TOP ACTIVATIONS
MAX = 0.425

and his bottle of g rog . He
and said , " F rog !" He put the card
the bee . Tim and Buzz became friends . They loved
name was Buzz y . Buzz y was a hard -
adow . His name was Buzz y . Buzz y was
the bird came back , Buzz and his friends threw the
I like your hive ." Buzz y smiled and said ,
friends . One day , Buzz y wanted to go outside
't mean to , but Buzz was too small for her
little bee named Buzz . Buzz lived in a hive with
hive with his friends . Buzz liked to fly around and
Andy . Buzz felt sorry for the poor
the net . Buzz told the bird , "
was a little bee named Buzz . Buzz lived in a
Lily loved Buzz , and Buzz loved Lily .
throwing . " Buzz ! Buzz !" a bee
his name . Now , Buzz was happy because he could
anymore . After playing , Buzz y went back to the
she played . Lily loved Buzz , and Buzz loved Lily
bee named Buzz y . Buzz y loved to rush from

MIN ACTIVATIONS
MIN = -0.434

ribbon for being the best bal ancer in the competition .
made him squ int . Tyler raced ahead of his mom
as he got closer , Tyler felt his heart start to
like a giant iron . Tyler couldn 't believe his eyes
was a little boy named Seth . Seth loved watching his
little boy named Seth . Seth loved watching his favorite show
show started to freeze ! Seth was very surprised and felt
was a giant fish ! Tyler gasped with delight and his
he made a bridge ! Tyler was so happy . He
all of a sudden , Tyler saw a big black cloud
Next , Bobby and then Tyler . When it
so big and bright and Tyler was scared .
lot of fun today . Tyler wanted to relax and enjoy
dark storm clouds above . Tyler started to worry , because
the store and got the bal m . She carefully rubbed
started to come down and Tyler knew it was time to
The monster grabbed Tyler and said , " You
boy . He was called Tyler . Tyler liked to explore
's good for you !" Tyler couldn 't help but g
" We must get Tyler out of the fire !"

INTERVAL 0.210 - 0.425
CONTAINS 0.614%

a time there was a True who was very spoiled .
his paw to get the frog 's attention .
?" The j olly man smiled and said ,
get . True to his mom 's words
Jake thought for a moment and then he decided to

INTERVAL -0.005 - 0.210
CONTAINS 51.355%

because her favorite toy had been ruined by the rain .
drops falling from the sky and she wanted to catch one
for them . She says some dogs are too big or
twisted the balloon very fast and very hard . They made
way , the bird could stay for longer and have a

INTERVAL -0.219 - -0.005
CONTAINS 47.742%

years old . One day he was walking around the city
told everyone what to do . One day , she decided
stories with her mom and dad and they praised her for
day , a man with an ugly face came to the
him to wipe it off . The little boy

INTERVAL -0.434 - -0.219
CONTAINS 0.290%

could talk to her friends even longer . So she decided
agreed and kindly gave Little Johnny the zipper .
Grand ma got out three m ugs and poured a big
Her nos y cat , Mitt ens , was following her
help the cut heal . Cand ace was so proud of
Token and
Token ID290
Feature activation+6.20e-02

Pos logit contributions
 bal+0.065
 Seth+0.063
 Tyler+0.062
ird+0.061
uka+0.061
Neg logit contributions
rog-0.053
acle-0.051
arium-0.050
 Buzz-0.048
Buzz-0.048
Token his
Token ID465
Feature activation-2.96e-02

Pos logit contributions
rog+0.094
acle+0.090
arium+0.089
 Buzz+0.086
Buzz+0.085
Neg logit contributions
 bal-0.096
 Seth-0.093
 Tyler-0.092
ird-0.090
uka-0.090
Token bottle
Token ID9294
Feature activation+2.70e-02

Pos logit contributions
 bal+0.041
 Seth+0.039
 Tyler+0.038
ird+0.037
isc+0.037
Neg logit contributions
rog-0.051
arium-0.049
acle-0.048
Buzz-0.047
 Buzz-0.046
Token of
Token ID286
Feature activation-5.18e-02

Pos logit contributions
rog+0.043
arium+0.041
acle+0.041
Buzz+0.039
 Buzz+0.039
Neg logit contributions
 bal-0.040
 Seth-0.039
 Tyler-0.039
ird-0.038
cest-0.037
Token g
Token ID308
Feature activation-3.29e-02

Pos logit contributions
 bal+0.080
 Seth+0.077
 Tyler+0.076
ird+0.075
 laund+0.074
Neg logit contributions
rog-0.079
acle-0.077
arium-0.076
Buzz-0.072
 Buzz-0.071
Tokenrog
Token ID3828
Feature activation+4.09e-01

Pos logit contributions
 bal+0.056
 Seth+0.054
 Tyler+0.053
ird+0.053
isc+0.053
Neg logit contributions
rog-0.046
acle-0.044
arium-0.044
Buzz-0.042
 Buzz-0.041
Token.
Token ID13
Feature activation-9.42e-04

Pos logit contributions
rog+0.656
acle+0.635
arium+0.624
Buzz+0.602
 Buzz+0.594
Neg logit contributions
 bal-0.604
 Seth-0.571
 Tyler-0.571
ird-0.562
cest-0.558
Token
Token ID220
Feature activation+5.10e-02

Pos logit contributions
 bal+0.002
cest+0.002
 Seth+0.002
 laund+0.002
ird+0.002
Neg logit contributions
rog-0.001
 Buzz-0.001
acle-0.001
arium-0.001
Buzz-0.001
Token
Token ID198
Feature activation-2.36e-02

Pos logit contributions
rog+0.077
acle+0.074
arium+0.073
 Buzz+0.071
Buzz+0.071
Neg logit contributions
 bal-0.078
 Seth-0.076
 Tyler-0.075
ird-0.074
cest-0.073
Token
Token ID198
Feature activation-2.57e-02

Pos logit contributions
 bal+0.032
 Seth+0.032
 Tyler+0.031
uka+0.031
ird+0.030
Neg logit contributions
acle-0.040
rog-0.039
arium-0.039
atively-0.037
 Buzz-0.036
TokenHe
Token ID1544
Feature activation-3.55e-02

Pos logit contributions
 bal+0.039
 Seth+0.037
 Tyler+0.037
ird+0.036
uka+0.036
Neg logit contributions
rog-0.040
acle-0.039
arium-0.039
 Buzz-0.037
atively-0.036
Token and
Token ID290
Feature activation+4.91e-03

Pos logit contributions
acle+0.168
rog+0.156
 Buzz+0.154
arium+0.153
atively+0.149
Neg logit contributions
ird-0.282
uka-0.273
 laund-0.268
 Seth-0.264
isc-0.263
Token said
Token ID531
Feature activation-7.36e-04

