257
Feature activation-4.15e+00

Pos logit contributions
ves+0.045
vern+0.044
ades+0.039
 backup+0.038
keys+0.037
Neg logit contributions
 around-0.073
rated-0.071
cy-0.070
 air-0.069
et-0.069
Token thoughtful
Token ID22677
Feature activation-6.10e+00

Pos logit contributions
ves+0.212
vern+0.209
ades+0.189
 backup+0.183
keys+0.182
Neg logit contributions
 around-0.240
cy-0.231
 air-0.229
rated-0.223
et-0.219
Token hunter
Token ID19177
Feature activation-5.54e+00

Pos logit contributions
ves+0.279
vern+0.274
ades+0.245
 backup+0.244
keys+0.242
Neg logit contributions
 around-0.370
rated-0.360
cy-0.349
|-0.342
 air-0.342
Token.
Token ID13
Feature activation+5.40e-01

Pos logit contributions
vern+0.327
ves+0.326
ades+0.300
 backup+0.292
keys+0.288
Neg logit contributions
 around-0.286
cy-0.264
 air-0.260
et-0.251
rated-0.250
Token He
Token ID679
Feature activation+1.78e+00

Pos logit contributions
rated+0.027
et+0.026
 around+0.026
cy+0.026
ening+0.024
Neg logit contributions
His-0.029
ves-0.028
 backup-0.027
vern-0.026
 mercy-0.026
Token brave
Token ID14802
Feature activation-6.15e-01

Pos logit contributions
ves+0.176
vern+0.170
ades+0.157
keys+0.151
 backup+0.150
Neg logit contributions
 around-0.211
 air-0.199
cy-0.198
rated-0.193
et-0.191
Token and
Token ID290
Feature activation+1.63e+00

Pos logit contributions
vern+0.035
ves+0.035
 backup+0.032
 mercy+0.032
ades+0.031
Neg logit contributions
cy-0.029
rated-0.029
|-0.028
 around-0.028
 air-0.027
Token comfortable
Token ID6792
Feature activation+1.87e+00

Pos logit contributions
 around+0.095
 air+0.086
rated+0.083
cy+0.083
 down+0.081
Neg logit contributions
ves-0.090
vern-0.088
ades-0.086
keys-0.078
 backup-0.077
Token even
Token ID772
Feature activation-3.04e+00

Pos logit contributions
cy+0.088
 around+0.086
rated+0.086
 air+0.085
et+0.082
Neg logit contributions
ves-0.110
vern-0.108
ades-0.099
 mercy-0.098
 backup-0.097
Token when
Token ID618
Feature activation-3.03e+00

Pos logit contributions
ves+0.140
vern+0.137
 backup+0.121
 mercy+0.121
keys+0.121
Neg logit contributions
 around-0.181
cy-0.179
 air-0.178
rated-0.174
et-0.171
Token her
Token ID607
Feature activation-1.61e+00

Pos logit contributions
ves+0.130
vern+0.128
ades+0.115
 backup+0.110
keys+0.109
Neg logit contributions
 around-0.201
 air-0.192
cy-0.191
rated-0.187
et-0.183
Token dream
Token ID4320
Feature activation-1.28e+00

Pos logit contributions
ves+0.093
vern+0.091
ades+0.084
 backup+0.082
keys+0.081
Neg logit contributions
 around-0.083
cy-0.079
 air-0.078
rated-0.077
et-0.075
Token was
Token ID373
Feature activation-1.13e+00

Pos logit contributions
ves+0.072
vern+0.068
ades+0.062
keys+0.060
 backup+0.060
Neg logit contributions
cy-0.068
 around-0.067
rated-0.064
 air-0.064
et-0.062
Token far
Token ID1290
Feature activation+2.73e+00

Pos logit contributions
ves+0.067
vern+0.066
ades+0.060
 backup+0.059
keys+0.059
Neg logit contributions
 around-0.055
cy-0.054
 air-0.052
rated-0.051
et-0.050
Token away
Token ID1497
Feature activation+5.90e+00

Pos logit contributions
cy+0.104
|+0.102
amp+0.095
 air+0.093
rated+0.093
Neg logit contributions
vern-0.172
ves-0.167
 backup-0.165
 mercy-0.163
 forgiveness-0.155
Token.
Token ID13
Feature activation+2.73e-01

