TOP ACTIVATIONS
MAX = 10.100

that said " RE VERS E ". L ila and Tom
mum to make things look long and bright ! <|endoftext|> Once
" RE VERS E , huh ? That 's
ice cream taste even y umm ier ! And every time
to make food look y umm ier than before . She
to make it taste y ummy . Lily helped her mom
could see lots of av oc ados that the supplier had
her doll was twelve inches long , her car was six
made her food taste y ummy . One day , her
a sign that said " E lev ator to the Moon
placed it onto the wheel bar row . John
couldn 't find any av oc ados . Finally , she
I will buy more av oc ados tomorrow . You can
learn more about rh in oc er oses and respect them
that it produced more av oc ados than ever before .
net on the rh in oc eros . They put the
" They all look y ummy . Can I have a
This block is ten inches long . This block is eight
ist ening golden l ily pad . The frog hopped up
a funny face . " E w , this is sour

MIN ACTIVATIONS
MIN = -8.875

After the concert , Lily 's mom said
concert . The concert was amazing and Emma sang
. He asked them what was happening , and
!" When the concert started , Lily saw a
stage !" The music stopped . The lights flashed
was shocked . She asked them what happened . They told
know why . He asked them what was wrong , but
One day , she asked them if they wanted to go
Hello , Lily ," a voice said . Lily turned around
. Jimmy asked them for help and they were
One day , she asked them if they could go on
The little girl asked them where the print had come
Lily just smiled and asked them politely if they could change
join them . He asked them if he could but they
an idea . He asked them if he could join and
! So , she asked them to introduce her to the
One day , she asked them why they couldn 't get
a way . She asked them , " What if I
be important ," one of them said .
so disappointed . She asked them why they wouldn 't buy

INTERVAL 5.357 - 10.100
CONTAINS 0.165%

that he dropped everything he had bought and ran away !
happening ! She watched as Mom my pulled a truck from
around the tree all day long . One sunny
. They sn uggle with Mom on the couch . Mom
, looking for something y ummy to eat . He saw

INTERVAL 0.613 - 5.357
CONTAINS 33.472%

. The daddy grabbed a paint brush and a
for all the fruits and vegetables in the town . The
was making the noise , but he was scared . He
never forgot the man who saved her from being lost in
to play with her toys , but her favorite was a

INTERVAL -4.131 - 0.613
CONTAINS 65.532%

night and she never stopped feeling happy .
the cool water and saw the sun gl int ing off
more careful when playing dress - up . <|endoftext|> Once upon
she needed her . Mitt ens ' owner knew that Mitt
time , a playful puppy named Max was playing in the

INTERVAL -8.875 - -4.131
CONTAINS 0.831%

scary dog came running towards them . Lily was scared and
agreed and the two of them set off on a journey
Today , Tom goes to visit Mia at her house .
berries . One day while out picking r asp berries she
Luckily , soon a grown up came to help . She
Token that
Token ID326
Feature activation+1.63e+00

Pos logit contributions
 goodbye+0.072
 jog+0.072
 bully+0.068
guard+0.068
 youth+0.067
Neg logit contributions
mmm-0.100
Finally-0.090
ions-0.086
mmmm-0.082
ra-0.080
Token said
Token ID531
Feature activation+1.59e+00

Pos logit contributions
mmm+0.076
Finally+0.069
ions+0.068
mmmm+0.064
ra+0.064
Neg logit contributions
 goodbye-0.048
 jog-0.045
 youth-0.043
 bully-0.043
 stranger-0.043
Token "
Token ID366
Feature activation+2.92e+00

Pos logit contributions
mmm+0.080
Finally+0.072
ions+0.069
mmmm+0.068
ra+0.064
Neg logit contributions
 jog-0.043
guard-0.041
 goodbye-0.041
 stranger-0.040
 bully-0.040
TokenRE
Token ID2200
Feature activation+1.57e+00

Pos logit contributions
mmm+0.126
Finally+0.112
ions+0.104
mmmm+0.103
icer+0.100
Neg logit contributions
 jog-0.098
guard-0.097
 goodbye-0.097
 stranger-0.094
 bully-0.093
TokenVERS
Token ID28884
Feature activation-4.00e-01

Pos logit contributions
mmm+0.070
Finally+0.065
ions+0.062
mmmm+0.059
ousy+0.056
Neg logit contributions
 goodbye-0.049
 jog-0.048
 bully-0.047
 wealthy-0.045
 aut-0.044
TokenE
Token ID36
Feature activation+1.01e+01

Pos logit contributions
guard+0.017
 bully+0.017
 stranger+0.016
 en+0.016
 jog+0.016
Neg logit contributions
mmm-0.015
Finally-0.011
mmmm-0.011
ions-0.011
mm-0.010
Token".
Token ID1911
Feature activation-1.26e+00

Pos logit contributions
Finally+0.352
mmm+0.350
Eventually+0.289
ions+0.289
mmmm+0.281
Neg logit contributions
 goodbye-0.396
guard-0.395
 stranger-0.380
 jog-0.376
 bully-0.375
Token L
Token ID406
Feature activation+2.45e+00

Pos logit contributions
 goodbye+0.031
 jog+0.029
guard+0.028
 stranger+0.027
 bully+0.027
Neg logit contributions
mmm-0.068
Finally-0.063
mmmm-0.059
ions-0.058
icer-0.058
Tokenila
Token ID10102
Feature activation+1.00e+00

Pos logit contributions
mmm+0.097
Finally+0.086
ions+0.079
mmmm+0.079
icer+0.076
Neg logit contributions
 goodbye-0.095
 jog-0.092
 stranger-0.090
guard-0.090
 bully-0.088
Token and
Token ID290
Feature activation-2.67e+00

Pos logit contributions
mmm+0.041
Finally+0.038
ra+0.036
mmmm+0.033
ions+0.033
Neg logit contributions
 goodbye-0.035
 jog-0.033
guard-0.033
 stranger-0.032
 aut-0.032
Token Tom
Token ID4186
Feature activation+1.16e+00

Pos logit contributions
guard+0.120
 goodbye+0.111
 stranger+0.109
 wealthy+0.107
 bully+0.104
Neg logit contributions
mmm-0.085
ra-0.069
ions-0.068
mmmm-0.061
els-0.061
Token mum
Token ID25682
Feature activation+2.02e+00

Pos logit contributions
 goodbye+0.055
guard+0.053
 jog+0.052
 stranger+0.051
 bully+0.051
Neg logit contributions
mmm-0.090
Finally-0.082
ions-0.076
mmmm-0.075
ra-0.073
Token to
Token ID284
Feature activation-1.14e+00

Pos logit contributions
mmm+0.099
Finally+0.090
ions+0.085
mmmm+0.083
icer+0.080
Neg logit contributions
 goodbye-0.056
guard-0.053
 stranger-0.053
 bully-0.053
 jog-0.053
Token make
Token ID787
Feature activation-7.64e-01

Pos logit contributions
 goodbye+0.029
 jog+0.028
guard+0.027
 stranger+0.027
 bully+0.026
Neg logit contributions
mmm-0.059
Finally-0.055
mmmm-0.051
ions-0.051
icer-0.050
Token things
Token ID1243
Feature activation-2.13e+00

Pos logit contributions
 new+0.018
 goodbye+0.018
 jog+0.017
 wealthy+0.017
 youth+0.017
Neg logit contributions
mmm-0.041
Finally-0.038
mmmm-0.036
icer-0.035
ions-0.035
Token look
Token ID804
Feature activation-3.11e-01

Pos logit contributions
 goodbye+0.067
 bully+0.065
 stranger+0.064
 jog+0.063
 seal+0.063
Neg logit contributions
mmm-0.096
Finally-0.084
ions-0.083
mmmm-0.078
ra-0.072
Token long
Token ID890
Feature activation+9.27e+00

Pos logit contributions
 goodbye+0.008
 jog+0.008
guard+0.007
 bully+0.007
 stranger+0.007
Neg logit contributions
mmm-0.016
Finally-0.015
mmmm-0.014
ions-0.014
icer-0.013
Token and
Token ID290
Feature activation+1.11e+00

Pos logit contributions
mmm+0.508
Finally+0.477
mmmm+0.448
icer+0.435
ions+0.425
Neg logit contributions
 goodbye-0.229
 new-0.202
 jog-0.200
guard-0.194
 wealthy-0.189
Token bright
Token ID6016
Feature activation+3.26e+00

Pos logit contributions
mmm+0.061
Finally+0.057
mmmm+0.053
ions+0.053
icer+0.051
Neg logit contributions
 goodbye-0.024
 jog-0.023
guard-0.023
 stranger-0.022
 bully-0.022
Token!
Token ID0
Feature activation-8.27e-01

Pos logit contributions
mmm+0.171
Finally+0.160
mmmm+0.147
icer+0.142
ions+0.139
Neg logit contributions
 goodbye-0.092
 new-0.084
 jog-0.082
 stranger-0.081
guard-0.081
Token<|endoftext|>
Token ID50256
Feature activation+3.68e+00

Pos logit contributions
 goodbye+0.019
 jog+0.018
guard+0.017
 stranger+0.017
 bully+0.016
Neg logit contributions
mmm-0.045
Finally-0.042
ions-0.040
mmmm-0.039
icer-0.039
TokenOnce
Token ID7454
Feature activation+9.43e-01

Pos logit contributions
mmm+0.191
Finally+0.174
mmmm+0.163
ions+0.161
icer+0.157
Neg logit contributions
 goodbye-0.094
 jog-0.092
guard-0.089
 stranger-0.088
 bully-0.085
Token
Token ID198
Feature activation+1.14e+00

Pos logit contributions
mmm+0.049
Finally+0.045
mmmm+0.042
ions+0.042
icer+0.041
Neg logit contributions
 goodbye-0.021
 jog-0.020
guard-0.019
 stranger-0.019
 bully-0.019
Token
Token ID198
Feature activation+3.40e-01

Pos logit contributions
mmm+0.070
Finally+0.063
ions+0.063
mmmm+0.062
icer+0.062
Neg logit contributions
 goodbye-0.017
 new-0.017
 jog-0.017
guard-0.016
 en-0.015
Token"
Token ID1
Feature activation+1.17e+00

Pos logit contributions
mmm+0.014
ions+0.012
mmmm+0.012
icer+0.011
umm+0.011
Neg logit contributions
 jog-0.012
guard-0.012
 goodbye-0.012
 en-0.012
 wealthy-0.012
TokenRE
Token ID2200
Feature activation+4.02e-01

Pos logit contributions
mmm+0.036
Finally+0.031
mmmm+0.028
ions+0.027
icer+0.026
Neg logit contributions
 goodbye-0.056
 jog-0.054
guard-0.053
 stranger-0.053
 bully-0.052
TokenVERS
Token ID28884
Feature activation-1.22e+00

Pos logit contributions
mmm+0.017
Finally+0.016
ions+0.015
mmmm+0.014
Eventually+0.013
Neg logit contributions
 goodbye-0.013
 bully-0.013
 jog-0.013
 en-0.013
 wealthy-0.013
TokenE
Token ID36
Feature activation+8.99e+00

Pos logit contributions
guard+0.052
 bully+0.050
 en+0.049
 stranger+0.049
 jog+0.048
Neg logit contributions
mmm-0.046
Finally-0.036
mmmm-0.036
ions-0.033
 hours-0.031
Token,
Token ID11
Feature activation+2.61e+00

Pos logit contributions
mmm+0.418
Finally+0.414
ions+0.369
Eventually+0.359
mmmm+0.357
Neg logit contributions
guard-0.260
 goodbye-0.255
 stranger-0.243
 jog-0.239
 bully-0.237
Token huh
Token ID24926
Feature activation+1.23e+00

Pos logit contributions
mmm+0.129
Finally+0.120
ions+0.111
mmmm+0.110
icer+0.107
Neg logit contributions
 goodbye-0.074
 jog-0.070
guard-0.069
 stranger-0.069
 bully-0.067
Token?
Token ID30
Feature activation-6.50e-01

Pos logit contributions
Finally+0.061
mmm+0.059
Eventually+0.054
 hours+0.054
ions+0.051
Neg logit contributions
 new-0.035
guard-0.035
 stranger-0.032
 friendly-0.031
 goodbye-0.031
Token That
Token ID1320
Feature activation+2.62e-01

Pos logit contributions
 goodbye+0.021
 jog+0.020
guard+0.020
 stranger+0.019
 bully+0.019
Neg logit contributions
mmm-0.030
Finally-0.027
mmmm-0.025
ions-0.025
icer-0.024
Token's
Token ID338
Feature activation-1.72e+00

Pos logit contributions
mmm+0.015
Finally+0.014
ions+0.013
mmmm+0.013
icer+0.013
Neg logit contributions
 goodbye-0.005
 jog-0.005
guard-0.005
 stranger-0.005
 bully-0.005
Token ice
Token ID4771
Feature activation+2.27e+00

Pos logit contributions
mmm+0.028
Finally+0.025
mmmm+0.024
icer+0.024
ions+0.024
Neg logit contributions
guard-0.014
 goodbye-0.013
 stranger-0.013
 jog-0.013
 bully-0.012
Token cream
Token ID8566
Feature activation+1.42e+00

Pos logit contributions
mmm+0.120
Finally+0.110
mmmm+0.103
ions+0.103
icer+0.100
Neg logit contributions
 goodbye-0.057
 jog-0.055
guard-0.053
 stranger-0.052
 bully-0.052
Token taste
Token ID6938
Feature activation+3.10e+00

Pos logit contributions
mmm+0.071
Finally+0.067
ions+0.063
mmmm+0.062
icer+0.059
Neg logit contributions
 goodbye-0.039
 jog-0.037
 new-0.037
guard-0.036
 stranger-0.035
Token even
Token ID772
Feature activation+5.56e+00

Pos logit contributions
mmm+0.149
Finally+0.138
ions+0.128
mmmm+0.127
icer+0.125
Neg logit contributions
 goodbye-0.091
 jog-0.087
guard-0.085
 stranger-0.084
 new-0.083
Token y
Token ID331
Feature activation+7.08e+00

Pos logit contributions
mmm+0.266
Finally+0.243
mmmm+0.225
ions+0.222
icer+0.217
Neg logit contributions
 goodbye-0.163
 jog-0.158
 bully-0.152
guard-0.151
 stranger-0.151
Tokenumm
Token ID13929
Feature activation+8.71e+00

Pos logit contributions
Finally+0.233
mmm+0.199
Eventually+0.191
 nine+0.171
ions+0.166
Neg logit contributions
 shrimp-0.291
 new-0.288
guard-0.287
 youth-0.286
 goodbye-0.282
Tokenier
Token ID959
Feature activation+4.33e+00

Pos logit contributions
mmm+0.360
Finally+0.359
Eventually+0.301
icer+0.297
mmmm+0.296
Neg logit contributions
guard-0.294
 goodbye-0.291
 stranger-0.270
 new-0.266
 jog-0.262
Token!
Token ID0
Feature activation+4.22e-01

Pos logit contributions
mmm+0.209
Finally+0.200
mmmm+0.179
icer+0.179
ions+0.178
Neg logit contributions
 goodbye-0.126
guard-0.120
 stranger-0.119
 jog-0.118
 new-0.116
Token And
Token ID843
Feature activation+6.24e-01

Pos logit contributions
mmm+0.025
Finally+0.024
 centimeters+0.023
icer+0.022
ra+0.022
Neg logit contributions
 goodbye-0.007
 jog-0.006
 His-0.006
 new-0.006
 youth-0.006
Token every
Token ID790
Feature activation-7.29e-01

Pos logit contributions
mmm+0.032
Finally+0.030
icer+0.028
mmmm+0.028
ions+0.028
Neg logit contributions
 goodbye-0.017
 jog-0.015
guard-0.015
 stranger-0.015
 new-0.015
Token time
Token ID640
Feature activation-1.09e+00

Pos logit contributions
 goodbye+0.023
 jog+0.022
guard+0.021
 stranger+0.021
 bully+0.021
Neg logit contributions
mmm-0.034
Finally-0.031
mmmm-0.029
ions-0.029
icer-0.028
Token to
Token ID284
Feature activation+1.12e+00

Pos logit contributions
mmm+0.060
Finally+0.056
mmmm+0.053
ions+0.051
icer+0.051
Neg logit contributions
 goodbye-0.026
 jog-0.024
guard-0.024
 stranger-0.023
 new-0.022
Token make
Token ID787
Feature activation+2.70e-01

Pos logit contributions
mmm+0.062
Finally+0.057
mmmm+0.055
ions+0.054
icer+0.053
Neg logit contributions
 jog-0.027
 swim-0.023
 goodbye-0.023
 new-0.023
 wife-0.022
Token food
Token ID2057
Feature activation+1.61e+00

Pos logit contributions
mmm+0.015
Finally+0.014
mmmm+0.013
icer+0.013
ions+0.012
Neg logit contributions
 new-0.007
 goodbye-0.006
 jog-0.006
 wealthy-0.006
 en-0.005
Token look
Token ID804
Feature activation-1.75e-01

Pos logit contributions
mmm+0.078
Finally+0.072
mmmm+0.067
ions+0.066
icer+0.065
Neg logit contributions
 goodbye-0.047
 jog-0.045
guard-0.044
 stranger-0.043
 new-0.042
Token y
Token ID331
Feature activation+6.85e+00

Pos logit contributions
 goodbye+0.004
 jog+0.004
 stranger+0.004
guard+0.004
 new+0.004
Neg logit contributions
mmm-0.010
Finally-0.009
ions-0.008
mmmm-0.008
icer-0.008
Tokenumm
Token ID13929
Feature activation+8.37e+00

Pos logit contributions
Finally+0.212
mmm+0.195
Eventually+0.169
ra+0.154
icer+0.153
Neg logit contributions
 new-0.297
guard-0.286
 jog-0.284
 shrimp-0.284
 youth-0.282
Tokenier
Token ID959
Feature activation+4.58e+00

Pos logit contributions
Finally+0.369
mmm+0.358
Eventually+0.311
mmmm+0.300
icer+0.297
Neg logit contributions
guard-0.270
 goodbye-0.262
 new-0.245
 stranger-0.239
 jog-0.239
Token than
Token ID621
Feature activation+1.20e+00

Pos logit contributions
mmm+0.237
Finally+0.229
mmmm+0.207
icer+0.205
ions+0.201
Neg logit contributions
 goodbye-0.118
 new-0.112
guard-0.111
 jog-0.109
 stranger-0.109
Token before
Token ID878
Feature activation+1.67e+00

Pos logit contributions
mmm+0.063
Finally+0.059
mmmm+0.054
icer+0.053
ions+0.051
Neg logit contributions
 goodbye-0.032
 new-0.030
guard-0.029
 stranger-0.029
 jog-0.029
Token.
Token ID13
Feature activation-2.63e-01

Pos logit contributions
mmm+0.093
Finally+0.090
icer+0.085
mmmm+0.083
innie+0.081
Neg logit contributions
 goodbye-0.037
 new-0.037
 jog-0.034
 to-0.032
 wealthy-0.032
Token She
Token ID1375
Feature activation+2.25e+00

Pos logit contributions
 goodbye+0.007
 jog+0.006
 new+0.006
 en+0.006
 stranger+0.006
Neg logit contributions
mmm-0.014
Finally-0.012
ions-0.012
ra-0.012
mmmm-0.012
Token to
Token ID284
Feature activation+2.25e+00

Pos logit contributions
mmm+0.146
Finally+0.132
ions+0.126
mmmm+0.124
icer+0.120
Neg logit contributions
 goodbye-0.083
 jog-0.081
guard-0.077
 stranger-0.077
 bully-0.077
Token make
Token ID787
Feature activation+1.01e+00

Pos logit contributions
mmm+0.121
icer+0.119
Finally+0.119
ions+0.115
opes+0.110
Neg logit contributions
 jog-0.042
 new-0.041
 swim-0.036
 wealthy-0.036
 wife-0.036
Token it
Token ID340
Feature activation+2.45e-01

Pos logit contributions
mmm+0.052
Finally+0.050
icer+0.046
mmmm+0.045
ions+0.045
Neg logit contributions
 new-0.025
 goodbye-0.025
 wealthy-0.023
 jog-0.023
 en-0.023
Token taste
Token ID6938
Feature activation+2.89e+00

Pos logit contributions
mmm+0.013
Finally+0.011
mmmm+0.011
ions+0.011
icer+0.010
Neg logit contributions
 goodbye-0.006
guard-0.006
 jog-0.006
 stranger-0.006
 bully-0.006
Token y
Token ID331
Feature activation+7.15e+00

Pos logit contributions
mmm+0.153
Finally+0.141
ions+0.132
mmmm+0.132
icer+0.130
Neg logit contributions
 goodbye-0.071
 jog-0.067
guard-0.066
 stranger-0.065
 new-0.064
Tokenummy
Token ID13513
Feature activation+8.35e+00

Pos logit contributions
Finally+0.257
Eventually+0.214
mmm+0.209
 nine+0.196
 hours+0.188
Neg logit contributions
 shrimp-0.275
 new-0.267
guard-0.260
 youth-0.256
 baths-0.255
Token.
Token ID13
Feature activation+3.92e-01

Pos logit contributions
mmm+0.397
Finally+0.382
ions+0.341
icer+0.339
mmmm+0.338
Neg logit contributions
 goodbye-0.247
guard-0.230
 new-0.230
 stranger-0.230
 jog-0.230
Token Lily
Token ID20037
Feature activation+2.03e+00

Pos logit contributions
mmm+0.021
Finally+0.020
ions+0.019
icer+0.018
mmmm+0.018
Neg logit contributions
 goodbye-0.009
 jog-0.008
 en-0.008
 stranger-0.008
 new-0.008
Token helped
Token ID4193
Feature activation-1.83e-01

Pos logit contributions
mmm+0.122
Finally+0.111
ions+0.108
mmmm+0.108
icer+0.105
Neg logit contributions
 goodbye-0.037
 jog-0.036
guard-0.032
 stranger-0.032
 bully-0.032
Token her
Token ID607
Feature activation-1.94e+00

Pos logit contributions
 goodbye+0.004
 jog+0.004
 stranger+0.004
guard+0.004
 bully+0.004
Neg logit contributions
mmm-0.010
Finally-0.009
mmmm-0.009
ions-0.009
icer-0.008
Token mom
Token ID1995
Feature activation+2.63e+00

Pos logit contributions
 goodbye+0.052
 jog+0.050
 new+0.049
 stranger+0.047
 wealthy+0.047
Neg logit contributions
mmm-0.101
Finally-0.092
ions-0.088
mmmm-0.088
icer-0.085
Token could
Token ID714
Feature activation+5.37e+00

Pos logit contributions
mmm+0.134
Finally+0.123
ions+0.114
mmmm+0.114
icer+0.110
Neg logit contributions
 goodbye-0.073
 jog-0.071
guard-0.069
 stranger-0.068
 bully-0.067
Token see
Token ID766
Feature activation+1.94e+00

Pos logit contributions
mmm+0.293
Finally+0.269
ions+0.257
icer+0.255
mmmm+0.255
Neg logit contributions
 goodbye-0.123
 jog-0.120
guard-0.112
 stranger-0.111
 bully-0.110
Token lots
Token ID6041
Feature activation+2.69e+00

Pos logit contributions
mmm+0.106
Finally+0.098
mmmm+0.092
icer+0.089
ions+0.089
Neg logit contributions
 goodbye-0.045
 new-0.045
 stranger-0.042
 en-0.041
guard-0.041
Token of
Token ID286
Feature activation+1.99e+00

Pos logit contributions
mmm+0.130
Finally+0.119
mmmm+0.111
ions+0.111
icer+0.107
Neg logit contributions
 goodbye-0.078
 jog-0.076
guard-0.074
 stranger-0.073
 bully-0.072
Token av
Token ID1196
Feature activation+4.52e+00

Pos logit contributions
mmm+0.112
Finally+0.103
ions+0.099
mmmm+0.097
icer+0.096
Neg logit contributions
 new-0.046
 en-0.043
 wealthy-0.043
 stranger-0.043
 goodbye-0.042
Tokenoc
Token ID420
Feature activation+8.33e+00

Pos logit contributions
ions+0.158
mmm+0.157
Finally+0.144
mmmm+0.133
innie+0.130
Neg logit contributions
 wealthy-0.169
 rich-0.160
 new-0.158
 friendly-0.157
 gr-0.157
Tokenados
Token ID22484
Feature activation+2.75e+00

Pos logit contributions
Finally+0.300
mmm+0.297
ions+0.251
icer+0.243
Eventually+0.239
Neg logit contributions
 goodbye-0.317
 bully-0.301
 youth-0.298
 forg-0.296
 stranger-0.294
Token that
Token ID326
Feature activation+2.23e+00

Pos logit contributions
mmm+0.130
Finally+0.119
mmmm+0.110
ions+0.109
icer+0.108
Neg logit contributions
 goodbye-0.083
 jog-0.080
guard-0.080
 stranger-0.078
 bully-0.076
Token the
Token ID262
Feature activation+2.73e-01