Pos logit contributions
 Buzz+0.006
acle+0.006
rog+0.005
Buzz+0.005
arium+0.005
Neg logit contributions
ird-0.009
 laund-0.009
isc-0.009
uka-0.009
 bal-0.009
Token,
Token ID11
Feature activation-9.54e-03

Pos logit contributions
 bal+0.001
 Seth+0.001
 Tyler+0.001
ird+0.001
uka+0.001
Neg logit contributions
rog-0.001
acle-0.001
arium-0.001
 Buzz-0.001
Buzz-0.001
Token "
Token ID366
Feature activation-6.46e-02

Pos logit contributions
 bal+0.013
 Seth+0.013
 Tyler+0.013
ird+0.013
uka+0.013
Neg logit contributions
rog-0.016
acle-0.015
arium-0.015
 Buzz-0.015
Buzz-0.015
TokenF
Token ID37
Feature activation-1.50e-01

Pos logit contributions
 bal+0.114
 Tyler+0.113
 Seth+0.113
ird+0.112
isc+0.110
Neg logit contributions
rog-0.083
Buzz-0.078
acle-0.077
arium-0.075
 Buzz-0.075
Tokenrog
Token ID3828
Feature activation+3.98e-01

Pos logit contributions
 roller+0.268
ird+0.267
 bal+0.264
uka+0.262
 Seth+0.259
Neg logit contributions
atively-0.166
acle-0.158
 Buzz-0.150
rus-0.147
Buzz-0.146
Token!"
Token ID2474
Feature activation-6.31e-02

Pos logit contributions
rog+0.648
acle+0.643
arium+0.622
Buzz+0.612
atively+0.606
Neg logit contributions
 bal-0.555
 Tyler-0.532
 Seth-0.529
cest-0.519
ird-0.514
Token He
Token ID679
Feature activation+3.24e-03

Pos logit contributions
 bal+0.105
 Seth+0.101
 Tyler+0.101
ird+0.101
cest+0.101
Neg logit contributions
rog-0.088
acle-0.085
arium-0.083
 Buzz-0.081
Buzz-0.079
Token put
Token ID1234
Feature activation-7.99e-02

Pos logit contributions
rog+0.005
acle+0.005
arium+0.004
 Buzz+0.004
Buzz+0.004
Neg logit contributions
 bal-0.005
 Seth-0.005
 Tyler-0.005
ird-0.005
uka-0.005
Token the
Token ID262
Feature activation-1.93e-02

Pos logit contributions
 bal+0.117
 Seth+0.115
 Tyler+0.114
uka+0.111
ird+0.109
Neg logit contributions
rog-0.127
acle-0.123
arium-0.122
Buzz-0.117
 Buzz-0.116
Token card
Token ID2657
Feature activation+1.04e-01

Pos logit contributions
 sax+0.025
 roller+0.024
 bal+0.024
ird+0.024
cest+0.023
Neg logit contributions
rog-0.034
 Buzz-0.032
Buzz-0.032
atively-0.031
arium-0.031
Token the
Token ID262
Feature activation+1.47e-02

Pos logit contributions
rog+0.067
acle+0.064
arium+0.064
Buzz+0.062
 Buzz+0.060
Neg logit contributions
 bal-0.067
 Seth-0.065
 Tyler-0.064
ird-0.063
uka-0.062
Token bee
Token ID20697
Feature activation+1.60e-01

Pos logit contributions
rog+0.023
arium+0.022
acle+0.022
Buzz+0.021
 Buzz+0.021
Neg logit contributions
 bal-0.022
 Seth-0.021
 Tyler-0.021
 roller-0.021
ird-0.020
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
rog+0.262
acle+0.259
arium+0.251
Buzz+0.243
atively+0.235
Neg logit contributions
 bal-0.226
 Seth-0.207
ird-0.204
cest-0.204
 Tyler-0.203
Token Tim
Token ID5045
Feature activation+1.20e-02

Pos logit contributions
rog+0.015
acle+0.014
arium+0.014
 Buzz+0.014
Buzz+0.014
Neg logit contributions
 bal-0.017
cest-0.017
 Seth-0.017
 laund-0.016
 Tyler-0.016
Token and
Token ID290
Feature activation+2.02e-02

Pos logit contributions
rog+0.018
acle+0.018
arium+0.017
 Buzz+0.017
Buzz+0.017
Neg logit contributions
 bal-0.018
 Tyler-0.018
 Seth-0.018
ird-0.017
uka-0.017
Token Buzz
Token ID15753
Feature activation+3.97e-01

Pos logit contributions
rog+0.029
acle+0.028
arium+0.028
 Buzz+0.027
Buzz+0.027
Neg logit contributions
 bal-0.033
 Seth-0.032
 Tyler-0.031
ird-0.031
uka-0.031
Token became
Token ID2627
Feature activation+5.42e-02

Pos logit contributions
rog+0.625
acle+0.612
arium+0.597
atively+0.562
 Buzz+0.554
Neg logit contributions
 bal-0.583
 Seth-0.559
ird-0.557
 Tyler-0.552
cest-0.544
Token friends
Token ID2460
Feature activation+7.76e-04

Pos logit contributions
 Buzz+0.075
rog+0.072
Buzz+0.072
 True+0.066
acle+0.065
Neg logit contributions
ird-0.093
isc-0.092
 Tyler-0.089
 bal-0.088
 Seth-0.087
Token.
Token ID13
Feature activation+6.90e-03

Pos logit contributions
rog+0.001
acle+0.001
arium+0.001
Buzz+0.001
 Buzz+0.001
Neg logit contributions
 bal-0.001
 Seth-0.001
 Tyler-0.001
ird-0.001
uka-0.001
Token They
Token ID1119
Feature activation+8.96e-02

Pos logit contributions
rog+0.010
acle+0.010
arium+0.010
atively+0.010
Buzz+0.009
Neg logit contributions
 bal-0.010
 Seth-0.010
 Tyler-0.010
 Sel-0.010
 Coc-0.010
Token loved
Token ID6151
Feature activation+3.30e-03

Pos logit contributions
rog+0.129
acle+0.124
arium+0.122
 Buzz+0.117
Buzz+0.117
Neg logit contributions
 bal-0.145
 Seth-0.141
 Tyler-0.140
ird-0.138
uka-0.137
Token name
Token ID1438
Feature activation-2.54e-02