Pos logit contributions
 around+0.286
cy+0.277
 air+0.274
rated+0.269
et+0.263
Neg logit contributions
ves-0.349
vern-0.343
ades-0.316
 backup-0.308
keys-0.307
Token hair
Token ID4190
Feature activation+2.20e+00

Pos logit contributions
ves+0.126
vern+0.123
ades+0.114
keys+0.108
 backup+0.106
Neg logit contributions
 around-0.161
 air-0.156
cy-0.154
et-0.147
rated-0.145
Token to
Token ID284
Feature activation-2.81e+00

Pos logit contributions
 around+0.108
cy+0.101
 air+0.101
rated+0.098
et+0.097
Neg logit contributions
ves-0.134
vern-0.132
ades-0.122
 backup-0.120
keys-0.119
Token look
Token ID804
Feature activation+2.47e+00

Pos logit contributions
ves+0.157
vern+0.155
ades+0.144
keys+0.139
 backup+0.138
Neg logit contributions
 around-0.150
 air-0.142
cy-0.139
rated-0.136
et-0.136
Token pretty
Token ID2495
Feature activation+2.24e+00

Pos logit contributions
cy+0.141
 air+0.137
 around+0.137
rated+0.134
|+0.133
Neg logit contributions
ves-0.121
vern-0.120
ades-0.109
 backup-0.106
keys-0.104
Token and
Token ID290
Feature activation+1.80e+00

Pos logit contributions
 around+0.104
cy+0.103
 air+0.101
rated+0.101
|+0.097
Neg logit contributions
ves-0.132
vern-0.131
ades-0.122
keys-0.118
 mercy-0.116
Token different
Token ID1180
Feature activation-1.19e+00

Pos logit contributions
 around+0.100
cy+0.099
 air+0.095
rated+0.095
et+0.094
Neg logit contributions
ves-0.092
vern-0.090
ades-0.080
 backup-0.080
 mercy-0.079
Token today
Token ID1909
Feature activation+8.69e-01

Pos logit contributions
ves+0.068
vern+0.067
ades+0.062
keys+0.060
 mercy+0.060
Neg logit contributions
 around-0.058
cy-0.057
rated-0.055
 air-0.055
|-0.054
Token."
Token ID526
Feature activation+3.30e+00

Pos logit contributions
 around+0.042
cy+0.041
rated+0.040
 air+0.040
et+0.039
Neg logit contributions
ves-0.051
vern-0.050
ades-0.046
keys-0.045
 backup-0.045
Token The
Token ID383
Feature activation+8.88e+00

Pos logit contributions
 around+0.151
rated+0.146
cy+0.144
 air+0.143
et+0.139
Neg logit contributions
ves-0.205
vern-0.199
ades-0.185
 backup-0.182
keys-0.181
Token ha
Token ID387
Feature activation-4.85e+00

Pos logit contributions
 air+0.540
 around+0.525
cy+0.498
et+0.469
 morning+0.465
Neg logit contributions
ves-0.432
vern-0.431
ades-0.406
keys-0.377
 backup-0.345
Tokenird
Token ID1447
Feature activation-5.30e+00

Pos logit contributions
vern+0.236
ves+0.231
ades+0.211
 backup+0.210
 mercy+0.210
Neg logit contributions
 around-0.286
cy-0.283
 air-0.271
et-0.267
rated-0.262
Token She
Token ID1375
Feature activation+5.13e+00

Pos logit contributions
rated+0.017
et+0.016
ening+0.015
cy+0.015
 around+0.015
Neg logit contributions
ves-0.018
vern-0.017
Her-0.017
ades-0.017
 backup-0.017
Token did
Token ID750
Feature activation+7.22e+00

Pos logit contributions
 around+0.248
cy+0.234
 air+0.233
et+0.223
rated+0.222
Neg logit contributions
vern-0.318
ves-0.310
ades-0.290
 backup-0.285
keys-0.278
Token not
Token ID407
Feature activation-8.90e+00

Pos logit contributions
 around+0.526
 down+0.472
 air+0.471
et+0.464
rated+0.442
Neg logit contributions
vern-0.268
ades-0.264
ves-0.246
keys-0.243
 backup-0.235
Token see
Token ID766
Feature activation+1.69e+00

Pos logit contributions
ves+0.576
vern+0.575
 backup+0.526
keys+0.525
 mercy+0.521
Neg logit contributions
 around-0.367
cy-0.359
 air-0.356
rated-0.345
et-0.329
Token the
Token ID262
Feature activation+4.01e+00