Pos logit contributions
mmm+0.103
Finally+0.093
ions+0.088
mmmm+0.087
icer+0.084
Neg logit contributions
 goodbye-0.068
 jog-0.067
guard-0.064
 stranger-0.063
 bully-0.063
Token supplier
Token ID22693
Feature activation+1.39e+00

Pos logit contributions
mmm+0.015
Finally+0.014
ions+0.013
mmmm+0.013
icer+0.012
Neg logit contributions
 stranger-0.007
 goodbye-0.007
 youth-0.007
 wealthy-0.006
 bully-0.006
Token had
Token ID550
Feature activation+5.79e+00

Pos logit contributions
mmm+0.071
Finally+0.065
mmmm+0.061
ions+0.060
icer+0.059
Neg logit contributions
 goodbye-0.037
 jog-0.035
guard-0.035
 stranger-0.034
 bully-0.033
Token her
Token ID607
Feature activation-1.75e+00

Pos logit contributions
 goodbye+0.020
guard+0.020
 jog+0.019
eal+0.019
 bully+0.019
Neg logit contributions
mmm-0.031
Finally-0.028
ions-0.028
mmmm-0.026
ra-0.025
Token doll
Token ID3654
Feature activation-6.57e-01

Pos logit contributions
 goodbye+0.048
 jog+0.046
guard+0.045
 stranger+0.043
 bully+0.043
Neg logit contributions
mmm-0.086
Finally-0.078
ions-0.074
mmmm-0.073
icer-0.073
Token was
Token ID373
Feature activation+9.53e-01

Pos logit contributions
 goodbye+0.013
 jog+0.013
guard+0.012
 stranger+0.012
 bully+0.012
Neg logit contributions
mmm-0.038
Finally-0.035
mmmm-0.034
ions-0.033
icer-0.032
Token twelve
Token ID14104
Feature activation+3.87e+00

Pos logit contributions
mmm+0.050
Finally+0.046
mmmm+0.043
ions+0.043
icer+0.042
Neg logit contributions
 goodbye-0.024
 jog-0.023
guard-0.023
 stranger-0.022
 bully-0.022
Token inches
Token ID8331
Feature activation+1.63e+00

Pos logit contributions
mmm+0.179
Finally+0.175
mmmm+0.157
ions+0.154
Eventually+0.150
Neg logit contributions
 new-0.130
 wealthy-0.116
 old-0.115
 en-0.113
 goodbye-0.112
Token long
Token ID890
Feature activation+8.22e+00

Pos logit contributions
mmm+0.089
mmmm+0.079
Finally+0.079
ions+0.079
icer+0.076
Neg logit contributions
 new-0.038
 wealthy-0.036
 goodbye-0.035
 old-0.035
 jog-0.035
Token,
Token ID11
Feature activation+3.58e+00

Pos logit contributions
mmm+0.494
Finally+0.473
mmmm+0.441
icer+0.424
ousy+0.413
Neg logit contributions
 goodbye-0.172
 new-0.151
 to-0.150
 old-0.137
 jog-0.136
Token her
Token ID607
Feature activation-1.07e+00

Pos logit contributions
mmm+0.192
Finally+0.179
icer+0.168
mmmm+0.168
ions+0.168
Neg logit contributions
 goodbye-0.089
 en-0.082
 new-0.081
 jog-0.077
 wealthy-0.076
Token car
Token ID1097
Feature activation-5.68e-01

Pos logit contributions
 goodbye+0.029
 jog+0.027
 new+0.026
 stranger+0.026
 bully+0.026
Neg logit contributions
mmm-0.056
Finally-0.052
mmmm-0.048
ions-0.048
icer-0.046
Token was
Token ID373
Feature activation+1.72e+00

Pos logit contributions
 goodbye+0.012
 jog+0.012
guard+0.012
 bully+0.011
 stranger+0.011
Neg logit contributions
mmm-0.032
Finally-0.029
mmmm-0.028
ions-0.027
icer-0.027
Token six
Token ID2237
Feature activation+6.20e+00

Pos logit contributions
mmm+0.093
Finally+0.086
mmmm+0.082
icer+0.080
ions+0.077
Neg logit contributions
 new-0.043
 goodbye-0.042
 wealthy-0.042
 en-0.042
 friendly-0.041
Token made
Token ID925
Feature activation+2.11e+00

Pos logit contributions
 goodbye+0.046
 jog+0.042
 stranger+0.040
guard+0.039
 aut+0.039
Neg logit contributions
mmm-0.062
Finally-0.057
icer-0.054
ions-0.053
mmmm-0.052
Token her
Token ID607
Feature activation+9.83e-01

Pos logit contributions
mmm+0.126
Finally+0.118
mmmm+0.110
icer+0.110
ions+0.108
Neg logit contributions
 new-0.042
 goodbye-0.038
 wealthy-0.035
 en-0.034
 jog-0.033
Token food
Token ID2057
Feature activation+6.90e-01

Pos logit contributions
mmm+0.052
Finally+0.047
icer+0.044
mmmm+0.044
ions+0.044
Neg logit contributions
guard-0.023
 goodbye-0.023
 jog-0.023
 stranger-0.022
 bully-0.021
Token taste
Token ID6938
Feature activation+2.74e+00

Pos logit contributions
mmm+0.037
Finally+0.034
mmmm+0.032
ions+0.032
icer+0.031
Neg logit contributions
 goodbye-0.017
 jog-0.016
guard-0.016
 stranger-0.015
 new-0.015
Token y
Token ID331
Feature activation+7.22e+00

Pos logit contributions
mmm+0.145
Finally+0.134
ions+0.125
mmmm+0.125
icer+0.122
Neg logit contributions
 goodbye-0.068
 jog-0.064
guard-0.063
 stranger-0.062
 new-0.061
Tokenummy
Token ID13513
Feature activation+8.20e+00

Pos logit contributions
Finally+0.219
mmm+0.202
Eventually+0.175
ions+0.163
 nine+0.161
Neg logit contributions
 new-0.310
 shrimp-0.303
 youth-0.299
 jog-0.298
guard-0.296
Token.
Token ID13
Feature activation+1.94e-02

Pos logit contributions
mmm+0.417
Finally+0.405
ions+0.362
mmmm+0.360
icer+0.358
Neg logit contributions
 goodbye-0.218
 new-0.204
 stranger-0.201
 jog-0.201
guard-0.198
Token One
Token ID1881
Feature activation+5.28e+00

Pos logit contributions
mmm+0.001
Finally+0.001
ions+0.001
mmmm+0.001
ra+0.001
Neg logit contributions
 goodbye-0.001
 jog-0.001
 new-0.001
 stranger-0.001
 en-0.000
Token day
Token ID1110
Feature activation-8.12e-01

Pos logit contributions
mmm+0.177
Finally+0.148
mmmm+0.142
icer+0.140
ousy+0.140
Neg logit contributions
 goodbye-0.217
 aut-0.214
 bully-0.213
guard-0.211
eal-0.207
Token,
Token ID11
Feature activation+6.22e-01

Pos logit contributions
 goodbye+0.027
 jog+0.026
guard+0.025
 stranger+0.025
 bully+0.025
Neg logit contributions
mmm-0.036
Finally-0.033
mmmm-0.030
ions-0.030
icer-0.030
Token her
Token ID607
Feature activation-3.10e+00

Pos logit contributions
mmm+0.032
Finally+0.029
ions+0.027
mmmm+0.027
icer+0.026
Neg logit contributions
 goodbye-0.016
 jog-0.016
guard-0.016
 stranger-0.015
 bully-0.015
Token a
Token ID257
Feature activation+2.67e+00

Pos logit contributions
mmm+0.120
Finally+0.108
mmmm+0.106
icer+0.101
ousy+0.100
Neg logit contributions
 new-0.041
 goodbye-0.038
 en-0.033
 wealthy-0.032
 friendly-0.032
Token sign
Token ID1051
Feature activation-1.75e+00

Pos logit contributions
mmm+0.172
ions+0.160
mmmm+0.153
icer+0.146
Finally+0.143
Neg logit contributions
 new-0.060
 friendly-0.049
 wealthy-0.047
 stranger-0.046
 happy-0.046
Token that
Token ID326
Feature activation+2.19e+00

Pos logit contributions
 goodbye+0.043
 jog+0.041
guard+0.040
 stranger+0.040
 new+0.039
Neg logit contributions
mmm-0.094
Finally-0.087
mmmm-0.082
icer-0.081
ions-0.080
Token said
Token ID531
Feature activation+1.80e+00

Pos logit contributions
mmm+0.112
Finally+0.103
ions+0.098
mmmm+0.096
ra+0.092
Neg logit contributions
 goodbye-0.058
 jog-0.055
 stranger-0.052
guard-0.052
 bully-0.051
Token "
Token ID366
Feature activation+2.98e+00

Pos logit contributions
mmm+0.097
Finally+0.089
ions+0.083
mmmm+0.083
icer+0.080
Neg logit contributions
 goodbye-0.043
 jog-0.042
guard-0.041
 stranger-0.040
 bully-0.039
TokenE
Token ID36
Feature activation+8.17e+00

Pos logit contributions
mmm+0.130
Finally+0.114
ions+0.106
icer+0.106
mmmm+0.105
Neg logit contributions
 jog-0.098
guard-0.097
 aut-0.093
 stranger-0.092
 bully-0.092
Tokenlev
Token ID2768
Feature activation-2.44e-01

Pos logit contributions
mmm+0.305
Finally+0.296
icer+0.251
mmmm+0.249
ions+0.247
Neg logit contributions
guard-0.306
 jog-0.297
 goodbye-0.291
 bully-0.287
 stranger-0.285
Tokenator
Token ID1352
Feature activation-1.04e+00

Pos logit contributions
guard+0.009
 jog+0.009
 aut+0.008
 new+0.008
 bully+0.008
Neg logit contributions
mmm-0.009
Finally-0.007
mmmm-0.007
 hours-0.007
ions-0.006
Token to
Token ID284
Feature activation+1.56e-01

Pos logit contributions
 goodbye+0.039
guard+0.036
 jog+0.036
 bully+0.035
 stranger+0.035
Neg logit contributions
mmm-0.042
Finally-0.039
mmmm-0.035
icer-0.034
ions-0.033
Token the
Token ID262
Feature activation-5.60e-01

Pos logit contributions
mmm+0.008
Finally+0.008
icer+0.007
ions+0.007
mmmm+0.007
Neg logit contributions
 new-0.004
 jog-0.004
 wealthy-0.004
 youth-0.003
 goodbye-0.003
Token Moon
Token ID6869
Feature activation+2.03e+00

Pos logit contributions
 new+0.018
 stranger+0.017
 bully+0.016
 wealthy+0.016
 youth+0.016
Neg logit contributions
mmm-0.031
mmmm-0.025
Finally-0.025
ions-0.024
rap-0.023
Token placed
Token ID4624
Feature activation+2.52e+00

Pos logit contributions
mmm+0.032
Finally+0.029
ions+0.028
mmmm+0.027
icer+0.026
Neg logit contributions
 goodbye-0.017
 jog-0.016
guard-0.016
 stranger-0.016
 bully-0.016
Token it
Token ID340
Feature activation+1.90e-01

Pos logit contributions
mmm+0.138
Finally+0.126
mmmm+0.119
icious+0.114
ousy+0.111
Neg logit contributions
 goodbye-0.067
 new-0.063
guard-0.057
 jog-0.055
 en-0.055
Token onto
Token ID4291
Feature activation+2.31e+00

Pos logit contributions
mmm+0.009
Finally+0.008
ions+0.008
mmmm+0.007
icer+0.007
Neg logit contributions
 bully-0.006
 goodbye-0.006
 stranger-0.006
 jog-0.005
guard-0.005
Token the
Token ID262
Feature activation+1.27e+00

Pos logit contributions
mmm+0.162
Finally+0.152
mmmm+0.146
icious+0.143
ousy+0.143
Neg logit contributions
 new-0.022
 goodbye-0.022
 his-0.020
 jog-0.016
 youth-0.015
Token wheel
Token ID7825
Feature activation+2.18e+00

Pos logit contributions
mmm+0.063
Finally+0.056
mmmm+0.054
ions+0.054
icer+0.050
Neg logit contributions
 goodbye-0.039
 new-0.038
 jog-0.038
 stranger-0.038
 youth-0.037
Tokenbar
Token ID5657
Feature activation+8.15e+00

Pos logit contributions
mmm+0.111
Finally+0.101
mmmm+0.096
icer+0.090
ions+0.089
Neg logit contributions
 goodbye-0.064
guard-0.060
 jog-0.059
 new-0.056
 stranger-0.054
Tokenrow
Token ID808
Feature activation+5.04e+00

Pos logit contributions
mmm+0.356
Finally+0.306
mmmm+0.298
icious+0.278
ions+0.258
Neg logit contributions
 goodbye-0.273
guard-0.266
 back-0.264
 new-0.264
 jog-0.253
Token.
Token ID13
Feature activation+7.65e-01

Pos logit contributions
mmm+0.249
Finally+0.224
mmmm+0.212
ions+0.206
icer+0.204
Neg logit contributions
 goodbye-0.149
guard-0.139
 jog-0.138
 stranger-0.134
 new-0.132
Token
Token ID198
Feature activation+6.01e-01

Pos logit contributions
mmm+0.038
Finally+0.035
ions+0.033
mmmm+0.033
icer+0.032
Neg logit contributions
 goodbye-0.021
 jog-0.020
guard-0.019
 stranger-0.019
 bully-0.019
Token
Token ID198
Feature activation-1.83e-01

Pos logit contributions
mmm+0.036
ions+0.033
ra+0.032
els+0.032
olk+0.032
Neg logit contributions
 jog-0.009
guard-0.009
 goodbye-0.008
 stranger-0.008
 new-0.008
TokenJohn
Token ID7554
Feature activation+3.88e-02

Pos logit contributions
 jog+0.007
guard+0.007
 stranger+0.007
 goodbye+0.007
 sport+0.006
Neg logit contributions
mmm-0.007
ions-0.006
els-0.006
icer-0.006
olk-0.006
Token couldn
Token ID3521
Feature activation+4.03e+00

Pos logit contributions
mmm+0.020
Finally+0.018
ions+0.017
mmmm+0.017
icer+0.016
Neg logit contributions
 goodbye-0.013
 jog-0.013
guard-0.012
 stranger-0.012
 bully-0.012
Token't
Token ID470
Feature activation-1.64e-01

Pos logit contributions
mmm+0.140
Finally+0.123
mmmm+0.110
ions+0.110
icer+0.105
Neg logit contributions
 goodbye-0.173
 jog-0.168
guard-0.166
 stranger-0.164
 bully-0.162
Token find
Token ID1064
Feature activation-9.58e-01

Pos logit contributions
 goodbye+0.003
 jog+0.003
guard+0.003
 stranger+0.003
 bully+0.003
Neg logit contributions
mmm-0.009
Finally-0.009
ions-0.008
mmmm-0.008
icer-0.008
Token any
Token ID597
Feature activation-3.98e-01

Pos logit contributions
 goodbye+0.024
 new+0.022
 jog+0.022
 stranger+0.021
 youth+0.020
Neg logit contributions
mmm-0.053
Finally-0.050
mmmm-0.046
icious-0.044
icer-0.044
Token av
Token ID1196
Feature activation+3.71e+00

Pos logit contributions
 goodbye+0.010
 new+0.010
 stranger+0.010
 jog+0.010
guard+0.010
Neg logit contributions
mmm-0.022
Finally-0.020
mmmm-0.019
ions-0.018
icer-0.018
Tokenoc
Token ID420
Feature activation+8.08e+00

Pos logit contributions
mmm+0.129
ions+0.116
Finally+0.113
mmmm+0.105
olk+0.101
Neg logit contributions
 wealthy-0.135
 stranger-0.133
 new-0.133
 jog-0.132
 bully-0.131
Tokenados
Token ID22484
Feature activation+2.15e+00

Pos logit contributions
Finally+0.284
mmm+0.281
ions+0.240
Eventually+0.225
icer+0.221
Neg logit contributions
 goodbye-0.319
 bully-0.309
 aut-0.303
 stranger-0.301
 youth-0.299
Token.
Token ID13
Feature activation+4.89e-01

Pos logit contributions
mmm+0.098
Finally+0.089
ions+0.084
mmmm+0.082
icer+0.079
Neg logit contributions
 goodbye-0.068
 jog-0.066
guard-0.064
 stranger-0.063
 bully-0.063
Token Finally
Token ID9461
Feature activation+6.83e+00

Pos logit contributions
mmm+0.025
ions+0.023
Finally+0.022
mmmm+0.022
icer+0.022
Neg logit contributions
 goodbye-0.012
 en-0.011
 jog-0.011
 new-0.011
 stranger-0.011
Token,
Token ID11
Feature activation+6.28e-01

Pos logit contributions
mmm+0.366
Finally+0.345
icer+0.336
mmmm+0.328
icious+0.324
Neg logit contributions
 goodbye-0.188
 jog-0.157
 new-0.150
 stranger-0.148
 sad-0.139
Token she
Token ID673
Feature activation+3.61e-03

Pos logit contributions
mmm+0.033
Finally+0.030
mmmm+0.029
ions+0.029
icer+0.028
Neg logit contributions
 goodbye-0.016
 jog-0.015
 stranger-0.015
guard-0.015
 bully-0.014
TokenI
Token ID40
Feature activation+1.30e+00

Pos logit contributions
mmm+0.066
Finally+0.059
ions+0.055
mmmm+0.055
icer+0.053
Neg logit contributions
 goodbye-0.049
 jog-0.048
guard-0.047
 stranger-0.046
 bully-0.045
Token will
Token ID481
Feature activation+1.30e+00

Pos logit contributions
mmm+0.060
Finally+0.056
ra+0.051
mmmm+0.050
ions+0.049
Neg logit contributions
 goodbye-0.041
 stranger-0.037
guard-0.037
 youth-0.036
 jog-0.036
Token buy
Token ID2822
Feature activation-1.19e-01

Pos logit contributions
mmm+0.072
Finally+0.067
ions+0.063
mmmm+0.063
icer+0.062
Neg logit contributions
 goodbye-0.029
 jog-0.028
guard-0.027
 stranger-0.026
 bully-0.026
Token more
Token ID517
Feature activation+1.46e+00

Pos logit contributions
 new+0.004
 goodbye+0.004
 wealthy+0.003
 stranger+0.003
guard+0.003
Neg logit contributions
mmm-0.006
Finally-0.006
icer-0.005
mmmm-0.005
ousy-0.005
Token av
Token ID1196
Feature activation+4.22e+00

Pos logit contributions
mmm+0.074
Finally+0.069
mmmm+0.064
ions+0.063
icer+0.062
Neg logit contributions
 goodbye-0.039
 jog-0.038
guard-0.037
 stranger-0.037
 new-0.036
Tokenoc
Token ID420
Feature activation+8.06e+00

Pos logit contributions
mmm+0.135
Finally+0.122
ions+0.120
mmmm+0.106
olk+0.105
Neg logit contributions
 wealthy-0.168
 goodbye-0.167
guard-0.165
 jog-0.165
 stranger-0.165
Tokenados
Token ID22484
Feature activation+2.75e+00

Pos logit contributions
Finally+0.270
mmm+0.267
ions+0.223
icer+0.219
Eventually+0.211
Neg logit contributions
 goodbye-0.336
 bully-0.322
guard-0.318
 aut-0.315
 stranger-0.312
Token tomorrow
Token ID9439
Feature activation+3.91e+00

Pos logit contributions
mmm+0.124
Finally+0.109
ions+0.105
mmmm+0.103
icer+0.098
Neg logit contributions
 goodbye-0.090
 jog-0.087
 bully-0.084
 stranger-0.084
guard-0.083
Token.
Token ID13
Feature activation+4.96e-01

Pos logit contributions
mmm+0.174
Finally+0.164
mmmm+0.147
ions+0.147
icer+0.146
Neg logit contributions
 goodbye-0.128
 jog-0.123
guard-0.120
 stranger-0.118
 new-0.118
Token You
Token ID921
Feature activation-4.97e-01

Pos logit contributions
mmm+0.024
Finally+0.024
icer+0.023
els+0.022
ions+0.022
Neg logit contributions
 goodbye-0.012
 jog-0.011
 His-0.010
 aut-0.010
 en-0.010
Token can
Token ID460
Feature activation+3.72e+00

Pos logit contributions
 jog+0.013
 goodbye+0.013
 bully+0.013
 wealthy+0.013
guard+0.013
Neg logit contributions
mmm-0.025
Finally-0.023
ions-0.022
mmmm-0.022
icer-0.021
Token learn
Token ID2193
Feature activation-1.90e+00

Pos logit contributions
 goodbye+0.042
guard+0.040
 stranger+0.040
 wealthy+0.039
 jog+0.039
Neg logit contributions
mmm-0.074
Finally-0.067
ions-0.062
mmmm-0.062
ra-0.061
Token more
Token ID517
Feature activation+9.77e-01

Pos logit contributions
eal+0.055
 jog+0.054
 bully+0.053
 goodbye+0.049
 en+0.049
Neg logit contributions
mmm-0.084
ions-0.079
Finally-0.077
mmmm-0.071
els-0.069
Token about
Token ID546
Feature activation+2.83e-01

Pos logit contributions
mmm+0.048
Finally+0.042
ions+0.041
mmmm+0.040
 centimeters+0.037
Neg logit contributions
eal-0.026
guard-0.025
 bully-0.025
 jog-0.025
 seal-0.025
Token rh
Token ID9529
Feature activation+2.11e+00

Pos logit contributions
mmm+0.014
Finally+0.013
ions+0.013
mmmm+0.012
icer+0.012
Neg logit contributions
 goodbye-0.007
guard-0.007
 jog-0.007
 stranger-0.007
eal-0.007
Tokenin
Token ID259
Feature activation+2.49e+00

Pos logit contributions
mmm+0.098
Finally+0.088
mmmm+0.082
ions+0.079
icer+0.077
Neg logit contributions
guard-0.067
 goodbye-0.064
 bully-0.064
 jog-0.064
 stranger-0.064
Tokenoc
Token ID420
Feature activation+8.05e+00

Pos logit contributions
mmm+0.080
Finally+0.068
ions+0.063
mmmm+0.062
icer+0.059
Neg logit contributions
 goodbye-0.110
 jog-0.107
 stranger-0.104
guard-0.104
 bully-0.103
Tokener
Token ID263
Feature activation+9.20e-01

Pos logit contributions
mmm+0.329
Finally+0.312
mmmm+0.267
ions+0.266
icer+0.258
Neg logit contributions
 goodbye-0.289
guard-0.281
 bully-0.273
 aut-0.267
 stranger-0.265
Tokenoses
Token ID4629
Feature activation+2.29e+00

Pos logit contributions
mmm+0.039
ions+0.034
Finally+0.034
mmmm+0.032
ra+0.031
Neg logit contributions
 goodbye-0.030
 jog-0.030
 stranger-0.029
guard-0.028
 bully-0.028
Token and
Token ID290
Feature activation+4.47e-01

Pos logit contributions
mmm+0.094
ions+0.084
Finally+0.082
mmmm+0.077
ra+0.075
Neg logit contributions
 jog-0.074
 goodbye-0.073
 stranger-0.072
 bully-0.071
eal-0.070
Token respect
Token ID2461
Feature activation+7.71e-02

Pos logit contributions
mmm+0.020
Finally+0.018
ions+0.017
mmmm+0.017
ra+0.016
Neg logit contributions
 goodbye-0.014
guard-0.013
 jog-0.013
 stranger-0.013
eal-0.012
Token them
Token ID606
Feature activation-2.47e+00

Pos logit contributions
mmm+0.004
Finally+0.004
mmmm+0.003
ions+0.003
icer+0.003
Neg logit contributions
 goodbye-0.002
 jog-0.002
guard-0.002
 stranger-0.002
 bully-0.002
Token that
Token ID326
Feature activation-9.50e-02

Pos logit contributions
 jog+0.054
 goodbye+0.053
 bully+0.052
guard+0.050
 stranger+0.050
Neg logit contributions
mmm-0.115
Finally-0.102
ions-0.101
mmmm-0.098
ra-0.093
Token it
Token ID340
Feature activation-2.63e+00

Pos logit contributions
 jog+0.003
 goodbye+0.003
guard+0.003
eal+0.003
 stranger+0.003
Neg logit contributions
mmm-0.005
Finally-0.004
ions-0.004
mmmm-0.004
icer-0.004
Token produced
Token ID4635
Feature activation+1.72e+00

Pos logit contributions
 goodbye+0.098
 jog+0.095
 aut+0.092
 sport+0.092
 wife+0.091
Neg logit contributions
mmm-0.097
Finally-0.090
ra-0.087
ions-0.087
 hours-0.076
Token more
Token ID517
Feature activation+1.81e+00