Pos logit contributions
rog+0.009
acle+0.009
arium+0.009
Buzz+0.008
atively+0.008
Neg logit contributions
 bal-0.007
 Seth-0.007
 Tyler-0.007
isc-0.007
 Sel-0.007
Token was
Token ID373
Feature activation+2.50e-03

Pos logit contributions
 bal+0.044
 Seth+0.043
 Tyler+0.042
 laund+0.042
ird+0.042
Neg logit contributions
rog-0.033
acle-0.032
 Buzz-0.032
arium-0.032
Buzz-0.031
Token Buzz
Token ID15753
Feature activation+3.87e-01

Pos logit contributions
rog+0.003
 Buzz+0.003
arium+0.003
acle+0.003
Buzz+0.003
Neg logit contributions
 bal-0.004
ird-0.004
 Seth-0.004
 laund-0.004
 Tyler-0.004
Tokeny
Token ID88
Feature activation+1.35e-01

Pos logit contributions
acle+0.615
rog+0.605
arium+0.581
atively+0.569
Buzz+0.545
Neg logit contributions
 bal-0.572
cest-0.554
 Tyler-0.524
 Seth-0.523
uka-0.513
Token.
Token ID13
Feature activation+1.45e-02

Pos logit contributions
rog+0.224
acle+0.217
arium+0.212
Buzz+0.207
atively+0.202
Neg logit contributions
 bal-0.189
 Tyler-0.176
 Seth-0.176
cest-0.173
 Sel-0.168
Token Buzz
Token ID15753
Feature activation+3.88e-01

Pos logit contributions
acle+0.023
atively+0.021
rog+0.021
arium+0.021
isy+0.020
Neg logit contributions
 bal-0.021
 Seth-0.020
 Tyler-0.020
 Coc-0.020
 Sel-0.019
Tokeny
Token ID88
Feature activation+1.35e-01

Pos logit contributions
acle+0.634
atively+0.580
rog+0.568
arium+0.548
osis+0.503
Neg logit contributions
cest-0.580
 bal-0.562
 Sel-0.501
 Seth-0.495
 Tyler-0.493
Token was
Token ID373
Feature activation+2.02e-04

Pos logit contributions
rog+0.230
acle+0.230
arium+0.216
atively+0.211
Buzz+0.206
Neg logit contributions
 bal-0.178
 Tyler-0.163
 Seth-0.160
cest-0.158
 Sel-0.158
Token a
Token ID257
Feature activation+7.13e-02

Pos logit contributions
rog+0.000
acle+0.000
arium+0.000
Buzz+0.000
atively+0.000
Neg logit contributions
 bal-0.000
 Seth-0.000
 Tyler-0.000
uka-0.000
 Sel-0.000
Token hard
Token ID1327
Feature activation+1.03e-01

Pos logit contributions
rog+0.103
acle+0.098
arium+0.097
 Buzz+0.094
Buzz+0.094
Neg logit contributions
 bal-0.115
 Seth-0.113
 Tyler-0.113
ird-0.111
uka-0.109
Token-
Token ID12
Feature activation-3.35e-02

Pos logit contributions
rog+0.156
acle+0.155
arium+0.151
Buzz+0.145
 Buzz+0.143
Neg logit contributions
 bal-0.160
cest-0.148
 Seth-0.147
 Tyler-0.145
uka-0.143
Tokenadow
Token ID4584
Feature activation+7.58e-02

Pos logit contributions
rog+0.223
acle+0.218
Buzz+0.209
atively+0.208
arium+0.208
Neg logit contributions
 bal-0.213
ird-0.208
cest-0.196
 Seth-0.194
uka-0.193
Token.
Token ID13
Feature activation+8.11e-03

Pos logit contributions
rog+0.152
Buzz+0.139
acky+0.138
osis+0.135
arium+0.132
Neg logit contributions
 bal-0.078
cest-0.071
ird-0.066
 Seth-0.063
 Su-0.060
Token His
Token ID2399
Feature activation+5.32e-03

Pos logit contributions
rog+0.012
acle+0.011
arium+0.011
atively+0.011
Buzz+0.010
Neg logit contributions
 bal-0.013
 Seth-0.013
 Tyler-0.013
ird-0.012
 Sel-0.012
Token name
Token ID1438
Feature activation-2.54e-02

Pos logit contributions
rog+0.009
acle+0.009
arium+0.009
Buzz+0.008
atively+0.008
Neg logit contributions
 bal-0.007
 Seth-0.007
 Tyler-0.007
isc-0.007
 Sel-0.007
Token was
Token ID373
Feature activation+2.50e-03

Pos logit contributions
 bal+0.044
 Seth+0.043
 Tyler+0.042
 laund+0.042
ird+0.042
Neg logit contributions
rog-0.033
acle-0.032
 Buzz-0.032
arium-0.032
Buzz-0.031
Token Buzz
Token ID15753
Feature activation+3.87e-01

Pos logit contributions
rog+0.003
 Buzz+0.003
arium+0.003
acle+0.003
Buzz+0.003
Neg logit contributions
 bal-0.004
ird-0.004
 Seth-0.004
 laund-0.004
 Tyler-0.004
Tokeny
Token ID88
Feature activation+1.35e-01

Pos logit contributions
acle+0.615
rog+0.605
arium+0.581
atively+0.569
Buzz+0.545
Neg logit contributions
 bal-0.572
cest-0.554
 Tyler-0.524
 Seth-0.523
uka-0.513
Token.
Token ID13
Feature activation+1.45e-02

Pos logit contributions
rog+0.224
acle+0.217
arium+0.212
Buzz+0.207
atively+0.202
Neg logit contributions
 bal-0.189
 Tyler-0.176
 Seth-0.176
cest-0.173
 Sel-0.168
Token Buzz
Token ID15753
Feature activation+3.88e-01

Pos logit contributions
acle+0.023
atively+0.021
rog+0.021
arium+0.021
isy+0.020
Neg logit contributions
 bal-0.021
 Seth-0.020
 Tyler-0.020
 Coc-0.020
 Sel-0.019
Tokeny
Token ID88
Feature activation+1.35e-01

Pos logit contributions
acle+0.634
atively+0.580
rog+0.568
arium+0.548
osis+0.503
Neg logit contributions
cest-0.580
 bal-0.562
 Sel-0.501
 Seth-0.495
 Tyler-0.493
Token was
Token ID373
Feature activation+2.02e-04

Pos logit contributions
rog+0.230
acle+0.230
arium+0.216
atively+0.211
Buzz+0.206
Neg logit contributions
 bal-0.178
 Tyler-0.163
 Seth-0.160
cest-0.158
 Sel-0.158
Token the
Token ID262
Feature activation-6.89e-03