Pos logit contributions
rated+0.096
cy+0.094
 around+0.091
|+0.089
 air+0.088
Neg logit contributions
ves-0.087
vern-0.083
 backup-0.078
 forgiveness-0.076
 mercy-0.076
Token small
Token ID1402
Feature activation-2.88e+00

Pos logit contributions
 around+0.247
cy+0.242
rated+0.236
|+0.234
 air+0.232
Neg logit contributions
ves-0.187
vern-0.179
ades-0.162
keys-0.157
 backup-0.157
Token stick
Token ID4859
Feature activation-2.98e+00

Pos logit contributions
ves+0.126
vern+0.111
keys+0.105
ades+0.103
 mercy+0.100
Neg logit contributions
|-0.181
 around-0.179
rated-0.174
cy-0.172
et-0.163
Token on
Token ID319
Feature activation+6.99e+00

Pos logit contributions
ves+0.174
vern+0.163
ades+0.152
keys+0.150
 backup+0.147
Neg logit contributions
cy-0.148
rated-0.144
 around-0.142
 air-0.141
|-0.138
Token the
Token ID262
Feature activation+3.98e+00

Pos logit contributions
rated+0.372
cy+0.370
 around+0.370
|+0.345
 air+0.342
Neg logit contributions
ves-0.388
vern-0.362
ades-0.333
 backup-0.332
keys-0.327
Token leaf
Token ID12835
Feature activation+1.96e+00

Pos logit contributions
cy+0.186
|+0.176
 around+0.176
rated+0.174
ained+0.162
Neg logit contributions
ves-0.248
vern-0.238
keys-0.218
 backup-0.216
ades-0.215
Token.
Token ID13
Feature activation+3.24e-01

Pos logit contributions
 around+0.097
cy+0.097
rated+0.095
 air+0.093
|+0.090
Neg logit contributions
ves-0.114
vern-0.108
ades-0.100
keys-0.099
 mercy-0.096
Token is
Token ID318
Feature activation+9.65e-01

Pos logit contributions
 around+0.056
cy+0.055
rated+0.054
 air+0.052
et+0.051
Neg logit contributions
ves-0.084
vern-0.082
ades-0.076
 backup-0.076
 mercy-0.075
Token sorry
Token ID7926
Feature activation-2.68e+00

Pos logit contributions
 around+0.050
 air+0.047
cy+0.045
et+0.044
rated+0.044
Neg logit contributions
ves-0.057
vern-0.056
ades-0.053
keys-0.051
 backup-0.050
Token.
Token ID13
Feature activation+2.64e-01

Pos logit contributions
ves+0.177
vern+0.175
ades+0.164
keys+0.160
 backup+0.159
Neg logit contributions
 around-0.121
 air-0.111
cy-0.107
rated-0.104
et-0.102
Token He
Token ID679
Feature activation+1.30e+00

Pos logit contributions
 around+0.012
cy+0.011
rated+0.011
 air+0.011
et+0.011
Neg logit contributions
ves-0.017
vern-0.017
ades-0.015
 backup-0.015
 mercy-0.015
Token wishes
Token ID12802
Feature activation-3.09e+00

Pos logit contributions
 around+0.057
cy+0.054
 air+0.053
rated+0.052
et+0.051
Neg logit contributions
ves-0.085
vern-0.083
ades-0.077
 backup-0.076
keys-0.075
Token they
Token ID484
Feature activation-1.03e+01

Pos logit contributions
vern+0.134
ves+0.126
ades+0.119
keys+0.116
 backup+0.108
Neg logit contributions
 around-0.214
 air-0.201
et-0.193
cy-0.191
 down-0.189
Token never
Token ID1239
Feature activation-5.57e-01

Pos logit contributions
ves+0.682
vern+0.665
ades+0.615
keys+0.610
 mercy+0.607
Neg logit contributions
 around-0.427
 air-0.411
cy-0.409
rated-0.405
et-0.395
Token found
Token ID1043
Feature activation-2.71e-01

Pos logit contributions
ves+0.037
vern+0.036
ades+0.034
keys+0.032
 backup+0.031
Neg logit contributions
 around-0.026
cy-0.024
 air-0.024
rated-0.023
 down-0.022
Token the
Token ID262
Feature activation+3.94e+00