Pos logit contributions
mmm+0.084
Finally+0.077
ions+0.072
mmmm+0.072
icer+0.068
Neg logit contributions
 jog-0.048
 goodbye-0.048
guard-0.047
 bully-0.045
 stranger-0.045
Token av
Token ID1196
Feature activation+4.47e+00

Pos logit contributions
mmm+0.087
Finally+0.079
mmmm+0.073
ions+0.073
icer+0.070
Neg logit contributions
 goodbye-0.054
 jog-0.053
guard-0.051
 stranger-0.050
 bully-0.050
Tokenoc
Token ID420
Feature activation+8.01e+00

Pos logit contributions
mmm+0.148
ions+0.138
Finally+0.133
mmmm+0.121
icer+0.117
Neg logit contributions
 wealthy-0.179
 goodbye-0.172
 new-0.172
 friendly-0.171
 rich-0.167
Tokenados
Token ID22484
Feature activation+2.48e+00

Pos logit contributions
mmm+0.260
Finally+0.252
ions+0.215
icer+0.209
mmmm+0.201
Neg logit contributions
 goodbye-0.343
guard-0.325
 bully-0.323
 stranger-0.319
 youth-0.319
Token than
Token ID621
Feature activation+3.46e-01

Pos logit contributions
mmm+0.107
Finally+0.091
ions+0.090
mmmm+0.086
ra+0.081
Neg logit contributions
 goodbye-0.084
 jog-0.083
 bully-0.083
eal-0.079
 stranger-0.078
Token ever
Token ID1683
Feature activation+1.63e+00

Pos logit contributions
mmm+0.016
Finally+0.015
ions+0.014
mmmm+0.014
icer+0.013
Neg logit contributions
 jog-0.010
 goodbye-0.010
guard-0.010
 stranger-0.010
 bully-0.010
Token before
Token ID878
Feature activation+7.44e-01

Pos logit contributions
mmm+0.070
Finally+0.061
mmmm+0.057
ions+0.057
icer+0.055
Neg logit contributions
 goodbye-0.056
 jog-0.056
guard-0.055
 bully-0.054
 stranger-0.054
Token.
Token ID13
Feature activation-1.06e-01

Pos logit contributions
mmm+0.037
Finally+0.035
icer+0.032
mmmm+0.032
ions+0.032
Neg logit contributions
 goodbye-0.020
 new-0.019
 jog-0.019
 stranger-0.019
 wealthy-0.018
Token net
Token ID2010
Feature activation-1.45e-01

Pos logit contributions
mmm+0.048
Finally+0.044
mmmm+0.041
ions+0.041
icer+0.038
Neg logit contributions
 goodbye-0.020
 jog-0.019
guard-0.019
 stranger-0.019
 new-0.019
Token on
Token ID319
Feature activation+1.76e+00

Pos logit contributions
 bully+0.004
 stranger+0.004
 jog+0.004
guard+0.004
 youth+0.004
Neg logit contributions
mmm-0.006
Finally-0.006
ions-0.006
ra-0.005
icer-0.005
Token the
Token ID262
Feature activation+1.03e+00

Pos logit contributions
mmm+0.118
Finally+0.109
mmmm+0.105
ions+0.102
icious+0.100
Neg logit contributions
 goodbye-0.025
 new-0.021
 jog-0.020
 stranger-0.019
 youth-0.018
Token rh
Token ID9529
Feature activation+2.05e+00

Pos logit contributions
mmm+0.052
Finally+0.047
mmmm+0.044
ions+0.044
icer+0.041
Neg logit contributions
 goodbye-0.031
 jog-0.030
 stranger-0.029
 new-0.029
guard-0.029
Tokenin
Token ID259
Feature activation+2.50e+00

Pos logit contributions
mmm+0.105
Finally+0.095
mmmm+0.089
ions+0.087
olk+0.082
Neg logit contributions
guard-0.058
 bully-0.054
 stranger-0.054
 seal-0.053
 goodbye-0.051
Tokenoc
Token ID420
Feature activation+7.93e+00

Pos logit contributions
mmm+0.069
Finally+0.058
mmmm+0.050
ions+0.050
icer+0.045
Neg logit contributions
 goodbye-0.127
 jog-0.125
guard-0.124
 stranger-0.122
 bully-0.120
Tokeneros
Token ID27498
Feature activation+9.45e-01

Pos logit contributions
mmm+0.389
Finally+0.374
ions+0.330
mmmm+0.326
Eventually+0.318
Neg logit contributions
 goodbye-0.234
guard-0.220
 bully-0.215
 seal-0.209
 stranger-0.208
Token.
Token ID13
Feature activation+1.58e+00

Pos logit contributions
mmm+0.049
Finally+0.045
ions+0.043
mmmm+0.042
icer+0.041
Neg logit contributions
 goodbye-0.024
 jog-0.023
guard-0.022
 stranger-0.022
 bully-0.022
Token They
Token ID1119
Feature activation+1.52e+00

Pos logit contributions
mmm+0.086
Finally+0.079
ions+0.074
mmmm+0.074
icer+0.073
Neg logit contributions
 goodbye-0.038
 jog-0.036
guard-0.034
 stranger-0.033
 bully-0.032
Token put
Token ID1234
Feature activation+1.20e+00

Pos logit contributions
mmm+0.077
Finally+0.071
ions+0.066
ra+0.065
mmmm+0.065
Neg logit contributions
 goodbye-0.038
guard-0.036
 stranger-0.036
 jog-0.034
 new-0.034
Token the
Token ID262
Feature activation+1.20e+00

Pos logit contributions
mmm+0.069
Finally+0.064
mmmm+0.060
ions+0.059
icer+0.057
Neg logit contributions
 goodbye-0.026
 jog-0.024
guard-0.023
 stranger-0.023
 new-0.023
Token "
Token ID366
Feature activation+2.35e+00

Pos logit contributions
mmm+0.076
Finally+0.069
mmmm+0.064
ions+0.063
icer+0.061
Neg logit contributions
guard-0.037
 jog-0.037
 goodbye-0.036
 stranger-0.035
 bully-0.035
TokenThey
Token ID2990
Feature activation+8.76e-01

Pos logit contributions
mmm+0.110
ions+0.097
Finally+0.097
rap+0.097
icer+0.094
Neg logit contributions
 jog-0.065
guard-0.065
 seal-0.062
 stranger-0.061
 goodbye-0.060
Token all
Token ID477
Feature activation+3.23e-01

Pos logit contributions
mmm+0.042
Finally+0.038
mmmm+0.035
ions+0.035
icer+0.034
Neg logit contributions
 goodbye-0.026
 jog-0.025
guard-0.025
 stranger-0.025
 bully-0.024
Token look
Token ID804
Feature activation-9.25e-01

Pos logit contributions
mmm+0.015
Finally+0.013
ions+0.012
mmmm+0.012
icer+0.012
Neg logit contributions
 goodbye-0.010
guard-0.010
 jog-0.010
 stranger-0.010
 wife-0.009
Token y
Token ID331
Feature activation+6.56e+00

Pos logit contributions
 goodbye+0.021
 new+0.019
 jog+0.019
 wealthy+0.018
 en+0.018
Neg logit contributions
mmm-0.051
Finally-0.048
ions-0.046
mmmm-0.045
icer-0.045
Tokenummy
Token ID13513
Feature activation+7.90e+00

Pos logit contributions
Finally+0.212
mmm+0.177
Eventually+0.164
icer+0.148
innie+0.140
Neg logit contributions
 goodbye-0.289
 shrimp-0.281
 new-0.280
guard-0.274
eal-0.273
Token.
Token ID13
Feature activation+8.99e-01

Pos logit contributions
mmm+0.380
Finally+0.368
mmmm+0.324
icer+0.319
ions+0.318
Neg logit contributions
 goodbye-0.241
guard-0.220
 stranger-0.220
 jog-0.220
 new-0.217
Token Can
Token ID1680
Feature activation+2.85e+00

Pos logit contributions
mmm+0.043
Finally+0.043
icer+0.039
ths+0.038
ions+0.038
Neg logit contributions
 goodbye-0.025
 jog-0.022
 aut-0.021
 bully-0.021
 en-0.021
Token I
Token ID314
Feature activation+1.04e+00

Pos logit contributions
mmm+0.122
Finally+0.111
ions+0.102
mmmm+0.102
icer+0.099
Neg logit contributions
 goodbye-0.100
 jog-0.096
guard-0.095
 stranger-0.092
 bully-0.091
Token have
Token ID423
Feature activation+1.28e+00

Pos logit contributions
mmm+0.059
Finally+0.055
ions+0.052
icer+0.052
mmmm+0.051
Neg logit contributions
 jog-0.022
 goodbye-0.021
 bully-0.020
guard-0.019
 stranger-0.019
Token a
Token ID257
Feature activation+1.86e+00

Pos logit contributions
mmm+0.068
Finally+0.064
icer+0.060
ions+0.059
mmmm+0.059
Neg logit contributions
 goodbye-0.032
 new-0.030
 jog-0.028
 wealthy-0.028
 stranger-0.027
TokenThis
Token ID1212
Feature activation-1.45e-01

Pos logit contributions
mmm+0.092
ions+0.086
ousy+0.086
ocol+0.083
igs+0.083
Neg logit contributions
 jog-0.044
 stranger-0.037
 ride-0.037
 sport-0.036
 youth-0.036
Token block
Token ID2512
Feature activation+8.64e-01

Pos logit contributions
 new+0.003
 goodbye+0.003
 jog+0.003
 bully+0.003
 stranger+0.002
Neg logit contributions
mmm-0.009
Finally-0.008
mmmm-0.007
ions-0.007
ousy-0.007
Token is
Token ID318
Feature activation+2.51e-01

Pos logit contributions
mmm+0.050
Finally+0.047
mmmm+0.043
ions+0.043
Eventually+0.042
Neg logit contributions
 goodbye-0.016
 new-0.016
 bully-0.016
guard-0.015
 jog-0.015
Token ten
Token ID3478
Feature activation+5.56e+00

Pos logit contributions
mmm+0.015
icer+0.015
Finally+0.015
ions+0.014
innie+0.014
Neg logit contributions
 new-0.005
 old-0.004
 to-0.004
 wealthy-0.004
 friendly-0.004
Token inches
Token ID8331
Feature activation+1.36e+00

Pos logit contributions
Finally+0.263
mmm+0.259
ousy+0.239
ions+0.237
innie+0.233
Neg logit contributions
 new-0.181
 old-0.164
 to-0.160
 wealthy-0.158
 goodbye-0.148
Token long
Token ID890
Feature activation+7.89e+00

Pos logit contributions
mmm+0.075
ions+0.069
Finally+0.068
innie+0.067
ousy+0.067
Neg logit contributions
 new-0.031
 old-0.030
 wealthy-0.029
 to-0.028
 jog-0.027
Token.
Token ID13
Feature activation+6.67e-01

Pos logit contributions
Finally+0.479
mmm+0.471
mmmm+0.424
ousy+0.423
Eventually+0.420
Neg logit contributions
 to-0.154
 goodbye-0.145
 old-0.126
 new-0.124
 youth-0.113
Token This
Token ID770
Feature activation+1.15e-01

Pos logit contributions
Finally+0.039
ousy+0.039
ths+0.038
igs+0.038
 hours+0.037
Neg logit contributions
 His-0.008
 The-0.008
 hello-0.007
 en-0.007
 aut-0.007
Token block
Token ID2512
Feature activation+1.54e+00

Pos logit contributions
mmm+0.006
Finally+0.006
mmmm+0.005
ions+0.005
ousy+0.005
Neg logit contributions
 new-0.003
 goodbye-0.003
 bully-0.003
 jog-0.003
 en-0.003
Token is
Token ID318
Feature activation+4.82e-01

Pos logit contributions
mmm+0.089
Finally+0.085
mmmm+0.078
ions+0.077
Eventually+0.076
Neg logit contributions
 new-0.028
 goodbye-0.028
 bully-0.027
guard-0.027
 jog-0.026
Token eight
Token ID3624
Feature activation+7.07e+00

Pos logit contributions
mmm+0.029
Finally+0.028
icer+0.027
mmmm+0.027
innie+0.026
Neg logit contributions
 new-0.010
 old-0.009
 wealthy-0.008
 friendly-0.008
 en-0.008
Tokenist
Token ID396
Feature activation-7.34e-01

Pos logit contributions
 goodbye+0.082
 jog+0.082
 stranger+0.082
 youth+0.081
guard+0.081
Neg logit contributions
mmm-0.055
Finally-0.047
ions-0.041
ra-0.041
mmmm-0.041
Tokenening
Token ID3101
Feature activation-2.07e+00

Pos logit contributions
 goodbye+0.026
 jog+0.025
guard+0.025
 stranger+0.025
 bully+0.024
Neg logit contributions
mmm-0.031
Finally-0.028
ions-0.025
mmmm-0.025
icer-0.024
Token golden
Token ID10861
Feature activation+2.18e+00

Pos logit contributions
 goodbye+0.054
 jog+0.052
 stranger+0.051
guard+0.051
 seal+0.049
Neg logit contributions
mmm-0.110
Finally-0.102
mmmm-0.095
ions-0.091
icer-0.089
Token l
Token ID300
Feature activation+1.99e+00

Pos logit contributions
mmm+0.110
Finally+0.102
mmmm+0.094
ions+0.094
icer+0.091
Neg logit contributions
 goodbye-0.061
 jog-0.059
 stranger-0.057
guard-0.057
 bully-0.055
Tokenily
Token ID813
Feature activation+6.80e+00

Pos logit contributions
mmm+0.089
Finally+0.080
mmmm+0.074
icer+0.072
ions+0.068
Neg logit contributions
 goodbye-0.068
guard-0.063
 jog-0.062
 stranger-0.061
 bully-0.060
Token pad
Token ID14841
Feature activation+7.89e+00

Pos logit contributions
mmm+0.290
Finally+0.260
mmmm+0.244
ions+0.230
icer+0.224
Neg logit contributions
 goodbye-0.256
 jog-0.244
 new-0.235
 stranger-0.231
guard-0.231
Token.
Token ID13
Feature activation-4.94e-01

Pos logit contributions
mmm+0.412
Finally+0.382
mmmm+0.357
icer+0.349
ions+0.334
Neg logit contributions
 goodbye-0.221
 jog-0.191
guard-0.188
 stranger-0.180
 to-0.178
Token The
Token ID383
Feature activation+3.76e-01

Pos logit contributions
 goodbye+0.012
 jog+0.011
guard+0.011
 stranger+0.011
 bully+0.011
Neg logit contributions
mmm-0.027
Finally-0.025
mmmm-0.023
ions-0.023
icer-0.022
Token frog
Token ID21264
Feature activation-1.21e+00

Pos logit contributions
mmm+0.019
Finally+0.019
icer+0.017
ions+0.017
mmmm+0.017
Neg logit contributions
 goodbye-0.008
 aut-0.007
guard-0.007
 jog-0.007
eal-0.006
Token hopped
Token ID45230
Feature activation+5.85e-01

Pos logit contributions
 goodbye+0.034
 aut+0.032
guard+0.032
 jog+0.031
 stranger+0.031
Neg logit contributions
mmm-0.057
Finally-0.055
ra-0.049
ions-0.048
icer-0.048
Token up
Token ID510
Feature activation-2.77e+00

Pos logit contributions
mmm+0.027
Finally+0.027
ions+0.025
ra+0.023
icer+0.023
Neg logit contributions
 bully-0.016
 wife-0.015
guard-0.015
 jog-0.015
 youth-0.015
Token a
Token ID257
Feature activation+3.01e+00

Pos logit contributions
mmm+0.107
Finally+0.099
mmmm+0.093
ions+0.092
icer+0.091
Neg logit contributions
 goodbye-0.044
 new-0.042
 jog-0.039
 en-0.039
 wealthy-0.037
Token funny
Token ID8258
Feature activation+8.69e-01

Pos logit contributions
mmm+0.180
ions+0.166
Finally+0.165
mmmm+0.159
icer+0.153
Neg logit contributions
 goodbye-0.057
 new-0.054
 jog-0.053
 stranger-0.051
 bully-0.049
Token face
Token ID1986
Feature activation-9.87e-01

Pos logit contributions
mmm+0.055
Finally+0.053
ions+0.051
mmmm+0.049
icer+0.048
Neg logit contributions
 goodbye-0.013
 jog-0.012
 new-0.011
 stranger-0.011
 bully-0.011
Token.
Token ID13
Feature activation+1.26e+00

Pos logit contributions
 goodbye+0.028
 jog+0.026
 stranger+0.025
 new+0.024
guard+0.024
Neg logit contributions
mmm-0.051
Finally-0.047
mmmm-0.044
ions-0.043
icer-0.043
Token "
Token ID366
Feature activation+3.22e+00

Pos logit contributions
mmm+0.063
Finally+0.058
icer+0.055
ions+0.055
mmmm+0.054
Neg logit contributions
 goodbye-0.036
 jog-0.033
 new-0.033
 en-0.032
 stranger-0.031
TokenE
Token ID36
Feature activation+7.88e+00

Pos logit contributions
mmm+0.136
ions+0.128
rap+0.124
ths+0.118
els+0.118
Neg logit contributions
 jog-0.102
 bully-0.094
 en-0.093
 seal-0.092
 stranger-0.091
Tokenw
Token ID86
Feature activation+4.18e+00

Pos logit contributions
mmm+0.182
Finally+0.176
ions+0.143
icer+0.135
Eventually+0.131
Neg logit contributions
guard-0.407
 jog-0.394
 goodbye-0.391
 stranger-0.387
 bully-0.386
Token,
Token ID11
Feature activation+1.63e+00

Pos logit contributions
Finally+0.215
mmm+0.202
Eventually+0.186
mmmm+0.183
ions+0.183
Neg logit contributions
 goodbye-0.106
 new-0.097
 forg-0.095
 sad-0.095
 gr-0.094
Token this
Token ID428
Feature activation-2.36e+00

Pos logit contributions
mmm+0.073
Finally+0.065
mmmm+0.061
ions+0.061
icer+0.059
Neg logit contributions
 goodbye-0.053
 jog-0.052
guard-0.051
 stranger-0.050
 bully-0.049
Token is
Token ID318
Feature activation-3.96e-01

Pos logit contributions
 goodbye+0.063
 jog+0.060
guard+0.059
 stranger+0.058
 bully+0.057
Neg logit contributions
mmm-0.120
Finally-0.111
mmmm-0.103
ions-0.103
icer-0.100
Token sour
Token ID11348
Feature activation+1.47e+00

Pos logit contributions
 goodbye+0.009
 new+0.009
 jog+0.009
 en+0.008
 wealthy+0.008
Neg logit contributions
mmm-0.021
Finally-0.020
ions-0.019
mmmm-0.018
icer-0.018
Token
Token ID220
Feature activation+7.44e-01

Pos logit contributions
 goodbye+0.042
 jog+0.040
guard+0.037
 stranger+0.037
 en+0.037
Neg logit contributions
mmm-0.087
Finally-0.080
icer-0.075
ions-0.075
mmmm-0.075
Token
Token ID198
Feature activation-1.48e+00

Pos logit contributions
mmm+0.041
Finally+0.037
mmmm+0.035
ions+0.035
icer+0.034
Neg logit contributions
 goodbye-0.017
 jog-0.016
guard-0.016
 stranger-0.015
 bully-0.015
Token
Token ID198
Feature activation-2.00e+00

Pos logit contributions
 jog+0.023
 goodbye+0.022
 stranger+0.022
 new+0.022
guard+0.021
Neg logit contributions
mmm-0.089
olk-0.079
ra-0.079
ions-0.078
mmmm-0.078
TokenAfter
Token ID3260
Feature activation+1.58e+00

Pos logit contributions
 jog+0.071
 stranger+0.067
guard+0.067
 sport+0.065
 youth+0.065
Neg logit contributions
mmm-0.082
olk-0.072
icer-0.071
ions-0.070
els-0.069
Token the
Token ID262
Feature activation-3.14e+00

Pos logit contributions
mmm+0.086
Finally+0.080
icer+0.077
mmmm+0.075
ions+0.073
Neg logit contributions
 goodbye-0.040
 jog-0.037
 stranger-0.034
 new-0.033
guard-0.033
Token concert
Token ID10010
Feature activation-8.71e+00

Pos logit contributions
 goodbye+0.077
 jog+0.074
guard+0.071
 stranger+0.070
 bully+0.069
Neg logit contributions
mmm-0.167
Finally-0.154
mmmm-0.144
ions-0.144
icer-0.140
Token,
Token ID11
Feature activation-2.62e-01

Pos logit contributions
 stranger+0.300
 jog+0.299
 goodbye+0.298
guard+0.294
 bully+0.293
Neg logit contributions
mmm-0.342
Finally-0.304
ions-0.289
ra-0.276
mmmm-0.272
Token Lily
Token ID20037
Feature activation+4.31e-01

Pos logit contributions
 goodbye+0.007
 jog+0.007
guard+0.007
 bully+0.007
 stranger+0.007
Neg logit contributions
mmm-0.013
Finally-0.012
ions-0.011
mmmm-0.011
icer-0.011
Token's
Token ID338
Feature activation-4.54e+00

Pos logit contributions
mmm+0.019
Finally+0.018
ra+0.017
icer+0.016
 hours+0.016
Neg logit contributions
 goodbye-0.012
guard-0.012
 stranger-0.012
 aut-0.012
 bully-0.011
Token mom
Token ID1995
Feature activation+1.49e+00

Pos logit contributions
guard+0.126
 goodbye+0.125
 stranger+0.121
 jog+0.121
 bully+0.120
Neg logit contributions
mmm-0.205
Finally-0.194
ra-0.176
ions-0.175
mmmm-0.171
Token said
Token ID531
Feature activation-2.61e-01

Pos logit contributions
mmm+0.071
Finally+0.065
ions+0.061
mmmm+0.060
icer+0.059
Neg logit contributions
 goodbye-0.044
 jog-0.042
guard-0.041
 stranger-0.041
 bully-0.040
Token concert
Token ID10010
Feature activation-6.61e+00

Pos logit contributions
 goodbye+0.041
eal+0.040
guard+0.040
 en+0.039
 bully+0.038
Neg logit contributions
Finally-0.060
mmm-0.058
icer-0.050
ions-0.050
Eventually-0.050
Token.
Token ID13
Feature activation-3.06e-01

Pos logit contributions
 bully+0.236
guard+0.234
 stranger+0.233
 seal+0.221
 jog+0.220
Neg logit contributions
mmm-0.249
Finally-0.234
ions-0.211
 hours-0.203
ra-0.200
Token
Token ID198
Feature activation-2.09e-01

Pos logit contributions
 goodbye+0.010
guard+0.010
 jog+0.010
 stranger+0.009
 bully+0.009
Neg logit contributions
mmm-0.014
Finally-0.013
ions-0.012
mmmm-0.012
icer-0.011
Token
Token ID198
Feature activation-8.90e-01

Pos logit contributions
 jog+0.003
 goodbye+0.003
 new+0.003
 stranger+0.003
guard+0.003
Neg logit contributions
mmm-0.013
ions-0.011
mmmm-0.011
Finally-0.011
icer-0.011
TokenThe
Token ID464
Feature activation-8.23e-01

Pos logit contributions
 jog+0.037
 goodbye+0.037
 stranger+0.036
guard+0.035
 wealthy+0.035
Neg logit contributions
mmm-0.032
ions-0.026
mmmm-0.026
icer-0.026
Finally-0.025
Token concert
Token ID10010
Feature activation-8.68e+00

Pos logit contributions
 goodbye+0.026
 His+0.025
 bully+0.025
eal+0.025
 aut+0.025
Neg logit contributions
Finally-0.032
mmm-0.031
 hours-0.027
Mom-0.027
Eventually-0.027
Token was
Token ID373
Feature activation-2.01e-01

Pos logit contributions
 jog+0.264
 aut+0.257
 goodbye+0.254
 stranger+0.254
 bully+0.252
Neg logit contributions
mmm-0.346
Finally-0.340
ra-0.317
ions-0.312
 hours-0.310
Token amazing
Token ID4998
Feature activation-9.34e-01

Pos logit contributions
guard+0.006
 jog+0.006
 goodbye+0.006
 bully+0.006
 stranger+0.006
Neg logit contributions
mmm-0.009
Finally-0.009
ions-0.008
mmmm-0.008
icer-0.008
Token and
Token ID290
Feature activation-1.17e+00

Pos logit contributions
 goodbye+0.033
 jog+0.032
guard+0.031
 stranger+0.031
 bully+0.030
Neg logit contributions
mmm-0.040
Finally-0.036
ions-0.033
mmmm-0.033
icer-0.032
Token Emma
Token ID18966
Feature activation+4.73e-01

Pos logit contributions
 jog+0.035
guard+0.035
 bully+0.035
 goodbye+0.034
 seal+0.033
Neg logit contributions
mmm-0.053
Finally-0.048
ions-0.045
mmmm-0.043
 hours-0.043
Token sang
Token ID25889
Feature activation-2.76e+00