Pos logit contributions
rog+0.054
acle+0.052
arium+0.051
Buzz+0.049
 Buzz+0.049
Neg logit contributions
 bal-0.053
 Seth-0.051
 Tyler-0.051
ird-0.049
uka-0.049
Token bird
Token ID6512
Feature activation+9.41e-02

Pos logit contributions
 bal+0.010
 Seth+0.009
 roller+0.009
 Tyler+0.009
 laund+0.009
Neg logit contributions
rog-0.012
acle-0.011
arium-0.011
 Buzz-0.011
Buzz-0.011
Token came
Token ID1625
Feature activation-2.22e-02

Pos logit contributions
rog+0.152
acle+0.149
arium+0.141
atively+0.136
Buzz+0.136
Neg logit contributions
 bal-0.138
 Seth-0.131
 Tyler-0.129
ird-0.128
cest-0.127
Token back
Token ID736
Feature activation+1.73e-02

Pos logit contributions
 bal+0.030
 Seth+0.029
 Tyler+0.027
 Su+0.026
cest+0.026
Neg logit contributions
rog-0.038
arium-0.037
acle-0.036
Buzz-0.035
acky-0.034
Token,
Token ID11
Feature activation-1.32e-02

Pos logit contributions
rog+0.026
acle+0.025
arium+0.025
 Buzz+0.024
Buzz+0.024
Neg logit contributions
 bal-0.027
 Seth-0.026
 Tyler-0.026
ird-0.026
uka-0.026
Token Buzz
Token ID15753
Feature activation+3.86e-01

Pos logit contributions
 bal+0.021
ird+0.021
 laund+0.020
 Tyler+0.020
isc+0.020
Neg logit contributions
rog-0.019
 Buzz-0.018
acle-0.018
arium-0.018
Buzz-0.017
Token and
Token ID290
Feature activation-1.15e-03

Pos logit contributions
rog+0.637
acle+0.608
arium+0.586
atively+0.561
Buzz+0.552
Neg logit contributions
 bal-0.549
cest-0.532
 Seth-0.519
 Tyler-0.511
ird-0.509
Token his
Token ID465
Feature activation-7.76e-02

Pos logit contributions
 Seth+0.001
 bal+0.001
 Tyler+0.001
 Sel+0.001
cest+0.001
Neg logit contributions
rog-0.002
acle-0.002
arium-0.002
agged-0.002
atively-0.002
Token friends
Token ID2460
Feature activation-1.14e-03

Pos logit contributions
 bal+0.100
 roller+0.091
 Seth+0.091
isc+0.089
 Tyler+0.088
Neg logit contributions
rog-0.141
arium-0.139
acle-0.135
Buzz-0.127
atively-0.126
Token threw
Token ID9617
Feature activation-4.23e-02

Pos logit contributions
 bal+0.002
 Seth+0.002
 Tyler+0.002
ird+0.002
cest+0.002
Neg logit contributions
rog-0.002
acle-0.002
arium-0.002
Buzz-0.002
 Buzz-0.002
Token the
Token ID262
Feature activation-8.54e-03

Pos logit contributions
 bal+0.055
 Seth+0.052
 Tyler+0.051
 Ther+0.049
 roller+0.049
Neg logit contributions
acle-0.077
rog-0.075
arium-0.075
atively-0.071
isy-0.068
Token I
Token ID314
Feature activation-4.67e-03

Pos logit contributions
rog+0.023
acle+0.022
arium+0.022
 Buzz+0.022
Buzz+0.021
Neg logit contributions
 bal-0.025
 Seth-0.025
 Tyler-0.024
cest-0.024
 laund-0.024
Token like
Token ID588
Feature activation-1.39e-01

Pos logit contributions
 bal+0.006
 Seth+0.006
 Tyler+0.006
ird+0.006
uka+0.006
Neg logit contributions
rog-0.008
acle-0.008
arium-0.008
 Buzz-0.007
Buzz-0.007
Token your
Token ID534
Feature activation-8.79e-02

Pos logit contributions
 bal+0.231
 Seth+0.224
 Tyler+0.223
ird+0.220
uka+0.218
Neg logit contributions
rog-0.193
acle-0.185
arium-0.183
 Buzz-0.177
Buzz-0.175
Token hive
Token ID35881
Feature activation+2.32e-01

Pos logit contributions
 bal+0.128
 Seth+0.121
 Tyler+0.120
isc+0.117
ird+0.116
Neg logit contributions
rog-0.141
acle-0.137
arium-0.135
Buzz-0.132
atively-0.129
Token."
Token ID526
Feature activation-5.00e-02

Pos logit contributions
rog+0.340
acle+0.329
arium+0.328
 Buzz+0.317
Buzz+0.308
Neg logit contributions
 Seth-0.367
 bal-0.365
 Tyler-0.364
uka-0.353
isc-0.350
Token Buzz
Token ID15753
Feature activation+3.86e-01

Pos logit contributions
 bal+0.072
 Seth+0.071
 Tyler+0.070
 Sel+0.067
ird+0.067
Neg logit contributions
rog-0.081
acle-0.079
arium-0.077
Buzz-0.074
atively-0.073
Tokeny
Token ID88
Feature activation+1.36e-01

Pos logit contributions
rog+0.673
acle+0.671
arium+0.631
alk+0.605
agged+0.597
Neg logit contributions
 bal-0.503
ird-0.439
 Sel-0.435
 Seth-0.434
cest-0.426
Token smiled
Token ID13541
Feature activation+1.54e-01

Pos logit contributions
rog+0.224
acle+0.212
arium+0.209
agged+0.199
alk+0.199
Neg logit contributions
 bal-0.195
 Seth-0.176
 Tyler-0.174
 Sel-0.172
ird-0.169
Token and
Token ID290
Feature activation+1.39e-02

Pos logit contributions
rog+0.210
acle+0.206
arium+0.200
 Buzz+0.196
Buzz+0.192
Neg logit contributions
 bal-0.255
 Seth-0.253
 Tyler-0.252
ird-0.251
uka-0.249
Token said
Token ID531
Feature activation+3.02e-03

Pos logit contributions
rog+0.018
 Buzz+0.018
acle+0.017
arium+0.017
Buzz+0.017
Neg logit contributions
 bal-0.024
ird-0.024
 Seth-0.024
 laund-0.023
 Tyler-0.023
Token,
Token ID11
Feature activation-1.86e-03

Pos logit contributions
rog+0.005
acle+0.004
arium+0.004
Buzz+0.004
 Buzz+0.004
Neg logit contributions
 bal-0.005
 Seth-0.005
 Tyler-0.004
ird-0.004
uka-0.004
Token friends
Token ID2460
Feature activation+1.51e-02