Pos logit contributions
ves+0.015
vern+0.014
ades+0.013
keys+0.013
 backup+0.013
Neg logit contributions
 around-0.015
 air-0.015
cy-0.014
et-0.014
rated-0.014
Token book
Token ID1492
Feature activation-1.75e+00

Pos logit contributions
 around+0.225
rated+0.217
cy+0.217
 air+0.210
et+0.206
Neg logit contributions
ves-0.201
vern-0.197
ades-0.180
 backup-0.179
keys-0.175
Token.
Token ID13
Feature activation+2.69e-01

Pos logit contributions
ves+0.108
vern+0.107
ades+0.099
 backup+0.096
keys+0.096
Neg logit contributions
 around-0.084
cy-0.078
 air-0.078
rated-0.076
et-0.074
Token Mia
Token ID32189
Feature activation+4.66e+00

Pos logit contributions
 around+0.045
 air+0.044
cy+0.040
 down+0.034
 night+0.034
Neg logit contributions
vern-0.091
ves-0.089
keys-0.083
ades-0.082
 mercy-0.079
Token said
Token ID531
Feature activation-1.25e+00

Pos logit contributions
 around+0.264
 air+0.250
cy+0.248
rated+0.237
et+0.237
Neg logit contributions
ves-0.250
vern-0.250
ades-0.226
 backup-0.226
 mercy-0.217
Token.
Token ID13
Feature activation+8.48e-02

Pos logit contributions
ves+0.086
vern+0.084
ades+0.080
 backup+0.078
keys+0.077
Neg logit contributions
 around-0.054
cy-0.047
 air-0.047
 down-0.045
rated-0.044
Token
Token ID198
Feature activation-8.78e-01

Pos logit contributions
 around+0.004
 air+0.004
cy+0.003
 down+0.003
rated+0.003
Neg logit contributions
ves-0.006
vern-0.005
ades-0.005
keys-0.005
 mercy-0.005
Token
Token ID198
Feature activation-8.83e-01

Pos logit contributions
ves+0.059
vern+0.058
keys+0.056
 mercy+0.056
 backup+0.056
Neg logit contributions
 around-0.035
 air-0.032
cy-0.030
 down-0.028
|-0.028
TokenThey
Token ID2990
Feature activation-1.04e+01

Pos logit contributions
ves+0.042
 mercy+0.041
vern+0.041
 forgiveness+0.040
 backup+0.039
Neg logit contributions
 around-0.049
 air-0.049
cy-0.047
amp-0.044
ny-0.043
Token ate
Token ID15063
Feature activation+1.34e-01

Pos logit contributions
ves+0.632
vern+0.625
ades+0.574
 backup+0.561
keys+0.556
Neg logit contributions
 around-0.510
cy-0.486
 air-0.481
rated-0.466
et-0.459
Token all
Token ID477
Feature activation+1.61e+00

Pos logit contributions
 around+0.007
rated+0.007
cy+0.007
 air+0.007
et+0.007
Neg logit contributions
ves-0.007
vern-0.007
ades-0.006
 backup-0.006
 mercy-0.006
Token the
Token ID262
Feature activation+3.85e+00

Pos logit contributions
rated+0.087
 around+0.082
|+0.080
cy+0.079
et+0.079
Neg logit contributions
ves-0.082
vern-0.078
ades-0.073
 mercy-0.070
 backup-0.070
Token corn
Token ID11676
Feature activation-5.24e+00

Pos logit contributions
 around+0.267
cy+0.257
 air+0.257
rated+0.253
et+0.248
Neg logit contributions
ves-0.153
vern-0.150
ades-0.132
 backup-0.128
keys-0.126
Token and
Token ID290
Feature activation+1.29e+00

Pos logit contributions
ves+0.324
vern+0.314
ades+0.293
keys+0.287
 backup+0.282
Neg logit contributions
 around-0.240
rated-0.230
cy-0.230
 air-0.228
et-0.218
Token Tom
Token ID4186
Feature activation+5.83e+00

Pos logit contributions
 around+0.074
 air+0.069
cy+0.069
 down+0.069
 night+0.065
Neg logit contributions
ves-0.082
vern-0.079
ades-0.075
keys-0.072
 mercy-0.068
Token asked
Token ID1965
Feature activation-1.18e+00

Pos logit contributions
 around+0.315
cy+0.300
 air+0.299
rated+0.293
et+0.286
Neg logit contributions
ves-0.321
vern-0.315
ades-0.289
 backup-0.282
keys-0.279
Token.
Token ID13
Feature activation+8.62e-02