Pos logit contributions
mmm+0.022
Finally+0.021
ra+0.020
ions+0.019
mmmm+0.018
Neg logit contributions
 goodbye-0.013
guard-0.013
 stranger-0.013
 jog-0.012
 bully-0.012
Token.
Token ID13
Feature activation-4.12e-01

Pos logit contributions
 goodbye+0.040
 jog+0.039
guard+0.038
 stranger+0.038
 bully+0.037
Neg logit contributions
mmm-0.057
Finally-0.052
ions-0.048
mmmm-0.048
icer-0.046
Token
Token ID198
Feature activation-3.52e-01

Pos logit contributions
 goodbye+0.010
 jog+0.009
guard+0.009
 stranger+0.009
 bully+0.009
Neg logit contributions
mmm-0.022
Finally-0.020
mmmm-0.019
ions-0.019
icer-0.019
Token
Token ID198
Feature activation-1.08e+00

Pos logit contributions
 jog+0.006
guard+0.006
 stranger+0.006
 goodbye+0.005
 new+0.005
Neg logit contributions
mmm-0.022
mmmm-0.019
ions-0.019
Finally-0.019
olk-0.019
TokenHe
Token ID1544
Feature activation+4.84e-01

Pos logit contributions
 jog+0.036
guard+0.035
 stranger+0.035
 goodbye+0.035
 bully+0.033
Neg logit contributions
mmm-0.048
ions-0.041
Finally-0.040
mmmm-0.040
icer-0.039
Token asked
Token ID1965
Feature activation-6.38e-01

Pos logit contributions
mmm+0.026
Finally+0.024
mmmm+0.022
ions+0.022
icer+0.021
Neg logit contributions
 goodbye-0.012
 jog-0.011
guard-0.011
 stranger-0.011
 bully-0.011
Token them
Token ID606
Feature activation-8.38e+00

Pos logit contributions
 jog+0.010
guard+0.010
 goodbye+0.010
 bully+0.009
 stranger+0.009
Neg logit contributions
mmm-0.038
Finally-0.036
ions-0.035
mmmm-0.034
icer-0.033
Token what
Token ID644
Feature activation-2.52e+00

Pos logit contributions
 goodbye+0.268
 jog+0.262
guard+0.260
 bully+0.259
 stranger+0.255
Neg logit contributions
mmm-0.372
Finally-0.337
ions-0.317
mmmm-0.308
icer-0.295
Token was
Token ID373
Feature activation-1.70e-01

Pos logit contributions
eal+0.088
 goodbye+0.083
 jog+0.075
 bully+0.074
guard+0.070
Neg logit contributions
mmm-0.102
ions-0.097
Finally-0.087
mmmm-0.084
 hours-0.083
Token happening
Token ID5836
Feature activation-3.40e+00

Pos logit contributions
 goodbye+0.005
 jog+0.005
guard+0.005
 bully+0.005
 stranger+0.005
Neg logit contributions
mmm-0.008
Finally-0.007
ions-0.007
mmmm-0.007
icer-0.006
Token,
Token ID11
Feature activation+9.14e-01

Pos logit contributions
 goodbye+0.079
 jog+0.076
guard+0.075
 stranger+0.073
 new+0.071
Neg logit contributions
mmm-0.187
Finally-0.175
mmmm-0.164
icer-0.160
ions-0.160
Token and
Token ID290
Feature activation-2.19e+00

Pos logit contributions
mmm+0.043
Finally+0.039
ions+0.036
mmmm+0.036
icer+0.035
Neg logit contributions
 goodbye-0.027
 jog-0.027
guard-0.026
 stranger-0.026
 bully-0.026
Token!"
Token ID2474
Feature activation-3.98e-01

Pos logit contributions
mmm+0.002
ions+0.002
Finally+0.002
icer+0.002
els+0.002
Neg logit contributions
 goodbye-0.001
 new-0.001
 wealthy-0.001
 friendly-0.001
 jog-0.001
Token
Token ID198
Feature activation-8.04e-01

Pos logit contributions
guard+0.010
 goodbye+0.010
 stranger+0.010
 jog+0.010
 bully+0.010
Neg logit contributions
mmm-0.021
Finally-0.019
mmmm-0.018
ions-0.018
icer-0.017
Token
Token ID198
Feature activation-1.31e+00

Pos logit contributions
 goodbye+0.017
 jog+0.016
guard+0.016
 stranger+0.015
 new+0.015
Neg logit contributions
mmm-0.045
Finally-0.041
ions-0.039
mmmm-0.039
icer-0.038
TokenWhen
Token ID2215
Feature activation-2.69e-01

Pos logit contributions
 jog+0.048
 new+0.044
 sport+0.044
 goodbye+0.043
 stranger+0.042
Neg logit contributions
mmm-0.055
ions-0.050
ocol-0.049
icer-0.048
mmmm-0.047
Token the
Token ID262
Feature activation-3.12e+00

Pos logit contributions
 goodbye+0.005
 jog+0.004
 new+0.004
 stranger+0.003
 wealthy+0.003
Neg logit contributions
mmm-0.017
Finally-0.016
mmmm-0.015
icer-0.015
ions-0.015
Token concert
Token ID10010
Feature activation-8.34e+00

Pos logit contributions
 disl+0.101
 forg+0.094
 en+0.091
mit+0.088
eal+0.087
Neg logit contributions
Finally-0.117
mmm-0.115
 hours-0.111
 months-0.106
ions-0.105
Token started
Token ID2067
Feature activation+2.33e-01

Pos logit contributions
 aut+0.274
 en+0.273
 jog+0.271
 wife+0.269
 stranger+0.268
Neg logit contributions
mmm-0.320
Finally-0.290
ra-0.276
ions-0.275
 hours-0.263
Token,
Token ID11
Feature activation+8.87e-01

Pos logit contributions
mmm+0.011
ions+0.010
Finally+0.009
mmmm+0.009
ra+0.009
Neg logit contributions
guard-0.007
 bully-0.007
 stranger-0.007
 goodbye-0.006
 seal-0.006
Token Lily
Token ID20037
Feature activation+1.07e+00

Pos logit contributions
mmm+0.048
Finally+0.044
mmmm+0.042
ions+0.041
icer+0.040
Neg logit contributions
 goodbye-0.021
 jog-0.020
guard-0.020
 stranger-0.019
 bully-0.019
Token saw
Token ID2497
Feature activation+9.28e-01

Pos logit contributions
mmm+0.050
Finally+0.049
ra+0.046
 hours+0.042
Eventually+0.042
Neg logit contributions
guard-0.029
 goodbye-0.029
 stranger-0.028
 aut-0.026
 bully-0.026
Token a
Token ID257
Feature activation+2.85e-01

Pos logit contributions
mmm+0.042
Finally+0.039
ions+0.038
mmmm+0.036
Eventually+0.034
Neg logit contributions
 jog-0.027
 goodbye-0.026
guard-0.026
 bully-0.025
eal-0.024
Token stage
Token ID3800
Feature activation-4.33e+00

Pos logit contributions
mmm+0.034
Finally+0.031
mmmm+0.029
ions+0.029
icer+0.028
Neg logit contributions
 goodbye-0.019
 jog-0.018
 stranger-0.018
guard-0.017
 bully-0.017
Token!"
Token ID2474
Feature activation+3.13e-01

Pos logit contributions
 goodbye+0.155
 jog+0.150
guard+0.147
 stranger+0.146
 bully+0.144
Neg logit contributions
mmm-0.180
Finally-0.162
ions-0.148
mmmm-0.148
icer-0.143
Token
Token ID198
Feature activation-8.01e-01

Pos logit contributions
mmm+0.016
Finally+0.015
mmmm+0.014
ions+0.014
icer+0.014
Neg logit contributions
 goodbye-0.008
 jog-0.008
guard-0.007
 stranger-0.007
 bully-0.007
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
 jog+0.013
 goodbye+0.012
 stranger+0.012
guard+0.012
 new+0.011
Neg logit contributions
mmm-0.049
Finally-0.043
ions-0.043
icer-0.043
mmmm-0.043
TokenThe
Token ID464
Feature activation-1.73e+00

Pos logit contributions
 jog+0.047
 stranger+0.044
guard+0.044
 youth+0.043
 bully+0.042
Neg logit contributions
mmm-0.058
icer-0.051
ions-0.050
olk-0.048
mmmm-0.048
Token music
Token ID2647
Feature activation-8.26e+00

Pos logit contributions
 goodbye+0.036
 jog+0.034
guard+0.033
 stranger+0.032
 bully+0.032
Neg logit contributions
mmm-0.098
Finally-0.091
mmmm-0.085
ions-0.085
icer-0.083
Token stopped
Token ID5025
Feature activation-1.46e+00

Pos logit contributions
 jog+0.203
 wealthy+0.200
 youth+0.197
 aut+0.197
 goodbye+0.195
Neg logit contributions
mmm-0.383
Finally-0.364
ions-0.349
ra-0.343
mmmm-0.322
Token.
Token ID13
Feature activation-6.98e-01

Pos logit contributions
 jog+0.035
 goodbye+0.035
 new+0.033
guard+0.032
 en+0.032
Neg logit contributions
mmm-0.079
Finally-0.074
mmmm-0.070
ions-0.068
icer-0.066
Token The
Token ID383
Feature activation-2.68e-02

Pos logit contributions
 goodbye+0.019
 jog+0.018
guard+0.017
 stranger+0.017
 bully+0.016
Neg logit contributions
mmm-0.036
Finally-0.033
ions-0.031
mmmm-0.031
icer-0.030
Token lights
Token ID7588
Feature activation-2.54e+00

Pos logit contributions
 goodbye+0.001
 jog+0.001
guard+0.001
 stranger+0.001
 bully+0.001
Neg logit contributions
mmm-0.001
Finally-0.001
ions-0.001
mmmm-0.001
icer-0.001
Token flashed
Token ID30050
Feature activation-4.18e-01

Pos logit contributions
 bully+0.074
 jog+0.073
 youth+0.072
 stranger+0.072
 aut+0.071
Neg logit contributions
mmm-0.109
Finally-0.102
ions-0.100
ra-0.094
mmmm-0.090
Token was
Token ID373
Feature activation-3.03e-01

Pos logit contributions
 goodbye+0.093
guard+0.091
 jog+0.091
 stranger+0.088
 bully+0.087
Neg logit contributions
mmm-0.193
Finally-0.177
ions-0.168
mmmm-0.164
ra-0.160
Token shocked
Token ID11472
Feature activation-2.78e+00

Pos logit contributions
 goodbye+0.008
 jog+0.007
guard+0.007
 stranger+0.007
 bully+0.007
Neg logit contributions
mmm-0.016
Finally-0.015
mmmm-0.014
ions-0.014
icer-0.013
Token.
Token ID13
Feature activation-7.68e-01

Pos logit contributions
 goodbye+0.081
 jog+0.076
guard+0.076
 stranger+0.075
 bully+0.072
Neg logit contributions
mmm-0.138
Finally-0.128
mmmm-0.118
ions-0.117
icer-0.117
Token She
Token ID1375
Feature activation+1.80e+00

Pos logit contributions
 goodbye+0.017
 jog+0.016
 en+0.016
 stranger+0.015
 bully+0.015
Neg logit contributions
mmm-0.042
Finally-0.039
ions-0.037
icer-0.037
mmmm-0.036
Token asked
Token ID1965
Feature activation+7.67e-02

Pos logit contributions
mmm+0.100
Finally+0.092
mmmm+0.087
ions+0.087
icer+0.085
Neg logit contributions
 goodbye-0.041
 jog-0.039
 stranger-0.038
guard-0.037
 bully-0.037
Token them
Token ID606
Feature activation-8.15e+00

Pos logit contributions
mmm+0.004
Finally+0.004
icer+0.004
mmmm+0.004
ions+0.004
Neg logit contributions
 goodbye-0.002
 new-0.002
 jog-0.002
 stranger-0.002
 youth-0.002
Token what
Token ID644
Feature activation-2.20e+00

Pos logit contributions
 jog+0.273
 goodbye+0.272
guard+0.268
 bully+0.267
 stranger+0.261
Neg logit contributions
mmm-0.340
Finally-0.307
ions-0.289
mmmm-0.277
icer-0.263
Token happened
Token ID3022
Feature activation-9.73e-01

Pos logit contributions
eal+0.073
 goodbye+0.073
 jog+0.067
 wife+0.062
 aut+0.061
Neg logit contributions
mmm-0.093
ions-0.086
Finally-0.079
mmmm-0.078
 hours-0.072
Token.
Token ID13
Feature activation-4.45e-01

Pos logit contributions
 goodbye+0.026
 jog+0.025
guard+0.024
 stranger+0.024
 bully+0.023
Neg logit contributions
mmm-0.049
Finally-0.046
mmmm-0.043
ions-0.042
icer-0.042
Token They
Token ID1119
Feature activation-2.70e-01

Pos logit contributions
 goodbye+0.011
 jog+0.010
 stranger+0.009
guard+0.009
 bully+0.009
Neg logit contributions
mmm-0.024
Finally-0.022
ions-0.021
mmmm-0.021
icer-0.021
Token told
Token ID1297
Feature activation+1.63e-01

Pos logit contributions
 goodbye+0.007
 jog+0.006
guard+0.006
 stranger+0.006
 bully+0.006
Neg logit contributions
mmm-0.014
Finally-0.013
ions-0.012
mmmm-0.012
icer-0.012
Token know
Token ID760
Feature activation-8.68e-01

Pos logit contributions
 goodbye+0.014
guard+0.013
 jog+0.013
 stranger+0.013
 aut+0.012
Neg logit contributions
mmm-0.028
Finally-0.025
mmmm-0.023
ions-0.023
ra-0.022
Token why
Token ID1521
Feature activation-2.09e+00

Pos logit contributions
 goodbye+0.026
 jog+0.024
 new+0.024
 stranger+0.023
guard+0.023
Neg logit contributions
mmm-0.043
Finally-0.040
mmmm-0.037
icer-0.037
ions-0.035
Token.
Token ID13
Feature activation-1.70e+00

Pos logit contributions
 goodbye+0.054
 jog+0.052
 new+0.049
 stranger+0.049
guard+0.048
Neg logit contributions
mmm-0.108
Finally-0.104
icer-0.094
mmmm-0.094
ions-0.092
Token He
Token ID679
Feature activation+3.19e-01

Pos logit contributions
 goodbye+0.038
 jog+0.036
 en+0.035
 bully+0.034
 stranger+0.034
Neg logit contributions
mmm-0.091
Finally-0.085
ions-0.081
icer-0.079
mmmm-0.079
Token asked
Token ID1965
Feature activation-2.76e-01

Pos logit contributions
mmm+0.017
Finally+0.016
mmmm+0.015
ions+0.015
icer+0.014
Neg logit contributions
 goodbye-0.008
 jog-0.007
guard-0.007
 stranger-0.007
 bully-0.007
Token them
Token ID606
Feature activation-8.11e+00

Pos logit contributions
 goodbye+0.005
 jog+0.004
 stranger+0.004
guard+0.004
 new+0.004
Neg logit contributions
mmm-0.017
Finally-0.016
mmmm-0.015
icer-0.015
ions-0.015
Token what
Token ID644
Feature activation-2.12e+00

Pos logit contributions
 bully+0.285
 jog+0.283
guard+0.281
eal+0.281
 goodbye+0.279
Neg logit contributions
mmm-0.310
Finally-0.277
ions-0.267
mmmm-0.244
els-0.237
Token was
Token ID373
Feature activation+2.64e-01

Pos logit contributions
eal+0.081
 goodbye+0.075
 jog+0.066
 wife+0.062
 en+0.061
Neg logit contributions
mmm-0.084
ions-0.078
mmmm-0.069
Finally-0.067
els-0.063
Token wrong
Token ID2642
Feature activation+6.22e-01

Pos logit contributions
mmm+0.012
Finally+0.011
ions+0.010
mmmm+0.010
ra+0.010
Neg logit contributions
 jog-0.008
 goodbye-0.008
eal-0.007
guard-0.007
 bully-0.007
Token,
Token ID11
Feature activation+1.05e+00

Pos logit contributions
mmm+0.031
Finally+0.028
mmmm+0.026
ions+0.026
icer+0.026
Neg logit contributions
 goodbye-0.018
 jog-0.017
guard-0.017
 stranger-0.016
 bully-0.016
Token but
Token ID475
Feature activation+7.82e-02

Pos logit contributions
mmm+0.053
Finally+0.048
mmmm+0.045
ions+0.045
icer+0.044
Neg logit contributions
 goodbye-0.029
 jog-0.028
guard-0.027
 stranger-0.027
 bully-0.026
Token One
Token ID1881
Feature activation+4.22e+00

Pos logit contributions
 jog+0.035
 goodbye+0.034
 new+0.034
 aut+0.032
 stranger+0.031
Neg logit contributions
mmm-0.043
Finally-0.039
ions-0.037
ra-0.036
mmmm-0.036
Token day
Token ID1110
Feature activation-1.55e+00

Pos logit contributions
mmm+0.116
Finally+0.102
Mom+0.095
ousy+0.090
mmmm+0.088
Neg logit contributions
 bully-0.195
 goodbye-0.191
guard-0.187
 aut-0.184
 forg-0.181
Token,
Token ID11
Feature activation-1.48e-01

Pos logit contributions
 goodbye+0.043
 jog+0.040
 new+0.039
 stranger+0.037
 bully+0.036
Neg logit contributions
mmm-0.079
Finally-0.073
icer-0.070
mmmm-0.069
ions-0.068
Token she
Token ID673
Feature activation-6.42e-01

Pos logit contributions
 goodbye+0.004
 jog+0.004
 new+0.004
 stranger+0.003
 wealthy+0.003
Neg logit contributions
mmm-0.008
Finally-0.007
icer-0.007
mmmm-0.007
ions-0.007
Token asked
Token ID1965
Feature activation-3.30e-01

Pos logit contributions
 goodbye+0.023
 aut+0.021
guard+0.020
 stranger+0.020
 bully+0.019
Neg logit contributions
Finally-0.024
mmm-0.024
ra-0.022
icer-0.021
Mom-0.021
Token them
Token ID606
Feature activation-8.09e+00

Pos logit contributions
 goodbye+0.009
guard+0.009
 jog+0.009
 bully+0.008
 stranger+0.008
Neg logit contributions
mmm-0.017
Finally-0.015
ions-0.014
mmmm-0.014
icer-0.013
Token if
Token ID611
Feature activation-5.03e-01

Pos logit contributions
 bully+0.238
guard+0.232
 goodbye+0.232
eal+0.230
 jog+0.227
Neg logit contributions
mmm-0.366
ions-0.327
Finally-0.326
mmmm-0.302
els-0.286
Token they
Token ID484
Feature activation-3.20e+00

Pos logit contributions
eal+0.017
 bully+0.016
 goodbye+0.016
 jog+0.016
 aut+0.015
Neg logit contributions
mmm-0.021
Finally-0.018
ions-0.018
mmmm-0.017
ra-0.016
Token wanted
Token ID2227
Feature activation+5.97e-01

Pos logit contributions
 goodbye+0.126
 bully+0.122
guard+0.122
 aut+0.120
 new+0.118
Neg logit contributions
mmm-0.103
Finally-0.095
ions-0.087
ra-0.083
 hours-0.083
Token to
Token ID284
Feature activation-1.05e+00

Pos logit contributions
mmm+0.031
ions+0.029
Finally+0.028
mmmm+0.027
 hours+0.026
Neg logit contributions
 bully-0.013
eal-0.013
guard-0.012
 en-0.012
 goodbye-0.011
Token go
Token ID467
Feature activation-1.72e+00

Pos logit contributions
guard+0.030
 goodbye+0.030
 stranger+0.029
 bully+0.028
 en+0.027
Neg logit contributions
mmm-0.050
Finally-0.046
mmmm-0.042
ions-0.041
ra-0.040
TokenHello
Token ID15496
Feature activation-2.17e+00

Pos logit contributions
mmm+0.015
Finally+0.013
ions+0.013
mmmm+0.012
ra+0.012
Neg logit contributions
guard-0.016
 stranger-0.015
 bully-0.015
 jog-0.015
 seal-0.015
Token,
Token ID11
Feature activation-1.19e+00

Pos logit contributions
 goodbye+0.084
 jog+0.082
guard+0.081
 stranger+0.079
 bully+0.079
Neg logit contributions
mmm-0.084
Finally-0.073
mmmm-0.068
ions-0.067
icer-0.064
Token Lily
Token ID20037
Feature activation-2.08e-01

Pos logit contributions
 goodbye+0.031
guard+0.031
 jog+0.030
 stranger+0.028
 bully+0.028
Neg logit contributions
mmm-0.059
Finally-0.053
mmmm-0.050
ions-0.050
icer-0.047
Token,"
Token ID553
Feature activation+1.23e+00

Pos logit contributions
 goodbye+0.007
 jog+0.007
guard+0.007
 stranger+0.007
 bully+0.007
Neg logit contributions
mmm-0.009
Finally-0.008
mmmm-0.007
ions-0.007
icer-0.007
Token a
Token ID257
Feature activation-3.63e+00

Pos logit contributions
mmm+0.062
Finally+0.056
mmmm+0.052
ions+0.052
icer+0.050
Neg logit contributions
 goodbye-0.033
 jog-0.032
guard-0.032
 stranger-0.031
 bully-0.030
Token voice
Token ID3809
Feature activation-8.09e+00

Pos logit contributions
 goodbye+0.063
 jog+0.060
guard+0.057
 stranger+0.055
 bully+0.054
Neg logit contributions
mmm-0.216
Finally-0.201
mmmm-0.189
ions-0.189
icer-0.184
Token said
Token ID531
Feature activation-1.44e+00

Pos logit contributions
 jog+0.242
 goodbye+0.232
 sport+0.225
 youth+0.224
 wealthy+0.221
Neg logit contributions
mmm-0.362
Finally-0.323
ions-0.320
els-0.305
mmmm-0.303
Token.
Token ID13
Feature activation-1.91e+00

Pos logit contributions
 jog+0.058
guard+0.056
 stranger+0.055
 bully+0.054
 sport+0.054
Neg logit contributions
mmm-0.052
Finally-0.044
ions-0.042
ra-0.041
mmmm-0.040
Token Lily
Token ID20037
Feature activation+6.06e-01

Pos logit contributions
 goodbye+0.050
 jog+0.049
guard+0.048
 stranger+0.046
 bully+0.046
Neg logit contributions
mmm-0.097
Finally-0.089
ions-0.083
mmmm-0.082
icer-0.079
Token turned
Token ID2900
Feature activation-1.14e+00

Pos logit contributions
mmm+0.028
Finally+0.026
ra+0.025
mmmm+0.022
icer+0.022
Neg logit contributions
 goodbye-0.017
guard-0.017
 aut-0.017
 stranger-0.016
 youth-0.016
Token around
Token ID1088
Feature activation-1.33e+00

Pos logit contributions
 jog+0.030
guard+0.029
 wife+0.028
 sport+0.028
 bully+0.028
Neg logit contributions
mmm-0.051
Finally-0.049
ions-0.048
els-0.046
ra-0.046
Token.
Token ID13
Feature activation-4.80e-01

Pos logit contributions
mmm+0.193
Finally+0.176
mmmm+0.166
icer+0.159
ions+0.159
Neg logit contributions
 goodbye-0.108
 jog-0.105
guard-0.101
 stranger-0.100
 new-0.098
Token
Token ID198
Feature activation-3.04e-01

Pos logit contributions
guard+0.014
 jog+0.014
 bully+0.014
 goodbye+0.014
 stranger+0.014
Neg logit contributions
mmm-0.022
Finally-0.021
mmmm-0.018
ions-0.018
icer-0.018
Token
Token ID198
Feature activation-1.01e+00

Pos logit contributions
 goodbye+0.006
 jog+0.006
guard+0.006
 stranger+0.006
 new+0.006
Neg logit contributions
mmm-0.017
Finally-0.016
ions-0.015
mmmm-0.015
icer-0.015
TokenJimmy
Token ID40335
Feature activation-1.17e+00

Pos logit contributions
 goodbye+0.039
 jog+0.038
guard+0.037
 stranger+0.037
 bully+0.036
Neg logit contributions
mmm-0.040
Finally-0.036
mmmm-0.032
ions-0.032
icer-0.031
Token asked
Token ID1965
Feature activation-6.90e-01

Pos logit contributions
 goodbye+0.031
guard+0.029
 jog+0.028
 stranger+0.028
 aut+0.028
Neg logit contributions
mmm-0.058
Finally-0.055
ra-0.050
ions-0.049
mmmm-0.049
Token them
Token ID606
Feature activation-8.07e+00

Pos logit contributions
 goodbye+0.016
 jog+0.016
guard+0.015
 bully+0.015
 stranger+0.015
Neg logit contributions
mmm-0.037
Finally-0.034
ions-0.032
mmmm-0.032
icer-0.031
Token for
Token ID329
Feature activation+4.09e-01