Pos logit contributions
 bal+0.067
cest+0.058
isc+0.058
 Sel+0.058
 Seth+0.057
Neg logit contributions
rog-0.105
acle-0.102
arium-0.101
atively-0.095
Buzz-0.094
Token.
Token ID13
Feature activation+1.55e-02

Pos logit contributions
rog+0.025
acle+0.024
arium+0.024
Buzz+0.024
atively+0.023
Neg logit contributions
 bal-0.021
 Tyler-0.020
 Seth-0.020
ird-0.020
cest-0.019
Token One
Token ID1881
Feature activation+1.39e-01

Pos logit contributions
acle+0.024
rog+0.023
atively+0.023
isy+0.022
arium+0.022
Neg logit contributions
 Seth-0.022
 Tyler-0.021
 bal-0.021
 Sel-0.020
 Coc-0.020
Token day
Token ID1110
Feature activation+3.67e-02

Pos logit contributions
acle+0.311
atively+0.283
rus+0.273
agged+0.270
beard+0.269
Neg logit contributions
 bal-0.151
cest-0.121
 Su-0.120
 North-0.115
uka-0.113
Token,
Token ID11
Feature activation+9.59e-03

Pos logit contributions
acle+0.067
rog+0.066
arium+0.065
urious+0.061
isy+0.058
Neg logit contributions
 bal-0.048
 Seth-0.042
 Tyler-0.042
ird-0.041
 Sel-0.040
Token Buzz
Token ID15753
Feature activation+3.86e-01

Pos logit contributions
acle+0.017
agged+0.016
rog+0.016
arium+0.016
urious+0.016
Neg logit contributions
 bal-0.012
 Seth-0.012
 Coc-0.012
 Su-0.012
 Cam-0.012
Tokeny
Token ID88
Feature activation+1.29e-01

Pos logit contributions
acle+0.529
rog+0.519
atively+0.484
arium+0.459
 Buzz+0.442
Neg logit contributions
 bal-0.647
cest-0.646
 Seth-0.612
isc-0.602
uka-0.602
Token wanted
Token ID2227
Feature activation+3.91e-02

Pos logit contributions
rog+0.230
acle+0.220
Buzz+0.204
arium+0.203
atively+0.203
Neg logit contributions
 bal-0.167
 Seth-0.156
 Tyler-0.156
cest-0.150
isc-0.150
Token to
Token ID284
Feature activation+2.23e-02

Pos logit contributions
acle+0.070
rog+0.069
atively+0.065
arium+0.065
acky+0.063
Neg logit contributions
 bal-0.050
 Seth-0.047
 Tyler-0.047
 laund-0.046
uka-0.045
Token go
Token ID467
Feature activation-9.85e-02

Pos logit contributions
rog+0.034
acle+0.033
arium+0.033
Buzz+0.031
 Buzz+0.031
Neg logit contributions
 bal-0.034
 Seth-0.033
 Tyler-0.033
ird-0.032
uka-0.032
Token outside
Token ID2354
Feature activation+2.45e-02

Pos logit contributions
 bal+0.134
 Seth+0.126
 Tyler+0.124
uka+0.121
cest+0.120
Neg logit contributions
rog-0.168
acle-0.166
arium-0.160
Buzz-0.156
atively-0.156
Token't
Token ID470
Feature activation+1.47e-01

Pos logit contributions
rog+0.085
arium+0.082
 Buzz+0.079
Buzz+0.078
acle+0.078
Neg logit contributions
 Seth-0.076
 Tyler-0.076
 bal-0.076
isc-0.073
uka-0.073
Token mean
Token ID1612
Feature activation+8.52e-03

Pos logit contributions
rog+0.236
acle+0.230
arium+0.228
Buzz+0.216
atively+0.213
Neg logit contributions
 bal-0.219
 Seth-0.210
 Tyler-0.206
ird-0.206
cest-0.204
Token to
Token ID284
Feature activation+3.67e-02

Pos logit contributions
rog+0.011
acle+0.010
arium+0.010
 Buzz+0.010
Buzz+0.010
Neg logit contributions
 bal-0.015
ird-0.015
 Tyler-0.015
uka-0.015
 laund-0.014
Token,
Token ID11
Feature activation+9.53e-03

Pos logit contributions
arium+0.057
rog+0.056
acle+0.056
atively+0.052
Buzz+0.051
Neg logit contributions
 Seth-0.055
 bal-0.054
 Tyler-0.054
ird-0.051
 Sel-0.051
Token but
Token ID475
Feature activation-5.17e-02

Pos logit contributions
rog+0.013
acle+0.013
 Buzz+0.013
arium+0.013
Buzz+0.012
Neg logit contributions
 bal-0.016
uka-0.015
isc-0.015
ird-0.015
 Seth-0.015
Token Buzz
Token ID15753
Feature activation+3.84e-01

Pos logit contributions
 bal+0.077
 Seth+0.076
 Tyler+0.075
ird+0.072
 Sel+0.072
Neg logit contributions
rog-0.081
acle-0.079
arium-0.078
Buzz-0.074
atively-0.072
Token was
Token ID373
Feature activation-3.78e-03

Pos logit contributions
rog+0.601
acle+0.584
arium+0.572
atively+0.544
Buzz+0.543
Neg logit contributions
 bal-0.565
 Seth-0.540
 Tyler-0.538
cest-0.536
ird-0.527
Token too
Token ID1165
Feature activation+1.58e-01

Pos logit contributions
 bal+0.006
 Seth+0.005
 Tyler+0.005
uka+0.005
ird+0.005
Neg logit contributions
rog-0.006
arium-0.006
acle-0.006
atively-0.006
Buzz-0.005
Token small
Token ID1402
Feature activation+7.27e-02

Pos logit contributions
rog+0.255
acle+0.248
arium+0.246
atively+0.233
 Buzz+0.226
Neg logit contributions
 bal-0.234
 Seth-0.224
 Tyler-0.219
cest-0.217
uka-0.213
Token for
Token ID329
Feature activation+2.75e-04

Pos logit contributions
rog+0.116
acle+0.111
arium+0.109
Buzz+0.107
 Buzz+0.105
Neg logit contributions
 bal-0.108
 Tyler-0.104
 Seth-0.103
ird-0.101
cest-0.101
Token her
Token ID607
Feature activation-2.93e-02

Pos logit contributions
arium+0.000
acle+0.000
rog+0.000
urious+0.000
hog+0.000
Neg logit contributions
 Seth-0.000
 Tyler-0.000
 Super-0.000
 Sel-0.000
 Coc-0.000
Token little
Token ID1310
Feature activation+1.13e-01