Pos logit contributions
ves+0.081
vern+0.081
keys+0.075
ades+0.074
 backup+0.073
Neg logit contributions
 around-0.051
cy-0.046
 air-0.044
 down-0.043
et-0.041
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
 around+0.003
 down+0.002
 air+0.002
cy+0.002
 Today+0.002
Neg logit contributions
vern-0.007
ves-0.007
keys-0.006
 mercy-0.006
ades-0.006
Token
Token ID198
Feature activation-1.05e+00

Pos logit contributions
keys+0.073
ves+0.073
vern+0.072
 mercy+0.070
sters+0.069
Neg logit contributions
 around-0.039
cy-0.033
 air-0.031
 down-0.030
|-0.029
Token"
Token ID1
Feature activation-9.78e+00

Pos logit contributions
 mercy+0.060
ves+0.059
keys+0.059
 forgiveness+0.059
 fries+0.058
Neg logit contributions
 around-0.047
cy-0.046
ny-0.045
 down-0.041
 over-0.039
TokenOf
Token ID5189
Feature activation-2.76e+00

Pos logit contributions
ves+0.643
vern+0.611
 mercy+0.574
ades+0.573
 instincts+0.560
Neg logit contributions
cy-0.444
 around-0.440
 air-0.376
ny-0.374
 down-0.355
Token course
Token ID1781
Feature activation-1.14e+00

Pos logit contributions
ves+0.178
vern+0.172
ades+0.164
keys+0.159
 backup+0.155
Neg logit contributions
 around-0.123
 air-0.122
cy-0.121
et-0.115
rated-0.111
Token,"
Token ID553
Feature activation+6.67e-01

Pos logit contributions
ves+0.076
vern+0.075
ades+0.072
 backup+0.068
keys+0.066
Neg logit contributions
 around-0.051
cy-0.046
 air-0.046
 down-0.042
rated-0.042
Token dad
Token ID9955
Feature activation-7.78e+00

Pos logit contributions
 air+0.032
cy+0.032
 around+0.031
 wind+0.029
 night+0.029
Neg logit contributions
ves-0.043
vern-0.041
keys-0.039
ades-0.039
lor-0.036
Token said
Token ID531
Feature activation-1.44e+00

Pos logit contributions
vern+0.510
ves+0.495
 backup+0.465
ades+0.451
 mercy+0.448
Neg logit contributions
 around-0.375
cy-0.345
 air-0.334
et-0.324
ny-0.308
Token too
Token ID1165
Feature activation+1.59e+00

Pos logit contributions
 around+0.152
 air+0.137
cy+0.136
 down+0.128
et+0.127
Neg logit contributions
ves-0.162
vern-0.158
ades-0.146
keys-0.143
 backup-0.140
Token.
Token ID13
Feature activation+4.84e-01

Pos logit contributions
 around+0.079
cy+0.078
 air+0.077
rated+0.076
et+0.075
Neg logit contributions
ves-0.090
vern-0.089
keys-0.081
ades-0.080
 backup-0.079
Token From
Token ID3574
Feature activation+1.55e+00

Pos logit contributions
rated+0.024
et+0.022
 around+0.022
ening+0.020
 air+0.020
Neg logit contributions
ves-0.027
vern-0.026
His-0.026
 backup-0.025
 forgiveness-0.024
Token then
Token ID788
Feature activation+1.61e+00

Pos logit contributions
 around+0.102
rated+0.102
cy+0.101
 air+0.100
et+0.097
Neg logit contributions
ves-0.063
vern-0.060
ades-0.054
keys-0.052
 backup-0.052
Token on
Token ID319
Feature activation+7.32e+00

Pos logit contributions
rated+0.077
cy+0.075
 around+0.072
 air+0.071
et+0.070
Neg logit contributions
ves-0.100
vern-0.091
 backup-0.084
ades-0.084
keys-0.081
Token they
Token ID484
Feature activation-9.75e+00

Pos logit contributions
 around+0.349
 air+0.325
cy+0.325
rated+0.308
et+0.306
Neg logit contributions
vern-0.454
ves-0.450
ades-0.419
 backup-0.408
keys-0.406
Token were
Token ID547
Feature activation-6.04e-01