Pos logit contributions
 goodbye+0.277
 jog+0.272
 bully+0.271
guard+0.271
 stranger+0.266
Neg logit contributions
mmm-0.330
Finally-0.296
ions-0.282
mmmm-0.266
icer-0.252
Token help
Token ID1037
Feature activation-1.95e+00

Pos logit contributions
mmm+0.022
Finally+0.020
mmmm+0.019
icer+0.019
ions+0.019
Neg logit contributions
 goodbye-0.010
 jog-0.010
 new-0.009
guard-0.009
 stranger-0.009
Token and
Token ID290
Feature activation-1.79e+00

Pos logit contributions
 jog+0.048
 goodbye+0.048
 new+0.045
guard+0.045
 youth+0.043
Neg logit contributions
mmm-0.105
Finally-0.097
mmmm-0.093
icer-0.089
ions-0.088
Token they
Token ID484
Feature activation-1.92e+00

Pos logit contributions
 goodbye+0.046
 jog+0.046
 stranger+0.043
guard+0.043
 bully+0.042
Neg logit contributions
mmm-0.087
Finally-0.081
ions-0.077
mmmm-0.073
ra-0.071
Token were
Token ID547
Feature activation+1.34e+00

Pos logit contributions
 goodbye+0.051
 jog+0.049
guard+0.048
 stranger+0.048
 bully+0.047
Neg logit contributions
mmm-0.096
Finally-0.089
ions-0.083
mmmm-0.082
icer-0.079
Token One
Token ID1881
Feature activation+4.52e+00

Pos logit contributions
 goodbye+0.032
 jog+0.031
 stranger+0.029
guard+0.029
 bully+0.029
Neg logit contributions
mmm-0.047
Finally-0.043
mmmm-0.040
ions-0.040
icer-0.039
Token day
Token ID1110
Feature activation-1.39e+00

Pos logit contributions
mmm+0.088
Finally+0.079
Mom+0.076
 hour+0.071
 hours+0.071
Neg logit contributions
 bully-0.231
 disl-0.225
 forg-0.221
eal-0.219
 aut-0.217
Token,
Token ID11
Feature activation+2.67e-02

Pos logit contributions
 goodbye+0.048
 jog+0.047
guard+0.047
 stranger+0.046
 bully+0.046
Neg logit contributions
mmm-0.060
Finally-0.053
ions-0.049
mmmm-0.049
icer-0.047
Token she
Token ID673
Feature activation-4.02e-01

Pos logit contributions
mmm+0.001
Finally+0.001
ions+0.001
mmmm+0.001
icer+0.001
Neg logit contributions
 goodbye-0.001
 jog-0.001
guard-0.001
 stranger-0.001
 bully-0.001
Token asked
Token ID1965
Feature activation-1.19e-01

Pos logit contributions
 goodbye+0.013
 aut+0.012
guard+0.012
 stranger+0.012
 bully+0.012
Neg logit contributions
Finally-0.016
mmm-0.016
ra-0.015
icer-0.015
 hours-0.014
Token them
Token ID606
Feature activation-8.05e+00

Pos logit contributions
 goodbye+0.003
guard+0.003
 jog+0.003
 stranger+0.003
 bully+0.003
Neg logit contributions
mmm-0.006
Finally-0.006
ions-0.005
mmmm-0.005
icer-0.005
Token if
Token ID611
Feature activation-1.66e-01

Pos logit contributions
 bully+0.216
eal+0.209
 jog+0.207
guard+0.205
 goodbye+0.203
Neg logit contributions
mmm-0.389
ions-0.345
Finally-0.345
mmmm-0.324
ousy-0.306
Token they
Token ID484
Feature activation-2.81e+00

Pos logit contributions
eal+0.006
 bully+0.006
 jog+0.005
 aut+0.005
 goodbye+0.005
Neg logit contributions
mmm-0.006
Finally-0.006
ions-0.005
ra-0.005
mmmm-0.005
Token could
Token ID714
Feature activation+3.18e+00

Pos logit contributions
 bully+0.112
 disl+0.110
 sport+0.109
 en+0.106
 goodbye+0.105
Neg logit contributions
mmm-0.086
Finally-0.081
ra-0.076
ions-0.069
 hours-0.068
Token go
Token ID467
Feature activation-1.56e+00

Pos logit contributions
mmm+0.166
Finally+0.153
mmmm+0.141
ions+0.141
ra+0.137
Neg logit contributions
 goodbye-0.079
guard-0.075
 stranger-0.074
 bully-0.073
 jog-0.071
Token on
Token ID319
Feature activation+1.31e-01

Pos logit contributions
 bully+0.045
 goodbye+0.043
 stranger+0.043
guard+0.041
 en+0.041
Neg logit contributions
mmm-0.072
Finally-0.066
ions-0.062
mmmm-0.059
icer-0.058
Token
Token ID198
Feature activation-9.32e-01

Pos logit contributions
 jog+0.004
 goodbye+0.004
 stranger+0.004
guard+0.004
 new+0.004
Neg logit contributions
mmm-0.014
icer-0.013
ions-0.013
Finally-0.013
mmmm-0.013
TokenThe
Token ID464
Feature activation-7.94e-01

Pos logit contributions
 goodbye+0.029
 jog+0.028
guard+0.028
 stranger+0.027
 bully+0.027
Neg logit contributions
mmm-0.044
Finally-0.038
ions-0.037
mmmm-0.037
icer-0.037
Token little
Token ID1310
Feature activation-5.62e-01

Pos logit contributions
 goodbye+0.017
guard+0.016
 jog+0.016
 aut+0.016
 bully+0.015
Neg logit contributions
mmm-0.041
Finally-0.039
ions-0.036
ra-0.035
mmmm-0.035
Token girl
Token ID2576
Feature activation-1.60e+00

Pos logit contributions
 goodbye+0.014
 aut+0.014
 jog+0.014
 bully+0.014
guard+0.014
Neg logit contributions
mmm-0.024
ions-0.023
Finally-0.023
ra-0.022
 hours-0.021
Token asked
Token ID1965
Feature activation-4.66e-01

Pos logit contributions
 goodbye+0.037
 jog+0.036
guard+0.035
 stranger+0.034
 bully+0.034
Neg logit contributions
mmm-0.086
Finally-0.080
mmmm-0.074
ions-0.074
ra-0.072
Token them
Token ID606
Feature activation-8.02e+00

Pos logit contributions
 goodbye+0.013
 jog+0.012
 stranger+0.012
guard+0.012
 new+0.011
Neg logit contributions
mmm-0.024
Finally-0.022
mmmm-0.021
ions-0.020
icer-0.020
Token where
Token ID810
Feature activation-5.08e+00

Pos logit contributions
 goodbye+0.275
 jog+0.270
guard+0.266
 bully+0.263
 stranger+0.262
Neg logit contributions
mmm-0.339
Finally-0.303
ions-0.284
mmmm-0.278
icer-0.265
Token the
Token ID262
Feature activation-1.83e+00

Pos logit contributions
eal+0.184
 bully+0.170
 jog+0.163
 youth+0.161
 aut+0.158
Neg logit contributions
ions-0.176
mmm-0.174
Finally-0.149
ra-0.144
 hours-0.142
Token print
Token ID3601
Feature activation-3.10e+00

Pos logit contributions
 goodbye+0.060
guard+0.058
 jog+0.057
 stranger+0.056
 youth+0.054
Neg logit contributions
mmm-0.077
Finally-0.070
ions-0.064
ra-0.064
mmmm-0.064
Token had
Token ID550
Feature activation+4.20e+00

Pos logit contributions
 goodbye+0.085
 jog+0.085
 youth+0.080
 stranger+0.079
guard+0.078
Neg logit contributions
mmm-0.144
Finally-0.131
ions-0.131
ra-0.122
mmmm-0.122
Token come
Token ID1282
Feature activation-2.39e+00

Pos logit contributions
mmm+0.179
Finally+0.162
ions+0.157
ra+0.156
mmmm+0.151
Neg logit contributions
 jog-0.132
guard-0.129
 goodbye-0.126
 youth-0.126
 stranger-0.125
Token Lily
Token ID20037
Feature activation-4.15e-01

Pos logit contributions
 goodbye+0.030
 jog+0.029
guard+0.027
 stranger+0.027
 bully+0.027
Neg logit contributions
mmm-0.047
Finally-0.045
icer-0.041
mmmm-0.041
ions-0.041
Token just
Token ID655
Feature activation-3.01e+00

Pos logit contributions
 goodbye+0.009
 jog+0.008
guard+0.008
 stranger+0.008
 bully+0.008
Neg logit contributions
mmm-0.024
Finally-0.022
ions-0.021
mmmm-0.021
icer-0.020
Token smiled
Token ID13541
Feature activation-3.70e+00

Pos logit contributions
 goodbye+0.070
 jog+0.067
guard+0.065
 stranger+0.064
 bully+0.062
Neg logit contributions
mmm-0.164
Finally-0.151
mmmm-0.142
ions-0.142
icer-0.138
Token and
Token ID290
Feature activation-1.87e+00

Pos logit contributions
guard+0.134
 bully+0.131
 jog+0.130
 stranger+0.124
 goodbye+0.122
Neg logit contributions
mmm-0.151
Finally-0.132
mmmm-0.120
ions-0.115
ra-0.113
Token asked
Token ID1965
Feature activation+1.65e-01

Pos logit contributions
guard+0.057
 stranger+0.052
 bully+0.052
 aut+0.051
 jog+0.051
Neg logit contributions
mmm-0.087
Finally-0.079
ra-0.073
mmmm-0.070
 hours-0.068
Token them
Token ID606
Feature activation-8.00e+00

Pos logit contributions
mmm+0.009
Finally+0.009
icer+0.008
mmmm+0.008
ions+0.008
Neg logit contributions
 goodbye-0.004
 new-0.004
 jog-0.004
 stranger-0.004
 youth-0.004
Token politely
Token ID34313
Feature activation+2.41e-01

Pos logit contributions
 bully+0.215
 jog+0.213
 goodbye+0.210
guard+0.208
 stranger+0.204
Neg logit contributions
mmm-0.388
Finally-0.353
ions-0.339
mmmm-0.327
icer-0.309
Token if
Token ID611
Feature activation-1.42e-01

Pos logit contributions
mmm+0.011
Finally+0.010
mmmm+0.009
ions+0.009
ra+0.009
Neg logit contributions
guard-0.007
 goodbye-0.007
 jog-0.007
 bully-0.007
 stranger-0.007
Token they
Token ID484
Feature activation-2.59e+00

Pos logit contributions
eal+0.004
 bully+0.004
 jog+0.004
 goodbye+0.004
 en+0.004
Neg logit contributions
mmm-0.006
Finally-0.005
ions-0.005
mmmm-0.005
ra-0.005
Token could
Token ID714
Feature activation+3.25e+00

Pos logit contributions
 goodbye+0.080
 stranger+0.076
 jog+0.076
 new+0.075
guard+0.075
Neg logit contributions
mmm-0.113
Finally-0.102
ra-0.095
ions-0.095
mmmm-0.094
Token change
Token ID1487
Feature activation-1.92e+00

Pos logit contributions
mmm+0.185
Finally+0.171
mmmm+0.162
ions+0.161
icer+0.160
Neg logit contributions
 goodbye-0.069
 jog-0.069
guard-0.063
 bully-0.061
 stranger-0.061
Token join
Token ID4654
Feature activation-3.64e+00

Pos logit contributions
 goodbye+0.022
guard+0.020
 stranger+0.019
 wealthy+0.019
eal+0.018
Neg logit contributions
mmm-0.043
Finally-0.040
mmmm-0.037
ions-0.037
ra-0.036
Token them
Token ID606
Feature activation-4.10e+00

Pos logit contributions
 goodbye+0.117
 jog+0.113
guard+0.111
 stranger+0.109
 bully+0.108
Neg logit contributions
mmm-0.166
Finally-0.150
ions-0.140
mmmm-0.139
icer-0.135
Token.
Token ID13
Feature activation-3.80e-01

Pos logit contributions
 goodbye+0.137
 jog+0.132
guard+0.130
 stranger+0.130
 bully+0.129
Neg logit contributions
mmm-0.176
Finally-0.157
ions-0.149
mmmm-0.145
icer-0.140
Token He
Token ID679
Feature activation+1.32e+00

Pos logit contributions
 goodbye+0.010
guard+0.010
 jog+0.010
 stranger+0.010
 bully+0.010
Neg logit contributions
mmm-0.019
Finally-0.018
mmmm-0.016
ions-0.016
icer-0.016
Token asked
Token ID1965
Feature activation+1.99e-01

Pos logit contributions
mmm+0.060
Finally+0.058
ra+0.052
ions+0.051
mmmm+0.050
Neg logit contributions
 goodbye-0.037
guard-0.035
 bully-0.034
 jog-0.034
 aut-0.034
Token them
Token ID606
Feature activation-7.97e+00

Pos logit contributions
mmm+0.011
Finally+0.010
mmmm+0.009
ions+0.009
icer+0.009
Neg logit contributions
 goodbye-0.005
 jog-0.005
guard-0.004
 stranger-0.004
 bully-0.004
Token if
Token ID611
Feature activation-1.43e-01

Pos logit contributions
 goodbye+0.261
 bully+0.259
 jog+0.256
guard+0.255
 stranger+0.250
Neg logit contributions
mmm-0.339
Finally-0.305
ions-0.292
mmmm-0.277
icer-0.261
Token he
Token ID339
Feature activation-7.43e-01

Pos logit contributions
eal+0.004
 jog+0.004
 bully+0.004
 goodbye+0.004
 aut+0.004
Neg logit contributions
mmm-0.006
Finally-0.006
ions-0.006
mmmm-0.005
ra-0.005
Token could
Token ID714
Feature activation+2.97e+00

Pos logit contributions
 goodbye+0.026
 jog+0.024
 stranger+0.024
 new+0.023
 youth+0.023
Neg logit contributions
mmm-0.030
Finally-0.026
ra-0.025
ions-0.024
mmmm-0.024
Token but
Token ID475
Feature activation+4.09e-01

Pos logit contributions
mmm+0.166
Finally+0.154
ions+0.145
mmmm+0.144
icer+0.139
Neg logit contributions
 goodbye-0.062
guard-0.057
 stranger-0.057
 jog-0.056
 bully-0.054
Token they
Token ID484
Feature activation-2.12e+00

Pos logit contributions
mmm+0.017
Finally+0.015
ions+0.014
ra+0.014
 nine+0.014
Neg logit contributions
eal-0.013
guard-0.011
 jog-0.011
 bully-0.011
 baths-0.011
Token an
Token ID281
Feature activation+2.17e-01

Pos logit contributions
mmm+0.132
Finally+0.124
ra+0.112
ions+0.112
mmmm+0.111
Neg logit contributions
guard-0.092
 jog-0.087
 goodbye-0.086
 stranger-0.086
 bully-0.084
Token idea
Token ID2126
Feature activation-2.90e+00

Pos logit contributions
mmm+0.012
Finally+0.011
ions+0.011
mmmm+0.010
icer+0.010
Neg logit contributions
 goodbye-0.005
 jog-0.005
 en-0.005
 stranger-0.005
 wealthy-0.005
Token.
Token ID13
Feature activation-1.17e+00

Pos logit contributions
 goodbye+0.088
guard+0.084
 jog+0.083
 stranger+0.081
 new+0.078
Neg logit contributions
mmm-0.140
Finally-0.131
icer-0.120
mmmm-0.120
ions-0.114
Token He
Token ID679
Feature activation+9.11e-01

Pos logit contributions
 goodbye+0.023
 jog+0.022
guard+0.021
 stranger+0.021
 bully+0.020
Neg logit contributions
mmm-0.067
Finally-0.062
mmmm-0.058
ions-0.058
icer-0.058
Token asked
Token ID1965
Feature activation+4.16e-02

Pos logit contributions
mmm+0.050
Finally+0.046
mmmm+0.044
ions+0.044
icer+0.043
Neg logit contributions
 goodbye-0.021
 jog-0.020
guard-0.019
 stranger-0.019
 bully-0.018
Token them
Token ID606
Feature activation-7.96e+00

Pos logit contributions
mmm+0.003
Finally+0.003
mmmm+0.003
icer+0.002
icious+0.002
Neg logit contributions
 goodbye-0.001
 jog-0.000
 new-0.000
 stranger-0.000
guard-0.000
Token if
Token ID611
Feature activation-8.32e-02

Pos logit contributions
 goodbye+0.222
 jog+0.214
guard+0.210
 stranger+0.207
 bully+0.206
Neg logit contributions
mmm-0.392
Finally-0.358
ions-0.337
mmmm-0.332
icer-0.321
Token he
Token ID339
Feature activation-7.30e-01

Pos logit contributions
eal+0.002
 jog+0.002
 goodbye+0.002
 bully+0.002
 stranger+0.002
Neg logit contributions
mmm-0.004
Finally-0.004
ions-0.004
mmmm-0.003
ra-0.003
Token could
Token ID714
Feature activation+3.13e+00

Pos logit contributions
 goodbye+0.022
 jog+0.021
guard+0.020
 stranger+0.020
 bully+0.019
Neg logit contributions
mmm-0.035
Finally-0.032
ions-0.030
mmmm-0.030
icer-0.028
Token join
Token ID4654
Feature activation-3.79e+00

Pos logit contributions
mmm+0.170
Finally+0.156
mmmm+0.147
ions+0.147
icer+0.143
Neg logit contributions
 goodbye-0.073
 jog-0.071
guard-0.068
 stranger-0.067
 bully-0.066
Token and
Token ID290
Feature activation-9.26e-01

Pos logit contributions
 goodbye+0.098
 jog+0.095
guard+0.091
 stranger+0.089
 bully+0.087
Neg logit contributions
mmm-0.199
Finally-0.184
mmmm-0.171
ions-0.168
icer-0.166
Token!
Token ID0
Feature activation-7.08e-01

Pos logit contributions
 goodbye+0.132
 jog+0.126
guard+0.125
 stranger+0.124
 bully+0.123
Neg logit contributions
mmm-0.175
Finally-0.156
ions-0.147
mmmm-0.145
icer-0.138
Token So
Token ID1406
Feature activation+2.20e+00

Pos logit contributions
 goodbye+0.022
guard+0.022
 jog+0.021
 stranger+0.021
 bully+0.021
Neg logit contributions
mmm-0.033
Finally-0.030
mmmm-0.028
ions-0.027
icer-0.026
Token,
Token ID11
Feature activation+1.48e-01

Pos logit contributions
mmm+0.123
icer+0.114
Finally+0.113
mmmm+0.110
ions+0.110
Neg logit contributions
 goodbye-0.059
 new-0.053
 jog-0.049
 stranger-0.045
 sad-0.045
Token she
Token ID673
Feature activation-6.55e-01

Pos logit contributions
mmm+0.007
Finally+0.006
ions+0.006
mmmm+0.006
ra+0.005
Neg logit contributions
guard-0.004
 goodbye-0.004
 bully-0.004
 jog-0.004
 stranger-0.004
Token asked
Token ID1965
Feature activation+1.70e-02

Pos logit contributions
 goodbye+0.020
guard+0.018
 bully+0.018
 stranger+0.018
 aut+0.018
Neg logit contributions
mmm-0.029
Finally-0.027
ra-0.025
ions-0.025
mmmm-0.024
Token them
Token ID606
Feature activation-7.96e+00

Pos logit contributions
mmm+0.001
Finally+0.001
ions+0.001
mmmm+0.001
rap+0.001
Neg logit contributions
guard-0.000
 bully-0.000
 jog-0.000
 goodbye-0.000
 stranger-0.000
Token to
Token ID284
Feature activation-2.70e+00

Pos logit contributions
 bully+0.252
 goodbye+0.249
guard+0.244
 jog+0.243
 stranger+0.240
Neg logit contributions
mmm-0.347
Finally-0.310
ions-0.304
mmmm-0.284
rap-0.268
Token introduce
Token ID10400
Feature activation-4.72e+00

Pos logit contributions
 goodbye+0.068
guard+0.064
 stranger+0.062
 wealthy+0.060
 en+0.060
Neg logit contributions
mmm-0.138
Finally-0.127
ions-0.119
mmmm-0.118
ra-0.115
Token her
Token ID607
Feature activation-1.92e+00

Pos logit contributions
 goodbye+0.132
 jog+0.124
guard+0.120
 stranger+0.119
 new+0.117
Neg logit contributions
mmm-0.243
Finally-0.222
mmmm-0.208
icer-0.204
ions-0.202
Token to
Token ID284
Feature activation-7.91e-01

Pos logit contributions
 bully+0.048
eal+0.045
guard+0.045
 stranger+0.044
 forg+0.042
Neg logit contributions
mmm-0.086
ions-0.086
Finally-0.078
ra-0.077
els-0.076
Token the
Token ID262
Feature activation-1.73e+00

Pos logit contributions
guard+0.021
 bully+0.020
 goodbye+0.019
 stranger+0.019
 jog+0.019
Neg logit contributions
mmm-0.038
Finally-0.035
ions-0.034
mmmm-0.033
ra-0.031
Token One
Token ID1881
Feature activation+4.54e+00

Pos logit contributions
 goodbye+0.027
guard+0.026
 jog+0.026
 stranger+0.026
 bully+0.025
Neg logit contributions
mmm-0.055
Finally-0.051
mmmm-0.047
ions-0.047
icer-0.046
Token day
Token ID1110
Feature activation-1.29e+00

Pos logit contributions
mmm+0.140
Finally+0.124
ions+0.119
ousy+0.114
 hours+0.112
Neg logit contributions
eal-0.178
 aut-0.177
 bully-0.171
 goodbye-0.169
 disl-0.166
Token,
Token ID11
Feature activation+3.16e-01

Pos logit contributions
 goodbye+0.045
 jog+0.044
guard+0.044
 stranger+0.043
 bully+0.042
Neg logit contributions
mmm-0.055
Finally-0.049
ions-0.045
mmmm-0.045
icer-0.043
Token she
Token ID673
Feature activation-2.96e-01

Pos logit contributions
mmm+0.016
Finally+0.015
ions+0.014
mmmm+0.014
icer+0.013
Neg logit contributions
 goodbye-0.008
guard-0.008
 jog-0.008
 bully-0.007
 stranger-0.007
Token asked
Token ID1965
Feature activation-8.04e-03

Pos logit contributions
 goodbye+0.009
guard+0.008
 aut+0.008
 jog+0.008
 stranger+0.008
Neg logit contributions
mmm-0.014
Finally-0.013
ra-0.012
icer-0.012
ions-0.011
Token them
Token ID606
Feature activation-7.95e+00

Pos logit contributions
 goodbye+0.000
 jog+0.000
 stranger+0.000
 new+0.000
guard+0.000
Neg logit contributions
mmm-0.000
Finally-0.000
mmmm-0.000
icer-0.000
ions-0.000
Token why
Token ID1521
Feature activation-2.65e+00

Pos logit contributions
 jog+0.195
 bully+0.193
 goodbye+0.191
guard+0.190
eal+0.185
Neg logit contributions
mmm-0.398
Finally-0.361
ions-0.352
mmmm-0.335
els-0.315
Token they
Token ID484
Feature activation-2.38e+00

Pos logit contributions
 goodbye+0.079
eal+0.078
 bully+0.077
 jog+0.076
 stranger+0.076
Neg logit contributions
mmm-0.119
ions-0.104
Finally-0.103
mmmm-0.097
ra-0.095
Token couldn
Token ID3521
Feature activation+4.36e+00

Pos logit contributions
 goodbye+0.091
 aut+0.083
guard+0.082
 stranger+0.082
 wife+0.081
Neg logit contributions
mmm-0.088
Finally-0.076
ra-0.068
mmmm-0.068
icer-0.068
Token't
Token ID470
Feature activation-9.37e-02

Pos logit contributions
mmm+0.146
Finally+0.127
ions+0.115
mmmm+0.114
icer+0.108
Neg logit contributions
 goodbye-0.193
 jog-0.186
 stranger-0.184
guard-0.184
 bully-0.180
Token get
Token ID651
Feature activation-2.32e+00

Pos logit contributions
 goodbye+0.002
 stranger+0.002
guard+0.002
 jog+0.002
 bully+0.002
Neg logit contributions
mmm-0.005
Finally-0.005
ions-0.004
mmmm-0.004
icer-0.004
Token a
Token ID257
Feature activation+6.13e-01

Pos logit contributions
 new+0.026
 jog+0.025
 goodbye+0.025
 stranger+0.023
guard+0.022
Neg logit contributions
mmm-0.084
Finally-0.081
mmmm-0.075
ions-0.073
ra-0.073
Token way
Token ID835
Feature activation-4.08e+00

Pos logit contributions
mmm+0.033
Finally+0.031
mmmm+0.029
ions+0.029
icer+0.028
Neg logit contributions
 goodbye-0.014
 jog-0.014
guard-0.014
 stranger-0.013
 bully-0.013
Token.
Token ID13
Feature activation-1.31e+00