Pos logit contributions
rog+0.092
acle+0.087
arium+0.087
Buzz+0.084
 Buzz+0.083
Neg logit contributions
 bal-0.149
 Seth-0.146
 Tyler-0.145
ird-0.143
isc-0.142
Token bee
Token ID20697
Feature activation+1.28e-01

Pos logit contributions
acle+0.172
rog+0.169
arium+0.164
atively+0.160
Buzz+0.152
Neg logit contributions
 bal-0.179
cest-0.166
 Seth-0.166
 Tyler-0.165
 pian-0.162
Token named
Token ID3706
Feature activation-9.05e-02

Pos logit contributions
rog+0.223
acle+0.214
arium+0.214
 Buzz+0.207
Buzz+0.207
Neg logit contributions
 bal-0.169
 Seth-0.165
 Tyler-0.164
ird-0.159
uka-0.159
Token Buzz
Token ID15753
Feature activation+3.81e-01

Pos logit contributions
 Su+0.155
 Sel+0.154
 Seth+0.153
 bal+0.152
uka+0.152
Neg logit contributions
acle-0.125
atively-0.115
arium-0.113
rog-0.110
agged-0.102
Token.
Token ID13
Feature activation+5.43e-03

Pos logit contributions
rog+0.486
acle+0.467
arium+0.458
 Buzz+0.437
Buzz+0.436
Neg logit contributions
 bal-0.677
 Seth-0.658
 Tyler-0.654
ird-0.644
uka-0.641
Token Buzz
Token ID15753
Feature activation+3.83e-01

Pos logit contributions
acle+0.005
erie+0.004
atively+0.004
arium+0.004
urious+0.004
Neg logit contributions
 bal-0.010
 Coc-0.010
 North-0.010
 Stri-0.010
 Sel-0.010
Token lived
Token ID5615
Feature activation+6.66e-02

Pos logit contributions
acle+0.611
rog+0.592
atively+0.567
arium+0.562
 Buzz+0.531
Neg logit contributions
 bal-0.572
cest-0.565
uka-0.519
 Seth-0.518
ird-0.515
Token in
Token ID287
Feature activation+1.00e-01

Pos logit contributions
rog+0.119
acle+0.118
atively+0.111
arium+0.111
beard+0.103
Neg logit contributions
 bal-0.085
uka-0.074
 Super-0.074
cest-0.072
 Es-0.071
Token a
Token ID257
Feature activation+7.26e-02

Pos logit contributions
acle+0.184
rog+0.182
atively+0.182
arium+0.171
ly+0.160
Neg logit contributions
 North-0.123
 bal-0.120
uka-0.118
 Super-0.117
 Seth-0.115
Token hive
Token ID35881
Feature activation+2.30e-01

Pos logit contributions
rog+0.120
acle+0.119
atively+0.113
arium+0.109
 Buzz+0.105
Neg logit contributions
 bal-0.102
 laund-0.095
uka-0.095
cest-0.095
 Seth-0.094
Token with
Token ID351
Feature activation+1.97e-02

Pos logit contributions
rog+0.423
acle+0.396
atively+0.394
Buzz+0.383
beard+0.370
Neg logit contributions
 bal-0.270
cest-0.264
ird-0.236
 North-0.228
 Es-0.219
Token hive
Token ID35881
Feature activation+2.30e-01

Pos logit contributions
rog+0.120
acle+0.119
atively+0.113
arium+0.109
 Buzz+0.105
Neg logit contributions
 bal-0.102
 laund-0.095
uka-0.095
cest-0.095
 Seth-0.094
Token with
Token ID351
Feature activation+1.97e-02

Pos logit contributions
rog+0.423
acle+0.396
atively+0.394
Buzz+0.383
beard+0.370
Neg logit contributions
 bal-0.270
cest-0.264
ird-0.236
 North-0.228
 Es-0.219
Token his
Token ID465
Feature activation-6.25e-02

Pos logit contributions
rog+0.037
acle+0.037
arium+0.036
atively+0.034
acky+0.032
Neg logit contributions
 bal-0.024
 North-0.022
 Seth-0.022
cest-0.021
 Sel-0.021
Token friends
Token ID2460
Feature activation+6.88e-03

Pos logit contributions
 bal+0.063
 North+0.055
cest+0.055
 Sel+0.054
isc+0.054
Neg logit contributions
acle-0.126
rog-0.125
arium-0.121
atively-0.119
beard-0.113
Token.
Token ID13
Feature activation+7.97e-03

Pos logit contributions
rog+0.012
acle+0.012
atively+0.012
Buzz+0.011
arium+0.011
Neg logit contributions
 bal-0.009
 Tyler-0.008
 Seth-0.008
ird-0.008
cest-0.008
Token Buzz
Token ID15753
Feature activation+3.83e-01

Pos logit contributions
isy+0.014
ly+0.014
acle+0.014
face+0.014
erie+0.013
Neg logit contributions
 Coc-0.008
 Whe-0.008
 Ther-0.007
 North-0.007
 Stri-0.007
Token liked
Token ID8288
Feature activation+5.24e-02

Pos logit contributions
acle+0.650
rog+0.635
atively+0.609
arium+0.584
 Buzz+0.561
Neg logit contributions
 bal-0.526
cest-0.522
 Tyler-0.473
ird-0.473
 Seth-0.472
Token to
Token ID284
Feature activation+2.25e-02

Pos logit contributions
acle+0.108
rog+0.102
atively+0.100
arium+0.096
acky+0.091
Neg logit contributions
 bal-0.057
 Coc-0.052
 North-0.052
 Seth-0.051
 Stri-0.051
Token fly
Token ID6129
Feature activation+1.08e-01

Pos logit contributions
acle+0.041
arium+0.040
beard+0.039
rus+0.039
atively+0.039
Neg logit contributions
 bal-0.025
 North-0.022
 Seth-0.021
 Es-0.021
ird-0.021
Token around
Token ID1088
Feature activation+3.63e-02

Pos logit contributions
rog+0.197
acle+0.193
atively+0.181
perate+0.179
arium+0.176
Neg logit contributions
 bal-0.115
cest-0.112
 Super-0.106
 Seth-0.097
 pian-0.097
Token and
Token ID290
Feature activation+1.91e-02

Pos logit contributions
acle+0.067
rog+0.064
atively+0.061
arium+0.059
isy+0.058
Neg logit contributions
 bal-0.040
 Super-0.039
cest-0.037
 Coc-0.037
 North-0.037
Token Andy
Token ID12382
Feature activation+1.36e-01