Pos logit contributions
ves+0.492
vern+0.474
 backup+0.438
keys+0.423
ades+0.414
Neg logit contributions
rated-0.538
 air-0.501
ening-0.496
 around-0.491
ained-0.455
Token a
Token ID257
Feature activation-4.34e+00

Pos logit contributions
ves+0.035
vern+0.034
ades+0.031
 backup+0.031
keys+0.030
Neg logit contributions
 around-0.031
cy-0.030
 air-0.029
rated-0.029
et-0.028
Token happy
Token ID3772
Feature activation+2.70e+00

Pos logit contributions
ves+0.252
vern+0.236
ades+0.226
keys+0.212
 mercy+0.211
Neg logit contributions
cy-0.232
 around-0.230
 air-0.219
et-0.202
 night-0.202
Token family
Token ID1641
Feature activation-4.83e+00

Pos logit contributions
 around+0.139
cy+0.132
 air+0.131
rated+0.127
et+0.124
Neg logit contributions
ves-0.158
vern-0.156
ades-0.144
keys-0.140
 backup-0.139
Token.
Token ID13
Feature activation+4.95e-01

Pos logit contributions
ves+0.261
vern+0.257
keys+0.230
 backup+0.229
 forgiveness+0.226
Neg logit contributions
rated-0.258
 air-0.239
 around-0.234
cy-0.232
|-0.225
Token Sara
Token ID24799
Feature activation+3.41e+00

Pos logit contributions
 air+0.040
 around+0.040
 down+0.036
cy+0.035
 morning+0.034
Neg logit contributions
vern-0.050
ves-0.048
ades-0.046
keys-0.044
 backup-0.042
Token says
Token ID1139
Feature activation+6.08e-01

Pos logit contributions
 around+0.172
rated+0.169
cy+0.168
 air+0.161
|+0.160
Neg logit contributions
ves-0.191
vern-0.187
ades-0.175
keys-0.167
 mercy-0.166
Token.
Token ID13
Feature activation+3.31e-01

Pos logit contributions
 around+0.026
 air+0.022
 down+0.021
cy+0.021
et+0.020
Neg logit contributions
ves-0.043
vern-0.042
ades-0.040
 backup-0.039
keys-0.039
Token
Token ID198
Feature activation-1.01e+00

Pos logit contributions
 around+0.014
 air+0.013
cy+0.012
 down+0.011
rated+0.011
Neg logit contributions
ves-0.023
vern-0.023
ades-0.021
keys-0.021
 mercy-0.021
Token
Token ID198
Feature activation-1.01e+00

Pos logit contributions
ves+0.066
vern+0.065
keys+0.062
 mercy+0.062
 backup+0.062
Neg logit contributions
 around-0.042
 air-0.038
cy-0.038
 down-0.034
|-0.033
Token"
Token ID1
Feature activation-9.73e+00

Pos logit contributions
ves+0.049
 mercy+0.047
vern+0.045
 backup+0.045
 forgiveness+0.044
Neg logit contributions
cy-0.058
 around-0.057
 air-0.055
amp-0.051
ny-0.051
TokenThank
Token ID10449
Feature activation-2.40e+00

Pos logit contributions
ves+0.674
vern+0.653
ades+0.607
 mercy+0.604
keys+0.601
Neg logit contributions
cy-0.404
 air-0.396
 around-0.386
et-0.332
rated-0.330
Token you
Token ID345
Feature activation-3.42e-01

Pos logit contributions
ves+0.139
vern+0.137
ades+0.129
 backup+0.124
keys+0.119
Neg logit contributions
 around-0.125
 air-0.119
cy-0.116
et-0.106
 down-0.104
Token,
Token ID11
Feature activation-1.19e+00

Pos logit contributions
ves+0.022
vern+0.022
ades+0.021
keys+0.020
 backup+0.020
Neg logit contributions
 around-0.015
 air-0.014
cy-0.014
rated-0.013
et-0.013
Token Sara
Token ID24799
Feature activation+3.37e+00

Pos logit contributions
ves+0.064
vern+0.061
ades+0.057
 backup+0.054
keys+0.053
Neg logit contributions
 air-0.068
 around-0.068
cy-0.064
et-0.062
rated-0.061
Token.
Token ID13
Feature activation+2.63e-01

Pos logit contributions
|+0.189
cy+0.186
rated+0.186
 around+0.185
 air+0.176
Neg logit contributions
vern-0.165
ves-0.164
 mercy-0.147
keys-0.140
 forgiveness-0.140