Pos logit contributions
 goodbye+0.052
 jog+0.048
guard+0.046
 stranger+0.044
 bully+0.043
Neg logit contributions
mmm-0.263
Finally-0.246
ions-0.234
mmmm-0.233
icer-0.227
Token She
Token ID1375
Feature activation+1.79e+00

Pos logit contributions
 goodbye+0.032
 en+0.029
 jog+0.028
 new+0.028
 stranger+0.027
Neg logit contributions
mmm-0.068
icer-0.062
Finally-0.062
ions-0.061
ppers-0.059
Token asked
Token ID1965
Feature activation-2.32e-02

Pos logit contributions
mmm+0.105
Finally+0.094
mmmm+0.093
ions+0.092
icer+0.091
Neg logit contributions
 goodbye-0.037
 jog-0.036
 stranger-0.034
guard-0.033
 wealthy-0.032
Token them
Token ID606
Feature activation-7.93e+00

Pos logit contributions
 goodbye+0.001
 new+0.000
 stranger+0.000
 jog+0.000
 youth+0.000
Neg logit contributions
mmm-0.001
Finally-0.001
icer-0.001
mmmm-0.001
icious-0.001
Token,
Token ID11
Feature activation-2.41e-01

Pos logit contributions
 goodbye+0.209
 jog+0.204
guard+0.200
 bully+0.198
 stranger+0.196
Neg logit contributions
mmm-0.396
Finally-0.363
ions-0.344
mmmm-0.336
icer-0.323
Token "
Token ID366
Feature activation+1.19e+00

Pos logit contributions
 goodbye+0.005
 jog+0.004
 new+0.004
 en+0.004
 stranger+0.004
Neg logit contributions
mmm-0.014
Finally-0.013
icer-0.013
mmmm-0.013
ions-0.013
TokenWhat
Token ID2061
Feature activation+3.31e-01

Pos logit contributions
mmm+0.055
olk+0.048
Finally+0.046
ions+0.045
igs+0.045
Neg logit contributions
 jog-0.037
guard-0.036
 stranger-0.036
 sport-0.032
 bully-0.032
Token if
Token ID611
Feature activation+9.53e-01

Pos logit contributions
mmm+0.014
ions+0.012
Finally+0.012
mmmm+0.012
ra+0.011
Neg logit contributions
 goodbye-0.011
guard-0.011
 stranger-0.010
 jog-0.010
eal-0.010
Token I
Token ID314
Feature activation+1.28e+00

Pos logit contributions
mmm+0.038
Finally+0.033
ions+0.031
mmmm+0.030
ra+0.029
Neg logit contributions
 goodbye-0.035
 jog-0.034
 stranger-0.033
eal-0.033
 bully-0.033
Token be
Token ID307
Feature activation-1.55e+00

Pos logit contributions
mmm+0.018
Finally+0.017
mmmm+0.015
ions+0.015
icer+0.015
Neg logit contributions
 goodbye-0.011
 stranger-0.011
guard-0.011
 jog-0.011
 aut-0.010
Token important
Token ID1593
Feature activation+2.39e-01

Pos logit contributions
 goodbye+0.035
 jog+0.033
guard+0.032
 stranger+0.031
 new+0.031
Neg logit contributions
mmm-0.086
Finally-0.079
mmmm-0.075
ions-0.074
icer-0.073
Token,"
Token ID553
Feature activation+1.82e+00

Pos logit contributions
mmm+0.015
Finally+0.014
icer+0.014
mmmm+0.013
ions+0.013
Neg logit contributions
 goodbye-0.004
 jog-0.004
guard-0.004
 stranger-0.004
 new-0.003
Token one
Token ID530
Feature activation-3.47e+00

Pos logit contributions
mmm+0.096
Finally+0.088
mmmm+0.082
ions+0.082
ra+0.078
Neg logit contributions
 jog-0.043
 goodbye-0.042
guard-0.041
 stranger-0.040
 bully-0.039
Token of
Token ID286
Feature activation-2.64e+00

Pos logit contributions
 goodbye+0.078
 jog+0.072
 stranger+0.071
guard+0.071
 new+0.068
Neg logit contributions
mmm-0.198
Finally-0.181
mmmm-0.173
ions-0.172
icer-0.169
Token them
Token ID606
Feature activation-7.90e+00

Pos logit contributions
 goodbye+0.046
 jog+0.042
guard+0.042
 stranger+0.041
 bully+0.039
Neg logit contributions
mmm-0.160
Finally-0.150
mmmm-0.141
ions-0.137
icer-0.136
Token said
Token ID531
Feature activation-9.28e-01

Pos logit contributions
 goodbye+0.199
guard+0.196
 jog+0.191
 stranger+0.189
 bully+0.185
Neg logit contributions
mmm-0.400
Finally-0.372
ions-0.339
mmmm-0.339
ra-0.331
Token.
Token ID13
Feature activation-1.44e+00

Pos logit contributions
 jog+0.036
guard+0.035
 bully+0.034
 stranger+0.034
 seal+0.033
Neg logit contributions
mmm-0.033
Finally-0.029
ions-0.028
ra-0.026
mmmm-0.025
Token
Token ID220
Feature activation+7.44e-01

Pos logit contributions
 goodbye+0.035
 jog+0.033
guard+0.032
 stranger+0.032
 bully+0.031
Neg logit contributions
mmm-0.076
Finally-0.070
mmmm-0.066
ions-0.066
icer-0.065
Token
Token ID198
Feature activation-9.30e-01

Pos logit contributions
mmm+0.040
Finally+0.037
ions+0.034
mmmm+0.034
icer+0.033
Neg logit contributions
 goodbye-0.018
 jog-0.017
guard-0.017
 stranger-0.016
 bully-0.016
Token
Token ID198
Feature activation-1.47e+00

Pos logit contributions
 jog+0.014
 goodbye+0.013
guard+0.013
 new+0.013
 stranger+0.013
Neg logit contributions
mmm-0.057
icer-0.050
ions-0.050
olk-0.050
mmmm-0.050
Token so
Token ID523
Feature activation-1.13e+00

Pos logit contributions
guard+0.036
 jog+0.033
 stranger+0.032
 aut+0.031
 goodbye+0.031
Neg logit contributions
mmm-0.048
Finally-0.047
ra-0.042
 nine-0.042
Eventually-0.042
Token disappointed
Token ID11679
Feature activation-3.01e+00

Pos logit contributions
guard+0.031
 seal+0.027
 goodbye+0.026
 jog+0.026
 soldier+0.026
Neg logit contributions
mmm-0.056
Finally-0.055
Eventually-0.049
ra-0.048
mmmm-0.045
Token.
Token ID13
Feature activation-1.37e+00

Pos logit contributions
 goodbye+0.101
 jog+0.098
guard+0.096
 bully+0.095
 stranger+0.094
Neg logit contributions
mmm-0.133
Finally-0.119
ions-0.109
mmmm-0.109
icer-0.103
Token She
Token ID1375
Feature activation+1.64e+00

Pos logit contributions
 goodbye+0.044
 jog+0.043
guard+0.041
 stranger+0.041
 bully+0.041
Neg logit contributions
mmm-0.062
Finally-0.056
mmmm-0.052
ions-0.052
icer-0.051
Token asked
Token ID1965
Feature activation-1.72e-01

Pos logit contributions
mmm+0.087
Finally+0.080
mmmm+0.075
ions+0.075
icer+0.073
Neg logit contributions
 goodbye-0.041
 jog-0.039
guard-0.038
 stranger-0.037
 bully-0.037
Token them
Token ID606
Feature activation-7.89e+00

Pos logit contributions
 goodbye+0.004
 jog+0.004
 stranger+0.004
guard+0.004
 bully+0.004
Neg logit contributions
mmm-0.009
Finally-0.008
mmmm-0.008
ions-0.008
icer-0.008
Token why
Token ID1521
Feature activation-2.86e+00

Pos logit contributions
 goodbye+0.215
 jog+0.214
 bully+0.209
guard+0.209
 stranger+0.204
Neg logit contributions
mmm-0.380
Finally-0.348
ions-0.330
mmmm-0.319
icer-0.303
Token they
Token ID484
Feature activation-2.45e+00

Pos logit contributions
 goodbye+0.083
 jog+0.081
 bully+0.080
eal+0.080
 stranger+0.079
Neg logit contributions
mmm-0.132
ions-0.117
Finally-0.116
mmmm-0.108
ra-0.106
Token wouldn
Token ID3636
Feature activation+8.19e-01

Pos logit contributions
 goodbye+0.081
 jog+0.075
guard+0.075
 aut+0.074
 stranger+0.073
Neg logit contributions
mmm-0.105
Finally-0.094
ions-0.086
mmmm-0.085
ra-0.085
Token't
Token ID470
Feature activation+3.61e-01

Pos logit contributions
mmm+0.029
Finally+0.026
mmmm+0.023
ions+0.023
icer+0.022
Neg logit contributions
 goodbye-0.034
 jog-0.034
guard-0.033
 stranger-0.033
 bully-0.032
Token buy
Token ID2822
Feature activation+6.09e-02

Pos logit contributions
mmm+0.017
Finally+0.015
ra+0.014
mmmm+0.014
ions+0.013
Neg logit contributions
 goodbye-0.011
 stranger-0.010
 aut-0.010
guard-0.010
 seal-0.010
Token that
Token ID326
Feature activation+6.59e-02

Pos logit contributions
 goodbye+0.063
 jog+0.061
guard+0.059
 bully+0.059
 stranger+0.058
Neg logit contributions
mmm-0.091
Finally-0.081
ions-0.076
mmmm-0.076
ra-0.071
Token he
Token ID339
Feature activation+8.99e-01

Pos logit contributions
mmm+0.003
Finally+0.003
ions+0.003
mmmm+0.003
ra+0.003
Neg logit contributions
 jog-0.002
 goodbye-0.002
guard-0.001
eal-0.001
 bully-0.001
Token dropped
Token ID5710
Feature activation+2.39e+00

Pos logit contributions
mmm+0.041
Finally+0.038
ra+0.034
ions+0.034
mmmm+0.033
Neg logit contributions
 goodbye-0.027
 jog-0.026
guard-0.026
 aut-0.025
 stranger-0.025
Token everything
Token ID2279
Feature activation-1.78e+00

Pos logit contributions
mmm+0.133
Finally+0.122
ions+0.119
mmmm+0.115
icer+0.114
Neg logit contributions
 jog-0.047
 goodbye-0.047
guard-0.046
 stranger-0.043
 bully-0.043
Token he
Token ID339
Feature activation+3.82e+00

Pos logit contributions
 goodbye+0.053
 wife+0.053
 jog+0.053
 bully+0.051
 stranger+0.051
Neg logit contributions
mmm-0.079
Finally-0.071
ions-0.070
mmmm-0.065
icer-0.064
Token had
Token ID550
Feature activation+5.58e+00

Pos logit contributions
mmm+0.185
Finally+0.172
ions+0.158
mmmm+0.156
ra+0.155
Neg logit contributions
 goodbye-0.106
 jog-0.101
guard-0.099
 stranger-0.098
 bully-0.095
Token bought
Token ID5839
Feature activation+2.40e+00

Pos logit contributions
mmm+0.226
Finally+0.214
ra+0.196
ions+0.189
mmmm+0.185
Neg logit contributions
 jog-0.182
 stranger-0.182
guard-0.180
 goodbye-0.177
 youth-0.175
Token and
Token ID290
Feature activation+2.34e-01

Pos logit contributions
mmm+0.103
Finally+0.091
ions+0.086
mmmm+0.085
icer+0.082
Neg logit contributions
 goodbye-0.081
 jog-0.081
guard-0.079
 stranger-0.078
 bully-0.077
Token ran
Token ID4966
Feature activation+7.46e-01

Pos logit contributions
mmm+0.011
Finally+0.010
ions+0.010
mmmm+0.009
ra+0.009
Neg logit contributions
 jog-0.006
 goodbye-0.006
guard-0.006
 stranger-0.006
 aut-0.006
Token away
Token ID1497
Feature activation-7.90e-01

Pos logit contributions
mmm+0.036
Finally+0.035
ions+0.032
ra+0.031
mmmm+0.031
Neg logit contributions
guard-0.018
 jog-0.017
 wife-0.017
 goodbye-0.017
 bully-0.017
Token!
Token ID0
Feature activation-1.35e-01

Pos logit contributions
 jog+0.030
 aut+0.029
guard+0.029
 bully+0.029
eal+0.029
Neg logit contributions
mmm-0.027
Finally-0.025
ions-0.022
ra-0.022
mmmm-0.020
Token happening
Token ID5836
Feature activation-2.63e+00

Pos logit contributions
mmm+0.064
Finally+0.059
ions+0.055
mmmm+0.055
icer+0.053
Neg logit contributions
 goodbye-0.037
 jog-0.035
guard-0.035
 stranger-0.034
 bully-0.034
Token!
Token ID0
Feature activation-1.26e+00

Pos logit contributions
 goodbye+0.067
 jog+0.062
 new+0.061
 stranger+0.060
guard+0.060
Neg logit contributions
mmm-0.140
Finally-0.132
mmmm-0.122
icer-0.121
ions-0.119
Token She
Token ID1375
Feature activation+2.42e+00

Pos logit contributions
 goodbye+0.033
 jog+0.033
 new+0.031
 en+0.030
 stranger+0.030
Neg logit contributions
mmm-0.064
Finally-0.057
ions-0.055
mmmm-0.054
icer-0.053
Token watched
Token ID7342
Feature activation-4.29e-01

Pos logit contributions
mmm+0.136
Finally+0.125
mmmm+0.119
ions+0.118
icer+0.116
Neg logit contributions
 goodbye-0.052
 jog-0.051
guard-0.048
 stranger-0.048
 bully-0.046
Token as
Token ID355
Feature activation-2.21e+00

Pos logit contributions
 goodbye+0.010
 jog+0.009
 new+0.009
 youth+0.008
 en+0.008
Neg logit contributions
mmm-0.025
Finally-0.023
mmmm-0.022
icer-0.022
ions-0.021
Token Mom
Token ID11254
Feature activation+5.97e+00

Pos logit contributions
 goodbye+0.047
 jog+0.045
 stranger+0.043
 new+0.043
guard+0.043
Neg logit contributions
mmm-0.127
Finally-0.117
mmmm-0.111
icer-0.109
ions-0.107
Tokenmy
Token ID1820
Feature activation+4.97e+00

Pos logit contributions
mmm+0.263
Finally+0.236
mmmm+0.222
icer+0.211
ions+0.203
Neg logit contributions
 jog-0.205
 goodbye-0.198
 joined-0.198
guard-0.195
 new-0.192
Token pulled
Token ID5954
Feature activation+3.28e+00

Pos logit contributions
mmm+0.263
Finally+0.241
mmmm+0.227
ions+0.225
icer+0.220
Neg logit contributions
 goodbye-0.124
 jog-0.119
guard-0.116
 stranger-0.114
 bully-0.111
Token a
Token ID257
Feature activation+2.43e+00

Pos logit contributions
mmm+0.224
Finally+0.207
mmmm+0.204
icious+0.191
mm+0.190
Neg logit contributions
 new-0.050
 goodbye-0.048
 back-0.045
 to-0.043
 jog-0.042
Token truck
Token ID7779
Feature activation+1.63e+00

Pos logit contributions
mmm+0.135
Finally+0.122
mmmm+0.118
ions+0.116
icer+0.113
Neg logit contributions
 goodbye-0.058
 new-0.058
 jog-0.057
 stranger-0.057
guard-0.054
Token from
Token ID422
Feature activation-1.44e+00

Pos logit contributions
mmm+0.098
Finally+0.090
mmmm+0.086
icer+0.085
ions+0.082
Neg logit contributions
 goodbye-0.033
 jog-0.032
guard-0.030
 stranger-0.029
 new-0.028
Token around
Token ID1088
Feature activation+1.40e-01

Pos logit contributions
mmm+0.051
Finally+0.048
ions+0.045
mmmm+0.044
icer+0.043
Neg logit contributions
 goodbye-0.026
 jog-0.025
guard-0.024
 stranger-0.024
 bully-0.023
Token the
Token ID262
Feature activation+5.23e-01

Pos logit contributions
mmm+0.008
Finally+0.008
mmmm+0.007
icious+0.007
ions+0.007
Neg logit contributions
 goodbye-0.003
 jog-0.003
 new-0.003
 youth-0.003
 stranger-0.003
Token tree
Token ID5509
Feature activation+2.19e+00

Pos logit contributions
mmm+0.027
Finally+0.024
ions+0.023
mmmm+0.023
ra+0.022
Neg logit contributions
 jog-0.015
 new-0.015
 wealthy-0.014
 stranger-0.014
 youth-0.014
Token all
Token ID477
Feature activation+1.06e+00

Pos logit contributions
mmm+0.103
Finally+0.094
ions+0.087
mmmm+0.087
icer+0.084
Neg logit contributions
 goodbye-0.067
 jog-0.064
guard-0.063
 stranger-0.062
 bully-0.061
Token day
Token ID1110
Feature activation+2.63e+00

Pos logit contributions
mmm+0.036
ions+0.035
Finally+0.034
icer+0.033
el+0.030
Neg logit contributions
 goodbye-0.042
 wife-0.041
 aut-0.040
 bully-0.039
 stranger-0.039
Token long
Token ID890
Feature activation+6.83e+00

Pos logit contributions
mmm+0.131
Finally+0.119
mmmm+0.115
ions+0.114
icer+0.111
Neg logit contributions
 goodbye-0.076
 jog-0.073
 new-0.071
 stranger-0.068
 wealthy-0.068
Token.
Token ID13
Feature activation-3.24e-01

Pos logit contributions
mmm+0.355
Finally+0.328
mmmm+0.307
icer+0.296
ions+0.290
Neg logit contributions
 goodbye-0.190
 jog-0.176
guard-0.171
 stranger-0.165
 new-0.165
Token
Token ID198
Feature activation-1.91e-01

Pos logit contributions
 goodbye+0.008
 jog+0.008
guard+0.008
 stranger+0.007
 bully+0.007
Neg logit contributions
mmm-0.017
Finally-0.016
mmmm-0.015
ions-0.015
icer-0.014
Token
Token ID198
Feature activation-9.03e-01

Pos logit contributions
 jog+0.003
 goodbye+0.003
 new+0.003
guard+0.003
 stranger+0.003
Neg logit contributions
mmm-0.011
Finally-0.010
mmmm-0.010
ions-0.010
ra-0.010
TokenOne
Token ID3198
Feature activation+4.18e+00

Pos logit contributions
 jog+0.046
 stranger+0.043
guard+0.043
 goodbye+0.042
 sport+0.042
Neg logit contributions
mmm-0.027
ions-0.020
mmmm-0.020
ra-0.019
olk-0.019
Token sunny
Token ID27737
Feature activation-2.13e+00

Pos logit contributions
mmm+0.145
Finally+0.131
ousy+0.117
mmmm+0.115
ions+0.111
Neg logit contributions
 goodbye-0.170
 aut-0.164
guard-0.162
 bully-0.161
 forg-0.156
Token.
Token ID13
Feature activation+4.35e-01

Pos logit contributions
 jog+0.062
 bully+0.062
 goodbye+0.060
 youth+0.060
 stranger+0.060
Neg logit contributions
mmm-0.078
Finally-0.070
ions-0.067
mmmm-0.064
ra-0.061
Token They
Token ID1119
Feature activation+9.95e-01

Pos logit contributions
mmm+0.021
Finally+0.019
mmmm+0.018
ions+0.017
icer+0.017
Neg logit contributions
 goodbye-0.013
 jog-0.013
guard-0.013
 stranger-0.012
 bully-0.012
Token sn
Token ID3013
Feature activation+6.67e-01

Pos logit contributions
mmm+0.053
Finally+0.049
mmmm+0.045
ions+0.045
icer+0.044
Neg logit contributions
 goodbye-0.024
 jog-0.023
guard-0.023
 stranger-0.022
 bully-0.022
Tokenuggle
Token ID33498
Feature activation-5.17e+00

Pos logit contributions
mmm+0.042
Finally+0.038
mmmm+0.038
ousy+0.038
opes+0.037
Neg logit contributions
 goodbye-0.010
 jog-0.008
eal-0.007
guard-0.006
 new-0.006
Token with
Token ID351
Feature activation-7.78e-01

Pos logit contributions
 bully+0.198
 stranger+0.183
 en+0.180
 jog+0.180
 aut+0.179
Neg logit contributions
mmm-0.188
ra-0.184
Finally-0.172
ions-0.170
ppers-0.167
Token Mom
Token ID11254
Feature activation+6.65e+00

Pos logit contributions
 goodbye+0.019
 jog+0.018
guard+0.017
 stranger+0.017
 new+0.017
Neg logit contributions
mmm-0.042
Finally-0.039
mmmm-0.036
ions-0.036
icer-0.035
Token on
Token ID319
Feature activation+9.69e-01

Pos logit contributions
mmm+0.307
Finally+0.281
ions+0.279
icer+0.264
ra+0.264
Neg logit contributions
 bully-0.187
 stranger-0.177
 jog-0.175
guard-0.174
 goodbye-0.174
Token the
Token ID262
Feature activation+5.53e-01

Pos logit contributions
mmm+0.062
Finally+0.058
mmmm+0.056
ions+0.055
icer+0.053
Neg logit contributions
 goodbye-0.016
 jog-0.014
 new-0.014
 stranger-0.012
 youth-0.012
Token couch
Token ID18507
Feature activation+5.16e-01

Pos logit contributions
mmm+0.024
Finally+0.022
mmmm+0.020
ions+0.020
icer+0.019
Neg logit contributions
 goodbye-0.019
 jog-0.018
guard-0.018
 stranger-0.018
 bully-0.018
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
mmm+0.026
Finally+0.024
ions+0.022
mmmm+0.022
icer+0.022
Neg logit contributions
 goodbye-0.014
 jog-0.013
guard-0.013
 stranger-0.013
 bully-0.013
Token Mom
Token ID11254
Feature activation+4.63e+00

Pos logit contributions
mmm+0.047
Finally+0.043
mmmm+0.039
ions+0.039
icer+0.037
Neg logit contributions
guard-0.032
 goodbye-0.032
 jog-0.031
 stranger-0.031
 bully-0.030
Token,
Token ID11
Feature activation+2.34e+00

Pos logit contributions
 goodbye+0.023
guard+0.023
 jog+0.023
 bully+0.022
 stranger+0.022
Neg logit contributions
mmm-0.035
Finally-0.032
ions-0.030
mmmm-0.029
icer-0.029
Token looking
Token ID2045
Feature activation-2.66e+00

Pos logit contributions
mmm+0.090
Finally+0.085
 hours+0.076
icer+0.074
ions+0.073
Neg logit contributions
guard-0.085
 aut-0.081
 bully-0.080
 stranger-0.077
 jog-0.073
Token for
Token ID329
Feature activation+3.75e+00

Pos logit contributions
guard+0.109
 bully+0.106
 jog+0.102
 aut+0.101
 stranger+0.099
Neg logit contributions
mmm-0.094
Finally-0.086
ions-0.077
icer-0.076
mmmm-0.073
Token something
Token ID1223
Feature activation-1.90e+00

Pos logit contributions
mmm+0.190
Finally+0.174
ions+0.163
mmmm+0.163
icer+0.158
Neg logit contributions
 goodbye-0.100
 jog-0.097
guard-0.095
 stranger-0.093
 bully-0.093
Token y
Token ID331
Feature activation+4.92e+00

Pos logit contributions
 bully+0.054
eal+0.049
 musician+0.046
 aut+0.045
 goodbye+0.045
Neg logit contributions
mmm-0.087
Finally-0.079
ions-0.078
 hours-0.073
ousy-0.073
Tokenummy
Token ID13513
Feature activation+6.19e+00

Pos logit contributions
Finally+0.155
mmm+0.146
Eventually+0.126
ions+0.113
mmmm+0.113
Neg logit contributions
guard-0.211
 goodbye-0.210
 jog-0.209
 new-0.207
 shrimp-0.204
Token to
Token ID284
Feature activation+1.69e+00

Pos logit contributions
mmm+0.366
Finally+0.336
ions+0.326
mmmm+0.320
icer+0.310
Neg logit contributions
 goodbye-0.107
 jog-0.102
 bully-0.099
guard-0.097
 stranger-0.096
Token eat
Token ID4483
Feature activation+3.74e+00

Pos logit contributions
mmm+0.099
Finally+0.096
ions+0.089
icer+0.088
mmmm+0.088
Neg logit contributions
 jog-0.033
 goodbye-0.031
 new-0.028
 stranger-0.027
 swim-0.026
Token.
Token ID13
Feature activation+5.60e-01

Pos logit contributions
mmm+0.200
Finally+0.191
mmmm+0.175
ra+0.170
icer+0.169
Neg logit contributions
 goodbye-0.093
 new-0.088
 jog-0.086
guard-0.085
 stranger-0.083
Token He
Token ID679
Feature activation+2.39e+00