Pos logit contributions
rog+0.067
acle+0.064
arium+0.064
Buzz+0.062
 Buzz+0.060
Neg logit contributions
 bal-0.067
 Seth-0.065
 Tyler-0.064
ird-0.063
uka-0.062
Token.
Token ID13
Feature activation+8.80e-03

Pos logit contributions
rog+0.222
acle+0.215
arium+0.214
Buzz+0.208
 Buzz+0.203
Neg logit contributions
 bal-0.194
 Seth-0.190
 Tyler-0.189
ird-0.184
cest-0.180
Token
Token ID220
Feature activation+6.08e-02

Pos logit contributions
rog+0.012
acle+0.012
 Buzz+0.011
arium+0.011
Buzz+0.011
Neg logit contributions
 bal-0.015
uka-0.014
cest-0.014
ird-0.014
 Seth-0.014
Token
Token ID198
Feature activation-2.27e-02

Pos logit contributions
rog+0.093
acle+0.090
arium+0.089
 Buzz+0.086
Buzz+0.086
Neg logit contributions
 bal-0.092
 Seth-0.089
 Tyler-0.089
ird-0.087
uka-0.086
Token
Token ID198
Feature activation-2.57e-02

Pos logit contributions
 bal+0.032
 Seth+0.032
 Tyler+0.032
ird+0.031
uka+0.030
Neg logit contributions
rog-0.036
acle-0.036
arium-0.035
 Buzz-0.033
Buzz-0.033
TokenBuzz
Token ID48230
Feature activation+3.82e-01

Pos logit contributions
 bal+0.041
 Seth+0.040
 Tyler+0.040
ird+0.039
uka+0.039
Neg logit contributions
rog-0.038
acle-0.036
arium-0.035
Buzz-0.034
 Buzz-0.034
Token felt
Token ID2936
Feature activation+3.47e-02

Pos logit contributions
acle+0.653
rog+0.640
arium+0.624
atively+0.597
agged+0.576
Neg logit contributions
 bal-0.495
cest-0.456
 Tyler-0.455
 Seth-0.452
 Sel-0.433
Token sorry
Token ID7926
Feature activation+5.93e-02

Pos logit contributions
rog+0.051
acle+0.050
 Buzz+0.049
arium+0.048
Buzz+0.048
Neg logit contributions
 Seth-0.053
 bal-0.053
 Tyler-0.053
ird-0.053
isc-0.052
Token for
Token ID329
Feature activation+3.57e-03

Pos logit contributions
rog+0.096
arium+0.093
acle+0.093
Buzz+0.090
 Buzz+0.087
Neg logit contributions
 bal-0.089
 Tyler-0.083
 Seth-0.083
 Sel-0.080
cest-0.080
Token the
Token ID262
Feature activation-3.33e-02

Pos logit contributions
rog+0.005
arium+0.005
acle+0.005
Buzz+0.005
atively+0.005
Neg logit contributions
 Tyler-0.006
 Seth-0.006
 Sel-0.006
 bal-0.005
 Su-0.005
Token poor
Token ID3595
Feature activation+2.25e-02

Pos logit contributions
 bal+0.050
 roller+0.046
 Tyler+0.046
 Seth+0.046
 laund+0.045
Neg logit contributions
rog-0.053
arium-0.052
acle-0.052
atively-0.048
Buzz-0.048
Token the
Token ID262
Feature activation-7.87e-03

Pos logit contributions
rog+0.129
acle+0.125
arium+0.123
Buzz+0.117
atively+0.115
Neg logit contributions
 bal-0.137
 Seth-0.136
 Tyler-0.134
 Sel-0.130
ird-0.130
Token net
Token ID2010
Feature activation+1.56e-01

Pos logit contributions
 bal+0.012
 roller+0.011
 Seth+0.011
 laund+0.011
cest+0.011
Neg logit contributions
rog-0.012
arium-0.012
acle-0.011
atively-0.011
 Buzz-0.011
Token.
Token ID13
Feature activation-2.24e-03

Pos logit contributions
rog+0.251
acle+0.237
arium+0.236
Buzz+0.232
 Buzz+0.227
Neg logit contributions
 bal-0.225
 Seth-0.213
 Tyler-0.213
ird-0.211
cest-0.208
Token
Token ID198
Feature activation-1.80e-02

Pos logit contributions
 bal+0.004
 Coc+0.004
 Super+0.003
 Seth+0.003
 Sel+0.003
Neg logit contributions
acle-0.003
rog-0.003
arium-0.003
atively-0.003
erie-0.003
Token
Token ID198
Feature activation-1.89e-02

Pos logit contributions
uka+0.013
 Tyler+0.013
 Seth+0.013
 Stri+0.012
 Coc+0.012
Neg logit contributions
acle-0.041
atively-0.038
ly-0.037
rog-0.037
arium-0.037
TokenBuzz
Token ID48230
Feature activation+3.81e-01

Pos logit contributions
 bal+0.034
Cam+0.032
 Coc+0.031
 laund+0.031
Ron+0.030
Neg logit contributions
acle-0.024
work-0.021
arium-0.020
flies-0.020
atively-0.019
Token told
Token ID1297
Feature activation-5.78e-02

Pos logit contributions
rog+0.637
acle+0.631
arium+0.597
atively+0.588
 Buzz+0.562
Neg logit contributions
 bal-0.517
cest-0.506
 Tyler-0.478
 Seth-0.477
ird-0.474
Token the
Token ID262
Feature activation-7.06e-03

Pos logit contributions
 Seth+0.036
 Super+0.035
 Gl+0.034
 bal+0.033
 Roc+0.033
Neg logit contributions
ider-0.133
acle-0.131
urious-0.131
arium-0.127
rog-0.122
Token bird
Token ID6512
Feature activation+7.94e-02

Pos logit contributions
 bal+0.009
 North+0.008
 Seth+0.007
cest+0.007
 roller+0.007
Neg logit contributions
acle-0.013
rog-0.013
arium-0.013
atively-0.013
agged-0.012
Token,
Token ID11
Feature activation-3.72e-03

Pos logit contributions
acle+0.168
atively+0.153
agged+0.151
rog+0.149
arium+0.147
Neg logit contributions
 bal-0.083
cest-0.076
 Seth-0.074
 Su-0.071
 Cam-0.068
Token "
Token ID366
Feature activation-6.08e-02

Pos logit contributions
 bal+0.004
 Seth+0.004
 Tyler+0.004
 Sel+0.004
 Es+0.003
Neg logit contributions
rog-0.008
arium-0.007
acle-0.007
Buzz-0.007
atively-0.007
Token was
Token ID373
Feature activation-3.35e-03