Pos logit contributions
mmm+0.030
Finally+0.027
ions+0.026
mmmm+0.026
icer+0.025
Neg logit contributions
 goodbye-0.014
 jog-0.013
guard-0.013
 stranger-0.013
 bully-0.012
Token saw
Token ID2497
Feature activation+1.89e+00

Pos logit contributions
mmm+0.130
Finally+0.120
mmmm+0.113
ions+0.113
icer+0.110
Neg logit contributions
 goodbye-0.055
 jog-0.053
guard-0.051
 stranger-0.051
 bully-0.049
Token.
Token ID13
Feature activation-8.48e-01

Pos logit contributions
mmm+0.077
Finally+0.071
mmmm+0.067
ions+0.064
icer+0.064
Neg logit contributions
 goodbye-0.041
 jog-0.040
 new-0.039
guard-0.038
 wealthy-0.038
Token
Token ID198
Feature activation-7.45e-01

Pos logit contributions
guard+0.034
 bully+0.033
 goodbye+0.031
 stranger+0.031
 forg+0.030
Neg logit contributions
mmm-0.033
Finally-0.031
mmmm-0.027
icer-0.026
Mom-0.026
Token
Token ID198
Feature activation-1.34e+00

Pos logit contributions
 goodbye+0.016
 jog+0.016
guard+0.015
 stranger+0.015
 bully+0.014
Neg logit contributions
mmm-0.042
Finally-0.038
mmmm-0.036
ions-0.036
icer-0.035
TokenThe
Token ID464
Feature activation-8.43e-01

Pos logit contributions
 jog+0.051
 goodbye+0.050
 stranger+0.049
guard+0.048
 youth+0.047
Neg logit contributions
mmm-0.055
Finally-0.046
ions-0.045
mmmm-0.045
icer-0.043
Token daddy
Token ID35822
Feature activation-3.93e-01

Pos logit contributions
 goodbye+0.022
guard+0.021
 jog+0.021
 bully+0.021
 stranger+0.020
Neg logit contributions
mmm-0.042
Finally-0.040
mmmm-0.036
ions-0.035
icer-0.035
Token grabbed
Token ID13176
Feature activation+1.30e+00

Pos logit contributions
 goodbye+0.007
 jog+0.007
guard+0.007
 stranger+0.007
 wealthy+0.007
Neg logit contributions
mmm-0.023
Finally-0.021
mmmm-0.020
ions-0.020
icer-0.020
Token a
Token ID257
Feature activation+1.55e+00

Pos logit contributions
mmm+0.070
Finally+0.064
ions+0.061
mmmm+0.061
icer+0.059
Neg logit contributions
 goodbye-0.030
 jog-0.029
guard-0.029
 stranger-0.028
 bully-0.027
Token paint
Token ID7521
Feature activation+4.77e-01

Pos logit contributions
mmm+0.076
Finally+0.068
mmmm+0.064
ions+0.064
icer+0.062
Neg logit contributions
 goodbye-0.045
 jog-0.044
 stranger-0.043
guard-0.042
 new-0.042
Tokenbrush
Token ID32680
Feature activation+3.31e+00

Pos logit contributions
mmm+0.026
Finally+0.024
mmmm+0.023
icer+0.022
ousy+0.021
Neg logit contributions
 goodbye-0.012
 new-0.012
 jog-0.011
 to-0.011
 back-0.011
Token and
Token ID290
Feature activation+4.35e-01

Pos logit contributions
mmm+0.164
Finally+0.149
ions+0.140
mmmm+0.138
icer+0.135
Neg logit contributions
 goodbye-0.091
 jog-0.089
guard-0.087
 stranger-0.086
 bully-0.086
Token a
Token ID257
Feature activation+1.46e+00

Pos logit contributions
mmm+0.023
Finally+0.021
mmmm+0.020
icer+0.020
ions+0.020
Neg logit contributions
 goodbye-0.011
 jog-0.010
guard-0.010
 new-0.010
 stranger-0.010
Token for
Token ID329
Feature activation+2.43e+00

Pos logit contributions
mmm+0.036
Finally+0.035
ions+0.032
mmmm+0.030
Eventually+0.030
Neg logit contributions
guard-0.025
 jog-0.024
 goodbye-0.024
 stranger-0.024
 bully-0.023
Token all
Token ID477
Feature activation-4.07e-01

Pos logit contributions
mmm+0.139
Finally+0.129
mmmm+0.122
ions+0.120
icer+0.119
Neg logit contributions
 goodbye-0.051
 jog-0.048
 new-0.046
guard-0.046
 stranger-0.045
Token the
Token ID262
Feature activation+1.44e-01

Pos logit contributions
 goodbye+0.013
 wife+0.013
 jog+0.013
eal+0.012
 stranger+0.012
Neg logit contributions
ions-0.017
mmm-0.017
els-0.014
Finally-0.014
 nine-0.014
Token fruits
Token ID15921
Feature activation+2.46e+00

Pos logit contributions
mmm+0.008
Finally+0.007
mmmm+0.007
ions+0.007
icer+0.007
Neg logit contributions
 goodbye-0.003
 jog-0.003
guard-0.003
 stranger-0.003
 bully-0.003
Token and
Token ID290
Feature activation+9.31e-01

Pos logit contributions
mmm+0.097
ions+0.089
Finally+0.082
mmmm+0.077
ra+0.076
Neg logit contributions
 goodbye-0.086
 jog-0.084
 bully-0.084
eal-0.083
 aut-0.081
Token vegetables
Token ID13701
Feature activation+1.41e+00

Pos logit contributions
mmm+0.043
Finally+0.039
mmmm+0.036
ions+0.036
icer+0.035
Neg logit contributions
 goodbye-0.029
 jog-0.028
guard-0.028
 stranger-0.028
 new-0.027
Token in
Token ID287
Feature activation+1.08e+00

Pos logit contributions
mmm+0.053
ions+0.048
Finally+0.046
mmmm+0.042
ra+0.041
Neg logit contributions
 goodbye-0.052
 bully-0.050
 jog-0.049
 stranger-0.049
eal-0.049
Token the
Token ID262
Feature activation+4.00e-01

Pos logit contributions
mmm+0.070
Finally+0.064
mmmm+0.062
ions+0.059
icer+0.059
Neg logit contributions
 jog-0.015
 goodbye-0.015
 new-0.015
 youth-0.014
 stranger-0.014
Token town
Token ID3240
Feature activation-2.51e+00

Pos logit contributions
Finally+0.016
mmm+0.015
icer+0.014
 hours+0.013
Eventually+0.013
Neg logit contributions
guard-0.013
 goodbye-0.013
 forg-0.012
 aut-0.012
eal-0.012
Token.
Token ID13
Feature activation+1.07e-01

Pos logit contributions
 goodbye+0.082
 jog+0.079
guard+0.077
 stranger+0.077
 bully+0.076
Neg logit contributions
mmm-0.111
Finally-0.101
ions-0.093
mmmm-0.092
icer-0.089
Token The
Token ID383
Feature activation+2.81e-01

Pos logit contributions
mmm+0.006
Finally+0.006
mmmm+0.005
ions+0.005
icer+0.005
Neg logit contributions
 goodbye-0.002
 jog-0.002
guard-0.002
 en-0.002
 youth-0.002
Token was
Token ID373
Feature activation+1.44e+00

Pos logit contributions
 goodbye+0.012
eal+0.012
guard+0.011
 jog+0.011
 bully+0.011
Neg logit contributions
mmm-0.040
Finally-0.037
ions-0.036
mmmm-0.035
 hours-0.033
Token making
Token ID1642
Feature activation-2.10e-01

Pos logit contributions
mmm+0.043
ions+0.037
 hours+0.035
 nine+0.033
vel+0.033
Neg logit contributions
 jog-0.057
eal-0.057
guard-0.056
lyss-0.054
 wife-0.054
Token the
Token ID262
Feature activation+7.85e-01

Pos logit contributions
 goodbye+0.007
 jog+0.007
guard+0.007
 stranger+0.007
 bully+0.007
Neg logit contributions
mmm-0.009
Finally-0.008
ions-0.007
mmmm-0.007
icer-0.007
Token noise
Token ID7838
Feature activation-1.04e+00

Pos logit contributions
mmm+0.052
Finally+0.048
ions+0.047
mmmm+0.046
icer+0.045
Neg logit contributions
 goodbye-0.010
 jog-0.009
 stranger-0.008
guard-0.008
 bully-0.008
Token,
Token ID11
Feature activation+3.15e+00

Pos logit contributions
 goodbye+0.036
 wife+0.034
 jog+0.034
eal+0.034
 stranger+0.033
Neg logit contributions
mmm-0.041
ions-0.035
Finally-0.035
mmmm-0.033
ra-0.032
Token but
Token ID475
Feature activation+1.49e+00

Pos logit contributions
mmm+0.144
Finally+0.131
mmmm+0.120
ions+0.120
icer+0.116
Neg logit contributions
 goodbye-0.096
 jog-0.095
guard-0.095
 stranger-0.092
 bully-0.092
Token he
Token ID339
Feature activation+3.17e-01

Pos logit contributions
mmm+0.068
Finally+0.062
ions+0.058
mmmm+0.055
 hours+0.054
Neg logit contributions
 jog-0.045
 aut-0.044
eal-0.043
 bully-0.042
guard-0.041
Token was
Token ID373
Feature activation+1.30e-01

Pos logit contributions
mmm+0.014
Finally+0.014
ra+0.012
mmmm+0.012
ions+0.012
Neg logit contributions
 goodbye-0.010
 jog-0.009
guard-0.009
 aut-0.009
 stranger-0.009
Token scared
Token ID12008
Feature activation-5.75e-01

Pos logit contributions
mmm+0.005
Finally+0.005
 nine+0.004
ions+0.004
Eventually+0.004
Neg logit contributions
guard-0.005
 jog-0.005
 aut-0.004
 goodbye-0.004
 stranger-0.004
Token.
Token ID13
Feature activation-5.57e-01

Pos logit contributions
 goodbye+0.016
 jog+0.016
guard+0.015
 stranger+0.015
 bully+0.015
Neg logit contributions
mmm-0.029
Finally-0.026
mmmm-0.024
ions-0.024
icer-0.024
Token He
Token ID679
Feature activation+1.37e+00

Pos logit contributions
 jog+0.017
guard+0.017
 goodbye+0.016
 stranger+0.016
 bully+0.016
Neg logit contributions
mmm-0.026
Finally-0.025
mmmm-0.022
ions-0.022
icer-0.022
Token never
Token ID1239
Feature activation+1.34e-02

Pos logit contributions
guard+0.030
 jog+0.029
 stranger+0.029
 goodbye+0.029
 aut+0.029
Neg logit contributions
mmm-0.039
Finally-0.036
ra-0.032
ions-0.032
mmmm-0.032
Token forgot
Token ID16453
Feature activation-4.69e-01

Pos logit contributions
mmm+0.000
ra+0.000
 fifteen+0.000
 soon+0.000
oh+0.000
Neg logit contributions
 sport-0.000
 aut-0.000
 uniform-0.000
 CD-0.000
 coach-0.000
Token the
Token ID262
Feature activation-5.55e-01

Pos logit contributions
eal+0.014
 bully+0.013
 jog+0.013
guard+0.013
 aut+0.013
Neg logit contributions
mmm-0.019
ions-0.018
Finally-0.017
 hours-0.016
mmmm-0.016
Token man
Token ID582
Feature activation-2.05e-01

Pos logit contributions
 goodbye+0.012
guard+0.012
 jog+0.011
 bully+0.011
 aut+0.011
Neg logit contributions
mmm-0.028
Finally-0.027
ra-0.024
mmmm-0.024
icer-0.024
Token who
Token ID508
Feature activation-1.29e-01

Pos logit contributions
 sport+0.006
 jog+0.006
eal+0.006
 aut+0.006
guard+0.006
Neg logit contributions
mmm-0.008
ra-0.007
Finally-0.007
ions-0.007
mmmm-0.007
Token saved
Token ID7448
Feature activation+1.44e+00

Pos logit contributions
 goodbye+0.004
eal+0.004
 sport+0.004
 aut+0.004
 jog+0.004
Neg logit contributions
mmm-0.005
ions-0.005
ra-0.004
Finally-0.004
 hours-0.004
Token her
Token ID607
Feature activation+1.83e-02

Pos logit contributions
mmm+0.068
Finally+0.062
mmmm+0.057
ions+0.057
icer+0.056
Neg logit contributions
 goodbye-0.044
 jog-0.042
guard-0.041
 stranger-0.041
 bully-0.040
Token from
Token ID422
Feature activation-2.30e+00

Pos logit contributions
mmm+0.001
Finally+0.001
ra+0.001
mmmm+0.001
ions+0.001
Neg logit contributions
eal-0.001
guard-0.001
 bully-0.001
 jog-0.001
 goodbye-0.001
Token being
Token ID852
Feature activation-4.11e+00

Pos logit contributions
 goodbye+0.051
 jog+0.048
 stranger+0.047
 new+0.047
guard+0.046
Neg logit contributions
mmm-0.131
Finally-0.122
mmmm-0.115
ions-0.111
icer-0.109
Token lost
Token ID2626
Feature activation+2.01e+00

Pos logit contributions
 jog+0.120
guard+0.112
 aut+0.105
 goodbye+0.104
 sport+0.100
Neg logit contributions
mmm-0.169
ions-0.157
Finally-0.156
ra-0.153
 hours-0.150
Token in
Token ID287
Feature activation+8.49e-01

Pos logit contributions
mmm+0.095
Finally+0.086
mmmm+0.080
ions+0.080
icer+0.077
Neg logit contributions
 goodbye-0.061
 jog-0.059
guard-0.058
 stranger-0.057
 bully-0.056
Token to
Token ID284
Feature activation-1.67e+00

Pos logit contributions
guard+0.002
 goodbye+0.002
 bully+0.002
eal+0.002
 stranger+0.002
Neg logit contributions
mmm-0.006
ions-0.006
Finally-0.006
mmmm-0.006
icer-0.005
Token play
Token ID711
Feature activation-2.43e+00

Pos logit contributions
guard+0.040
 goodbye+0.039
 stranger+0.037
 bully+0.035
 en+0.034
Neg logit contributions
mmm-0.088
Finally-0.080
mmmm-0.076
ions-0.075
ra-0.071
Token with
Token ID351
Feature activation-3.04e+00

Pos logit contributions
 goodbye+0.072
guard+0.069
 stranger+0.066
 jog+0.065
 aut+0.063
Neg logit contributions
mmm-0.116
Finally-0.107
ions-0.101
mmmm-0.098
icer-0.096
Token her
Token ID607
Feature activation-1.24e+00

Pos logit contributions
 goodbye+0.073
 jog+0.071
 stranger+0.067
guard+0.067
 bully+0.066
Neg logit contributions
mmm-0.165
Finally-0.153
mmmm-0.143
ions-0.141
icer-0.138
Token toys
Token ID14958
Feature activation-6.90e-01

Pos logit contributions
 goodbye+0.041
guard+0.039
 jog+0.037
 bully+0.037
eal+0.037
Neg logit contributions
mmm-0.051
Finally-0.048
ions-0.047
icer-0.045
ra-0.044
Token,
Token ID11
Feature activation+2.21e+00

Pos logit contributions
 goodbye+0.019
 jog+0.019
guard+0.018
 stranger+0.018
 bully+0.018
Neg logit contributions
mmm-0.034
Finally-0.031
mmmm-0.029
ions-0.029
icer-0.028
Token but
Token ID475
Feature activation+6.15e-01

Pos logit contributions
mmm+0.077
Finally+0.068
ions+0.063
mmmm+0.060
icer+0.060
Neg logit contributions
 goodbye-0.089
guard-0.089
eal-0.085
 bully-0.085
 aut-0.084
Token her
Token ID607
Feature activation-2.64e+00

Pos logit contributions
mmm+0.032
Finally+0.030
mmmm+0.028
ions+0.028
icer+0.028
Neg logit contributions
 goodbye-0.016
 jog-0.015
 new-0.014
guard-0.014
 stranger-0.014
Token favorite
Token ID4004
Feature activation-1.17e-01

Pos logit contributions
guard+0.064
 goodbye+0.056
eal+0.054
 stranger+0.053
 bully+0.052
Neg logit contributions
mmm-0.129
Finally-0.124
icer-0.121
ra-0.120
ousy-0.116
Token was
Token ID373
Feature activation-1.11e-01

Pos logit contributions
 goodbye+0.003
guard+0.003
 jog+0.003
eal+0.003
 aut+0.003
Neg logit contributions
mmm-0.005
Finally-0.005
ions-0.005
icer-0.005
ra-0.005
Token a
Token ID257
Feature activation+9.44e-01

Pos logit contributions
 goodbye+0.003
eal+0.003
 jog+0.003
guard+0.003
 bully+0.003
Neg logit contributions
mmm-0.005
ions-0.005
Finally-0.005
icer-0.004
innie-0.004
Token night
Token ID1755
Feature activation+2.57e+00

Pos logit contributions
mmm+0.043
Finally+0.039
ions+0.036
mmmm+0.036
icer+0.034
Neg logit contributions
 goodbye-0.030
 jog-0.030
guard-0.029
 bully-0.029
 stranger-0.028
Token and
Token ID290
Feature activation-6.25e-01

Pos logit contributions
mmm+0.111
Finally+0.099
ions+0.093
mmmm+0.091
ra+0.088
Neg logit contributions
 goodbye-0.085
 jog-0.084
guard-0.083
 stranger-0.083
 bully-0.082
Token she
Token ID673
Feature activation+1.77e+00

Pos logit contributions
guard+0.020
 stranger+0.020
 bully+0.019
 jog+0.019
 goodbye+0.019
Neg logit contributions
mmm-0.027
Finally-0.025
ions-0.022
mmmm-0.022
ra-0.022
Token never
Token ID1239
Feature activation+9.33e-01

Pos logit contributions
mmm+0.074
Finally+0.071
ra+0.066
ions+0.064
 hours+0.061
Neg logit contributions
 stranger-0.055
guard-0.054
 goodbye-0.054
 aut-0.053
 bully-0.052
Token stopped
Token ID5025
Feature activation+7.36e-02

Pos logit contributions
mmm+0.037
ra+0.033
Finally+0.033
 hours+0.032
h+0.031
Neg logit contributions
 stranger-0.027
 sport-0.026
 uniform-0.026
 aut-0.026
guard-0.025
Token feeling
Token ID4203
Feature activation-1.40e+00

Pos logit contributions
mmm+0.003
Finally+0.003
ions+0.003
ra+0.003
mmmm+0.003
Neg logit contributions
 goodbye-0.002
guard-0.002
 stranger-0.002
 jog-0.002
 bully-0.002
Token happy
Token ID3772
Feature activation-3.58e-01

Pos logit contributions
guard+0.038
 jog+0.037
 wife+0.036
eal+0.036
 seal+0.036
Neg logit contributions
mmm-0.058
Finally-0.052
 hours-0.051
ions-0.051
ra-0.048
Token.
Token ID13
Feature activation-7.14e-02

Pos logit contributions
 jog+0.011
guard+0.011
 goodbye+0.011
 bully+0.011
 stranger+0.011
Neg logit contributions
mmm-0.015
Finally-0.013
ions-0.013
mmmm-0.013
ra-0.012
Token
Token ID220
Feature activation+1.83e+00

Pos logit contributions
guard+0.002
 goodbye+0.002
 jog+0.002
 bully+0.002
 stranger+0.002
Neg logit contributions
mmm-0.004
Finally-0.003
mmmm-0.003
ions-0.003
icer-0.003
Token
Token ID198
Feature activation-5.01e-02

Pos logit contributions
mmm+0.092
Finally+0.086
ions+0.079
mmmm+0.078
icer+0.075
Neg logit contributions
 goodbye-0.051
guard-0.049
 jog-0.048
 stranger-0.048
 bully-0.046
Token
Token ID198
Feature activation-7.40e-01

Pos logit contributions
 goodbye+0.001
 jog+0.001
guard+0.001
 stranger+0.001
 bully+0.001
Neg logit contributions
mmm-0.003
Finally-0.002
mmmm-0.002
ions-0.002
icer-0.002
Token the
Token ID262
Feature activation+1.19e-01

Pos logit contributions
guard+0.017
 stranger+0.017
 nods+0.016
 bully+0.016
 wife+0.016
Neg logit contributions
mmm-0.013
Finally-0.013
 hours-0.012
Eventually-0.011
ions-0.011
Token cool
Token ID3608
Feature activation+2.07e+00

Pos logit contributions
mmm+0.005
Finally+0.005
icer+0.005
ions+0.004
mmmm+0.004
Neg logit contributions
 goodbye-0.003
 stranger-0.003
guard-0.003
 bully-0.003
 forg-0.003
Token water
Token ID1660
Feature activation+3.64e-01

Pos logit contributions
mmm+0.084
ions+0.078
icer+0.073
olk+0.072
Finally+0.072
Neg logit contributions
 aut-0.061
 stranger-0.060
 wife-0.060
 forg-0.059
 wealthy-0.059
Token and
Token ID290
Feature activation+5.65e-01

Pos logit contributions
mmm+0.014
ions+0.014
Finally+0.012
icer+0.012
ra+0.012
Neg logit contributions
 wife-0.012
 aut-0.012
 bully-0.012
 goodbye-0.012
 stranger-0.012
Token saw
Token ID2497
Feature activation+2.56e+00

Pos logit contributions
mmm+0.024
 hours+0.023
Finally+0.022
ions+0.021
Eventually+0.019
Neg logit contributions
guard-0.016
 stranger-0.016
 bully-0.016
 aut-0.016
 wife-0.015
Token the
Token ID262
Feature activation-4.95e-01

Pos logit contributions
mmm+0.111
Finally+0.105
ions+0.103
mmmm+0.095
icer+0.094
Neg logit contributions
 jog-0.076
 goodbye-0.074
guard-0.073
 bully-0.072
 stranger-0.071
Token sun
Token ID4252
Feature activation+2.08e+00

Pos logit contributions
 goodbye+0.014
guard+0.012
 jog+0.012
 stranger+0.012
 aut+0.012
Neg logit contributions
mmm-0.023
Finally-0.022
icer-0.020
ions-0.020
mmmm-0.019
Token gl
Token ID1278
Feature activation+1.01e+00

Pos logit contributions
mmm+0.091
Finally+0.081
ions+0.077
mmmm+0.075
icer+0.074
Neg logit contributions
 goodbye-0.069
 jog-0.066
 bully-0.066
 stranger-0.065
guard-0.065
Tokenint
Token ID600
Feature activation+3.68e+00

Pos logit contributions
mmm+0.033
Finally+0.029
ions+0.026
mmmm+0.025
icer+0.025
Neg logit contributions
 stranger-0.046
 goodbye-0.045
 bully-0.045
 jog-0.045
 youth-0.044
Tokening
Token ID278
Feature activation-2.16e-01

Pos logit contributions
mmm+0.161
Finally+0.146
mmmm+0.134
ions+0.133
icer+0.129
Neg logit contributions
 goodbye-0.126
 jog-0.121
guard-0.119
 stranger-0.118
 bully-0.115
Token off
Token ID572
Feature activation+1.37e-01

Pos logit contributions
 goodbye+0.006
 jog+0.006
guard+0.006
 bully+0.006
 stranger+0.006
Neg logit contributions
mmm-0.010
Finally-0.009
ions-0.008
mmmm-0.008
icer-0.008
Token more
Token ID517
Feature activation+3.00e-01

Pos logit contributions
 goodbye+0.042
guard+0.042
 jog+0.041
 stranger+0.040
 bully+0.039
Neg logit contributions
mmm-0.065
Finally-0.062
ions-0.056
mmmm-0.055
Eventually-0.053
Token careful
Token ID8161
Feature activation-1.13e-01

Pos logit contributions
mmm+0.013
Finally+0.012
mmmm+0.011
ions+0.011
ra+0.010
Neg logit contributions
 goodbye-0.010
guard-0.010
 jog-0.010
 stranger-0.010
 seal-0.009
Token when
Token ID618
Feature activation-1.08e+00

Pos logit contributions
 goodbye+0.003
 jog+0.003
guard+0.003
 new+0.003
 stranger+0.003
Neg logit contributions
mmm-0.006
Finally-0.005
mmmm-0.005
icer-0.005
ions-0.005
Token playing
Token ID2712
Feature activation-2.21e+00

Pos logit contributions
 goodbye+0.028
 jog+0.028
 new+0.027
guard+0.026
 wealthy+0.026
Neg logit contributions
mmm-0.056
Finally-0.052
mmmm-0.048
icer-0.047
ions-0.047
Token dress
Token ID6576
Feature activation-6.96e-01

Pos logit contributions
 goodbye+0.067
guard+0.064
 jog+0.063
 stranger+0.063
 bully+0.060
Neg logit contributions
mmm-0.103
Finally-0.095
ions-0.089
mmmm-0.087
icer-0.086
Token-
Token ID12
Feature activation-6.14e-01

Pos logit contributions
 stranger+0.023
 goodbye+0.023
guard+0.022
 bully+0.022
 seal+0.022
Neg logit contributions
mmm-0.031
Finally-0.027
ions-0.026
mmmm-0.025
ra-0.024
Tokenup
Token ID929
Feature activation-1.13e-01

Pos logit contributions
 goodbye+0.016
 jog+0.015
 stranger+0.015
 bully+0.014
guard+0.014
Neg logit contributions
mmm-0.032
Finally-0.030
ions-0.028
mmmm-0.028
ra-0.027
Token.
Token ID13
Feature activation-6.09e-01

Pos logit contributions
 stranger+0.004
guard+0.004
 jog+0.004
 seal+0.004
 goodbye+0.004
Neg logit contributions
mmm-0.004
ions-0.004
Finally-0.004
ra-0.003
mmmm-0.003
Token<|endoftext|>
Token ID50256
Feature activation+3.34e+00

Pos logit contributions
 goodbye+0.017
guard+0.017
 jog+0.016
 stranger+0.016
 bully+0.016
Neg logit contributions
mmm-0.031
Finally-0.028
mmmm-0.026
ions-0.026
icer-0.025
TokenOnce
Token ID7454
Feature activation+7.40e-01

Pos logit contributions
mmm+0.148
Finally+0.140
ions+0.129
icer+0.128
mmmm+0.125
Neg logit contributions
 goodbye-0.107
 jog-0.100
guard-0.099
 wife-0.098
 bully-0.098
Token upon
Token ID2402
Feature activation+7.08e-01

Pos logit contributions
mmm+0.033
Finally+0.031
ions+0.029
icer+0.028
mmmm+0.028
Neg logit contributions
 goodbye-0.023
 jog-0.022
 bully-0.022
guard-0.022
 stranger-0.022
Token she
Token ID673
Feature activation+1.04e+00

Pos logit contributions
 goodbye+0.032
 jog+0.031
guard+0.029
 new+0.029
 stranger+0.029
Neg logit contributions
mmm-0.072
Finally-0.067
mmmm-0.063
icer-0.062
ions-0.061
Token needed
Token ID2622
Feature activation+2.86e+00

Pos logit contributions
mmm+0.054
Finally+0.050
ions+0.047
mmmm+0.046
icer+0.046
Neg logit contributions
 goodbye-0.026
guard-0.024
 stranger-0.024
 jog-0.024
 youth-0.023
Token her
Token ID607
Feature activation-1.01e+00

Pos logit contributions
mmm+0.175
Finally+0.162
icer+0.158
mmmm+0.155
icious+0.148
Neg logit contributions
 goodbye-0.057
 jog-0.051
 new-0.049
guard-0.045
 stranger-0.045
Token.
Token ID13
Feature activation-8.57e-01

Pos logit contributions
guard+0.027
 stranger+0.026
 goodbye+0.026
 bully+0.026
 jog+0.024
Neg logit contributions
mmm-0.047
Finally-0.043
ions-0.042
ra-0.040
mmmm-0.039
Token Mitt
Token ID16627
Feature activation+3.01e+00

Pos logit contributions
 goodbye+0.029
 jog+0.028
 new+0.026
 en+0.025
 stranger+0.025
Neg logit contributions
mmm-0.038
Finally-0.034
ions-0.033
mmmm-0.032
icer-0.032
Tokenens
Token ID641
Feature activation-7.96e-01

Pos logit contributions
mmm+0.166
Finally+0.154
ions+0.144
mmmm+0.144
icer+0.140
Neg logit contributions
 goodbye-0.066
 jog-0.065
guard-0.062
 stranger-0.061
 bully-0.060
Token'
Token ID6
Feature activation-1.83e+00

Pos logit contributions
 goodbye+0.022
guard+0.022
 aut+0.021
 stranger+0.021
 bully+0.021
Neg logit contributions
mmm-0.036
Finally-0.035
ra-0.030
innie-0.030
mmmm-0.030
Token owner
Token ID4870
Feature activation+5.09e-01

Pos logit contributions
 goodbye+0.039
guard+0.037
 jog+0.037
 stranger+0.036
 bully+0.035
Neg logit contributions
mmm-0.100
Finally-0.094
ions-0.088
mmmm-0.087
icer-0.086
Token knew
Token ID2993
Feature activation+9.89e-01

Pos logit contributions
mmm+0.027
Finally+0.025
ions+0.023
mmmm+0.023
icer+0.023
Neg logit contributions
 goodbye-0.012
 jog-0.012
guard-0.011
 stranger-0.011
 bully-0.011
Token that
Token ID326
Feature activation-1.02e+00

Pos logit contributions
mmm+0.047
Finally+0.042
ions+0.040
mmmm+0.039
icer+0.037
Neg logit contributions
 goodbye-0.030
 jog-0.029
guard-0.028
 bully-0.028
 stranger-0.028
Token Mitt
Token ID16627
Feature activation+4.18e+00

Pos logit contributions
 goodbye+0.030
guard+0.029
 jog+0.028
 bully+0.028
 stranger+0.028
Neg logit contributions
mmm-0.048
Finally-0.043
ions-0.041
mmmm-0.040
ra-0.038
Token time
Token ID640
Feature activation-3.54e+00

Pos logit contributions
 goodbye+0.058
 jog+0.057
 stranger+0.054
 bully+0.053
guard+0.053
Neg logit contributions
mmm-0.091
Finally-0.082
ions-0.080
mmmm-0.078
icer-0.074
Token,
Token ID11
Feature activation-6.23e-01

Pos logit contributions
 goodbye+0.121
 jog+0.117
guard+0.115
 stranger+0.114
 bully+0.112
Neg logit contributions
mmm-0.154
Finally-0.139
ions-0.128
mmmm-0.128
icer-0.123
Token a
Token ID257
Feature activation-2.03e+00

Pos logit contributions
 goodbye+0.012
 jog+0.011
 new+0.011
 en+0.011
 sad+0.010
Neg logit contributions
mmm-0.037
Finally-0.034
mmmm-0.033
ions-0.032
icious-0.031
Token playful
Token ID34264
Feature activation-3.86e+00

Pos logit contributions
 goodbye+0.035
 jog+0.032
guard+0.032
 stranger+0.030
 bully+0.029
Neg logit contributions
mmm-0.122
Finally-0.114
mmmm-0.107
ions-0.106
icer-0.105
Token puppy
Token ID26188
Feature activation-3.68e+00

Pos logit contributions
 goodbye+0.083
guard+0.081
 aut+0.076
 jog+0.075
 stranger+0.070
Neg logit contributions
mmm-0.202
Finally-0.182
icer-0.176
ions-0.176
mmmm-0.175
Token named
Token ID3706
Feature activation-2.26e-01

Pos logit contributions
 goodbye+0.148
 jog+0.143
guard+0.142
 stranger+0.140
 bully+0.138
Neg logit contributions
mmm-0.137
Finally-0.122
ions-0.112
mmmm-0.110
icer-0.106
Token Max
Token ID5436
Feature activation-5.60e-01

Pos logit contributions
 goodbye+0.006
 jog+0.006
 new+0.005
 stranger+0.005
 seal+0.005
Neg logit contributions
mmm-0.012
Finally-0.011
mmmm-0.011
ions-0.011
ra-0.010
Token was
Token ID373
Feature activation-1.23e+00

Pos logit contributions
 goodbye+0.017
guard+0.016
 stranger+0.016
 aut+0.016
 bully+0.015
Neg logit contributions
mmm-0.026
Finally-0.023
ions-0.022
icer-0.021
mmmm-0.021
Token playing
Token ID2712
Feature activation-2.00e+00

Pos logit contributions
 goodbye+0.032
 jog+0.031
 stranger+0.029
guard+0.029
 bully+0.029
Neg logit contributions
mmm-0.065
Finally-0.059
mmmm-0.056
ions-0.055
icer-0.054
Token in
Token ID287
Feature activation+1.06e-01

Pos logit contributions
 goodbye+0.054
guard+0.051
 jog+0.050
 stranger+0.050
 bully+0.048
Neg logit contributions
mmm-0.100
Finally-0.094
ions-0.087
mmmm-0.086
icer-0.085
Token the
Token ID262
Feature activation-2.97e-02

Pos logit contributions
mmm+0.007
Finally+0.006
mmmm+0.006
ions+0.006
icer+0.006
Neg logit contributions
 jog-0.001
 goodbye-0.001
 new-0.001
 stranger-0.001
guard-0.001
Token scary
Token ID14343
Feature activation-1.64e+00

Pos logit contributions
 goodbye+0.034
 jog+0.029
 aut+0.029
guard+0.029
eal+0.028
Neg logit contributions
mmm-0.077
Finally-0.074
mmmm-0.066
ions-0.065
ousy-0.065
Token dog
Token ID3290
Feature activation-3.02e+00

Pos logit contributions
 goodbye+0.047
 aut+0.042
guard+0.042
 jog+0.040
 wealthy+0.038
Neg logit contributions
mmm-0.076
ra-0.065
mmmm-0.064
ousy-0.063
Finally-0.063
Token came
Token ID1625
Feature activation-2.76e+00

Pos logit contributions
 goodbye+0.075
 jog+0.070
guard+0.069
 stranger+0.068
 wealthy+0.066
Neg logit contributions
mmm-0.157
Finally-0.145
ions-0.137
mmmm-0.135
icer-0.132
Token running
Token ID2491
Feature activation-2.50e+00

Pos logit contributions
 goodbye+0.067
 jog+0.063
guard+0.062
 stranger+0.061
 bully+0.059
Neg logit contributions
mmm-0.148
Finally-0.137
ions-0.128
mmmm-0.128
icer-0.125
Token towards
Token ID3371
Feature activation-6.18e-01

Pos logit contributions
 goodbye+0.057
 jog+0.054
guard+0.053
 stranger+0.051
 bully+0.051
Neg logit contributions
mmm-0.136
Finally-0.127
ions-0.119
mmmm-0.118
icer-0.116
Token them
Token ID606
Feature activation-4.20e+00

Pos logit contributions
 goodbye+0.017
 jog+0.017
 stranger+0.016
guard+0.016
 bully+0.015
Neg logit contributions
mmm-0.031
Finally-0.029
mmmm-0.027
ions-0.026
icer-0.026
Token.
Token ID13
Feature activation-5.22e-01

Pos logit contributions
 goodbye+0.121
 jog+0.118
guard+0.114
 stranger+0.112
 bully+0.110
Neg logit contributions
mmm-0.208
Finally-0.191
mmmm-0.179
ions-0.175
icer-0.172
Token Lily
Token ID20037
Feature activation+1.63e+00

Pos logit contributions
guard+0.022
 aut+0.019
 jog+0.019
 stranger+0.018
 seal+0.018
Neg logit contributions
mmm-0.018
Finally-0.017
 Finally-0.015
mmmm-0.014
icer-0.014
Token was
Token ID373
Feature activation-5.13e-01

Pos logit contributions
mmm+0.080
Finally+0.076
ra+0.068
icer+0.067
ousy+0.066
Neg logit contributions
 goodbye-0.045
guard-0.042
 aut-0.041
 stranger-0.039
 jog-0.038
Token scared
Token ID12008
Feature activation-1.34e+00

Pos logit contributions
guard+0.020
 goodbye+0.018
 aut+0.017
ability+0.017
earned+0.017
Neg logit contributions
ousy-0.016
Finally-0.016
 nine-0.015
mmm-0.015
pped-0.014
Token and
Token ID290
Feature activation-1.92e+00

Pos logit contributions
 goodbye+0.033
 jog+0.032
guard+0.031
 stranger+0.031
 bully+0.030
Neg logit contributions
mmm-0.072
Finally-0.066
mmmm-0.062
ions-0.062
icer-0.061
Token agreed
Token ID4987
Feature activation-2.96e+00

Pos logit contributions
mmm+0.077
Finally+0.072
ra+0.067
innie+0.066
ions+0.064
Neg logit contributions
 goodbye-0.055
 stranger-0.051
 jog-0.051
 youth-0.050
 bully-0.049
Token and
Token ID290
Feature activation-3.18e+00

Pos logit contributions
 goodbye+0.078
 jog+0.076
guard+0.074
 stranger+0.073
 bully+0.073
Neg logit contributions
mmm-0.152
Finally-0.139
mmmm-0.130
ions-0.129
icer-0.124
Token the
Token ID262
Feature activation-2.86e+00

Pos logit contributions
 jog+0.091
 goodbye+0.091
 stranger+0.089
 bully+0.086
guard+0.086
Neg logit contributions
mmm-0.152
Finally-0.133
ions-0.131
mmmm-0.125
ra-0.122
Token two
Token ID734
Feature activation+3.33e-01

Pos logit contributions
 goodbye+0.093
guard+0.089
 stranger+0.085
eal+0.084
 jog+0.083
Neg logit contributions
mmm-0.115
Finally-0.113
ra-0.099
mmmm-0.096
 nine-0.092
Token of
Token ID286
Feature activation-1.19e+00

Pos logit contributions
mmm+0.016
Finally+0.015
ions+0.014
mmmm+0.014
icer+0.013
Neg logit contributions
 goodbye-0.009
 jog-0.009
guard-0.009
 stranger-0.009
 bully-0.008
Token them
Token ID606
Feature activation-5.69e+00

Pos logit contributions
guard+0.034
 goodbye+0.034
 new+0.034
 jog+0.034
 stranger+0.032
Neg logit contributions
mmm-0.059
Finally-0.053
mmmm-0.050
icer-0.047
ra-0.047
Token set
Token ID900
Feature activation-4.81e-01

Pos logit contributions
 goodbye+0.138
 jog+0.132
 stranger+0.129
guard+0.129
 bully+0.126
Neg logit contributions
mmm-0.296
Finally-0.275
ions-0.260
mmmm-0.255
icer-0.249
Token off
Token ID572
Feature activation-2.82e+00

Pos logit contributions
 stranger+0.013
guard+0.013
 jog+0.013
 goodbye+0.013
 bully+0.013
Neg logit contributions
mmm-0.023
Finally-0.021
ions-0.020
ra-0.019
mmmm-0.019
Token on
Token ID319
Feature activation-2.66e-01

Pos logit contributions
 goodbye+0.087
 jog+0.086
guard+0.084
 stranger+0.084
 bully+0.083
Neg logit contributions
mmm-0.126
Finally-0.116
ions-0.111
mmmm-0.106
icer-0.104
Token a
Token ID257
Feature activation+1.19e+00

Pos logit contributions
 new+0.004
 jog+0.004
 goodbye+0.004
 aut+0.003
 wealthy+0.003
Neg logit contributions
mmm-0.017
Finally-0.016
mmmm-0.015
ions-0.015
icious-0.014
Token journey
Token ID7002
Feature activation-3.29e+00

Pos logit contributions
mmm+0.061
Finally+0.057
mmmm+0.051
ions+0.051
icer+0.051
Neg logit contributions
 goodbye-0.030
guard-0.029
 bully-0.028
 jog-0.027
 stranger-0.027
Token Today
Token ID6288
Feature activation+2.08e+00

Pos logit contributions
 goodbye+0.036
 jog+0.034
 en+0.031
 youth+0.030
 stranger+0.030
Neg logit contributions
mmm-0.083
Finally-0.076
icer-0.073
ions-0.073
mmmm-0.072
Token,
Token ID11
Feature activation+1.10e-02

Pos logit contributions
mmm+0.095
Finally+0.085
ions+0.079
mmmm+0.079
icer+0.076
Neg logit contributions
 goodbye-0.065
 jog-0.063
guard-0.062
 stranger-0.062
 bully-0.061
Token Tom
Token ID4186
Feature activation-4.75e-01

Pos logit contributions
mmm+0.001
Finally+0.001
mmmm+0.001
icer+0.001
ions+0.001
Neg logit contributions
 goodbye-0.000
 jog-0.000
 stranger-0.000
guard-0.000
 new-0.000
Token goes
Token ID2925
Feature activation-3.42e+00

Pos logit contributions
 goodbye+0.012
guard+0.012
 stranger+0.012
 jog+0.011
 aut+0.011
Neg logit contributions
mmm-0.023
Finally-0.021
ra-0.020
icer-0.020
ions-0.019
Token to
Token ID284
Feature activation-1.39e+00

Pos logit contributions
 bully+0.077
 en+0.071
 goodbye+0.069
guard+0.068
 stranger+0.068
Neg logit contributions
mmm-0.162
Finally-0.159
ions-0.157
icer-0.147
 nine-0.147
Token visit
Token ID3187
Feature activation-4.29e+00

Pos logit contributions
 goodbye+0.032
guard+0.031
 stranger+0.029
 jog+0.028
 bully+0.028
Neg logit contributions
mmm-0.074
Finally-0.068
mmmm-0.064
ions-0.064
icer-0.063
Token Mia
Token ID32189
Feature activation+2.36e+00

Pos logit contributions
 goodbye+0.075
 jog+0.069
 stranger+0.065
guard+0.065
 new+0.062
Neg logit contributions
mmm-0.262
Finally-0.245
mmmm-0.231
ions-0.230
icer-0.225
Token at
Token ID379
Feature activation-2.03e+00

Pos logit contributions
mmm+0.117
Finally+0.108
ions+0.101
icer+0.100
mmmm+0.098
Neg logit contributions
 goodbye-0.058
guard-0.057
 bully-0.056
 stranger-0.056
 jog-0.054
Token her
Token ID607
Feature activation-2.29e+00

Pos logit contributions
 goodbye+0.048
 jog+0.046
guard+0.045
 stranger+0.044
 bully+0.043
Neg logit contributions
mmm-0.109
Finally-0.100
ions-0.095
mmmm-0.094
icer-0.092
Token house
Token ID2156
Feature activation-1.07e-01

Pos logit contributions
 goodbye+0.070
guard+0.068
eal+0.066
 bully+0.065
 stranger+0.065
Neg logit contributions
mmm-0.100
Finally-0.090
mmmm-0.082
ions-0.082
icer-0.082
Token.
Token ID13
Feature activation-2.09e-01

Pos logit contributions
 goodbye+0.003
 jog+0.003
guard+0.003
 stranger+0.003
 bully+0.003
Neg logit contributions
mmm-0.005
Finally-0.005
mmmm-0.004
ions-0.004
icer-0.004
Tokenberries
Token ID20853
Feature activation+2.83e+00

Pos logit contributions
mmm+0.172
Finally+0.164
ra+0.137
mmmm+0.135
Eventually+0.131
Neg logit contributions
guard-0.184
 jog-0.183
 stranger-0.179
 youth-0.176
 goodbye-0.175
Token.
Token ID13
Feature activation-5.65e-01

Pos logit contributions
mmm+0.135
Finally+0.123
mmmm+0.114
ions+0.113
icer+0.111
Neg logit contributions
 goodbye-0.085
 jog-0.082
guard-0.081
 stranger-0.080
 bully-0.077
Token One
Token ID1881
Feature activation+4.77e+00

Pos logit contributions
 goodbye+0.017
 jog+0.017
 new+0.016
 stranger+0.015
 youth+0.015
Neg logit contributions
mmm-0.027
Finally-0.024
ions-0.023
ra-0.023
mmmm-0.023
Token day
Token ID1110
Feature activation-1.36e+00

Pos logit contributions
mmm+0.171
Finally+0.152
ousy+0.145
mmmm+0.139
icer+0.138
Neg logit contributions
 goodbye-0.185
 aut-0.182
 bully-0.182
guard-0.179
eal-0.174
Token while
Token ID981
Feature activation-7.23e-01

Pos logit contributions
 goodbye+0.041
 jog+0.039
 stranger+0.037
 new+0.037
guard+0.036
Neg logit contributions
mmm-0.066
Finally-0.061
mmmm-0.057
icer-0.056
ions-0.056
Token out
Token ID503
Feature activation-4.21e+00

Pos logit contributions
 goodbye+0.015
 jog+0.015
 new+0.014
 youth+0.013
 wealthy+0.013
Neg logit contributions
mmm-0.043
Finally-0.039
mmmm-0.038
icer-0.037
icious-0.037
Token picking
Token ID10868
Feature activation+3.08e-01

Pos logit contributions
 goodbye+0.130
 jog+0.125
guard+0.122
 stranger+0.120
 bully+0.119
Neg logit contributions
mmm-0.199
Finally-0.182
mmmm-0.168
ions-0.164
icer-0.162
Token r
Token ID374
Feature activation+3.06e+00

Pos logit contributions
mmm+0.016
Finally+0.015
mmmm+0.013
ions+0.013
ra+0.013
Neg logit contributions
 goodbye-0.008
 new-0.008
 jog-0.008
 stranger-0.008
 wealthy-0.007
Tokenasp
Token ID5126
Feature activation+4.91e+00

Pos logit contributions
mmm+0.126
Finally+0.115
ra+0.103
mmmm+0.102
Eventually+0.092
Neg logit contributions
 jog-0.102
guard-0.102
 en-0.100
 new-0.100
 wealthy-0.100
Tokenberries
Token ID20853
Feature activation+3.35e+00

Pos logit contributions
mmm+0.163
Finally+0.149
mmmm+0.126
ra+0.121
ions+0.120
Neg logit contributions
 jog-0.209
 goodbye-0.208
guard-0.208
 stranger-0.204
 youth-0.200
Token she
Token ID673
Feature activation+3.31e+00

Pos logit contributions
mmm+0.145
Finally+0.130
ions+0.122
mmmm+0.120
icer+0.116
Neg logit contributions
 goodbye-0.116
 jog-0.111
guard-0.109
 stranger-0.109
 bully-0.108
TokenLuckily
Token ID42332
Feature activation+1.03e+00

Pos logit contributions
 goodbye+0.027
 jog+0.026
 stranger+0.026
guard+0.026
 bully+0.025
Neg logit contributions
mmm-0.025
Finally-0.021
ions-0.020
mmmm-0.020
icer-0.020
Token,
Token ID11
Feature activation-6.57e-01

Pos logit contributions
mmm+0.045
Finally+0.040
ions+0.037
mmmm+0.037
icer+0.036
Neg logit contributions
 goodbye-0.034
 jog-0.034
guard-0.033
 stranger-0.033
 bully-0.033
Token soon
Token ID2582
Feature activation+1.15e+00

Pos logit contributions
 goodbye+0.020
 jog+0.020
guard+0.020
 bully+0.019
 stranger+0.019
Neg logit contributions
mmm-0.030
Finally-0.028
mmmm-0.026
ions-0.025
icer-0.024
Token a
Token ID257
Feature activation-1.26e+00

Pos logit contributions
mmm+0.047
Finally+0.041
mmmm+0.038
ions+0.038
 hours+0.036
Neg logit contributions
 bully-0.039
guard-0.039
 jog-0.039
 aut-0.039
 en-0.038
Token grown
Token ID7334
Feature activation-1.32e+00

Pos logit contributions
 goodbye+0.023
 jog+0.021
guard+0.021
 aut+0.019
 bully+0.019
Neg logit contributions
mmm-0.072
Finally-0.069
mmmm-0.063
ions-0.063
icer-0.061
Token up
Token ID510
Feature activation-4.13e+00

Pos logit contributions
 goodbye+0.051
 jog+0.050
 bully+0.048
 sport+0.047
 aut+0.047
Neg logit contributions
mmm-0.043
Finally-0.041
ions-0.039
ra-0.039
 centimeters-0.038
Token came
Token ID1625
Feature activation-2.31e+00

Pos logit contributions
 goodbye+0.118
 bully+0.114
 jog+0.113
 aut+0.110
 stranger+0.109
Neg logit contributions
mmm-0.187
Finally-0.170
ions-0.166
ra-0.162
mmmm-0.154
Token to
Token ID284
Feature activation-3.68e-01

Pos logit contributions
 goodbye+0.064
 jog+0.062
 bully+0.061
guard+0.061
 stranger+0.060
Neg logit contributions
mmm-0.110
Finally-0.102
ions-0.096
mmmm-0.093
ra-0.092
Token help
Token ID1037
Feature activation-1.25e+00

Pos logit contributions
 goodbye+0.010
 jog+0.009
guard+0.009
 stranger+0.009
 bully+0.009
Neg logit contributions
mmm-0.019
Finally-0.017
mmmm-0.016
ions-0.016
icer-0.016
Token.
Token ID13
Feature activation-4.58e-01

Pos logit contributions
 goodbye+0.037
 jog+0.035
guard+0.035
 stranger+0.034
 bully+0.033
Neg logit contributions
mmm-0.060
Finally-0.055
mmmm-0.051
ions-0.051
icer-0.050
Token She
Token ID1375
Feature activation+2.19e+00

Pos logit contributions
guard+0.017
 jog+0.017
 bully+0.016
 goodbye+0.016
 sport+0.016
Neg logit contributions
mmm-0.019
Finally-0.016
mmmm-0.016
ions-0.014
Eventually-0.013