Pos logit contributions
rog+0.120
 Buzz+0.116
arium+0.115
acle+0.110
Buzz+0.109
Neg logit contributions
 bal-0.225
 pian-0.221
 laund-0.219
 Seth-0.217
ird-0.217
Token a
Token ID257
Feature activation+7.92e-02

Pos logit contributions
 bal+0.005
 Tyler+0.004
uka+0.004
 roller+0.004
 Seth+0.004
Neg logit contributions
rog-0.006
acle-0.006
atively-0.006
arium-0.006
flies-0.005
Token little
Token ID1310
Feature activation+1.13e-01

Pos logit contributions
rog+0.092
acle+0.087
arium+0.087
Buzz+0.084
 Buzz+0.083
Neg logit contributions
 bal-0.149
 Seth-0.146
 Tyler-0.145
ird-0.143
isc-0.142
Token bee
Token ID20697
Feature activation+1.28e-01

Pos logit contributions
acle+0.172
rog+0.169
arium+0.164
atively+0.160
Buzz+0.152
Neg logit contributions
 bal-0.179
cest-0.166
 Seth-0.166
 Tyler-0.165
 pian-0.162
Token named
Token ID3706
Feature activation-9.05e-02

Pos logit contributions
rog+0.223
acle+0.214
arium+0.214
 Buzz+0.207
Buzz+0.207
Neg logit contributions
 bal-0.169
 Seth-0.165
 Tyler-0.164
ird-0.159
uka-0.159
Token Buzz
Token ID15753
Feature activation+3.81e-01

Pos logit contributions
 Su+0.155
 Sel+0.154
 Seth+0.153
 bal+0.152
uka+0.152
Neg logit contributions
acle-0.125
atively-0.115
arium-0.113
rog-0.110
agged-0.102
Token.
Token ID13
Feature activation+5.43e-03

Pos logit contributions
rog+0.486
acle+0.467
arium+0.458
 Buzz+0.437
Buzz+0.436
Neg logit contributions
 bal-0.677
 Seth-0.658
 Tyler-0.654
ird-0.644
uka-0.641
Token Buzz
Token ID15753
Feature activation+3.83e-01

Pos logit contributions
acle+0.005
erie+0.004
atively+0.004
arium+0.004
urious+0.004
Neg logit contributions
 bal-0.010
 Coc-0.010
 North-0.010
 Stri-0.010
 Sel-0.010
Token lived
Token ID5615
Feature activation+6.66e-02

Pos logit contributions
acle+0.611
rog+0.592
atively+0.567
arium+0.562
 Buzz+0.531
Neg logit contributions
 bal-0.572
cest-0.565
uka-0.519
 Seth-0.518
ird-0.515
Token in
Token ID287
Feature activation+1.00e-01

Pos logit contributions
rog+0.119
acle+0.118
atively+0.111
arium+0.111
beard+0.103
Neg logit contributions
 bal-0.085
uka-0.074
 Super-0.074
cest-0.072
 Es-0.071
Token a
Token ID257
Feature activation+7.26e-02

Pos logit contributions
acle+0.184
rog+0.182
atively+0.182
arium+0.171
ly+0.160
Neg logit contributions
 North-0.123
 bal-0.120
uka-0.118
 Super-0.117
 Seth-0.115
Token Lily
Token ID20037
Feature activation+1.58e-02

Pos logit contributions
acle+0.006
arium+0.005
rus+0.005
beard+0.005
 nowhere+0.005
Neg logit contributions
 bal-0.004
 Coc-0.004
 Sel-0.004
 Super-0.004
 Whe-0.004
Token loved
Token ID6151
Feature activation+3.18e-03

Pos logit contributions
rog+0.023
acle+0.022
arium+0.021
 Buzz+0.021
Buzz+0.021
Neg logit contributions
 bal-0.026
 Seth-0.025
 Tyler-0.025
ird-0.024
uka-0.024
Token Buzz
Token ID15753
Feature activation+3.80e-01

Pos logit contributions
rog+0.005
acle+0.005
arium+0.005
atively+0.005
Buzz+0.005
Neg logit contributions
 bal-0.005
 Seth-0.005
 Tyler-0.005
 Sel-0.004
uka-0.004
Token,
Token ID11
Feature activation+1.76e-03

Pos logit contributions
acle+0.706
rog+0.693
atively+0.665
arium+0.655
Buzz+0.636
Neg logit contributions
 bal-0.482
cest-0.444
ird-0.421
 Coc-0.406
 Tyler-0.400
Token and
Token ID290
Feature activation+1.42e-02

Pos logit contributions
rog+0.003
acle+0.003
arium+0.003
Buzz+0.003
 Buzz+0.003
Neg logit contributions
 bal-0.002
 Seth-0.002
 Tyler-0.002
ird-0.002
cest-0.002
Token Buzz
Token ID15753
Feature activation+3.80e-01

Pos logit contributions
acle+0.026
rog+0.026
arium+0.024
agged+0.023
atively+0.023
Neg logit contributions
 bal-0.018
 Seth-0.017
 Tyler-0.017
 Sel-0.016
 Coc-0.016
Token loved
Token ID6151
Feature activation+3.82e-03

Pos logit contributions
rog+0.530
arium+0.509
acle+0.504
 Buzz+0.491
Buzz+0.489
Neg logit contributions
 bal-0.631
 Seth-0.622
 Tyler-0.617
ird-0.602
uka-0.602
Token Lily
Token ID20037
Feature activation+1.70e-02

Pos logit contributions
rog+0.006
acle+0.006
arium+0.006
atively+0.005
Buzz+0.005
Neg logit contributions
 bal-0.006
 Seth-0.005
 Tyler-0.005
 Sel-0.005
uka-0.005
Token.
Token ID13
Feature activation+3.59e-03

Pos logit contributions
rog+0.031
acle+0.031
arium+0.030
atively+0.029
Buzz+0.029
Neg logit contributions
 bal-0.022
ird-0.020
cest-0.019
 Tyler-0.019
 Seth-0.019
Token
Token ID198
Feature activation-1.06e-02

Pos logit contributions
acle+0.007
rus+0.006
 nowhere+0.006
rog+0.006
arium+0.006
Neg logit contributions
 bal-0.004
 Coc-0.004
isc-0.004
 Sel-0.004
 Ther-0.003
Token
Token ID198
Feature activation-1.09e-02

Pos logit contributions
uka+0.011
 Tyler+0.011
 bal+0.011
 Seth+0.010
 Sel+0.010
Neg logit contributions
acle-0.021
rog-0.020
arium-0.019
atively-0.019
flies-0.019
Token throwing
Token ID9644
Feature activation-5.57e-02

Pos logit contributions
rog+0.035
acle+0.034
arium+0.033
Buzz+0.032
 Buzz+0.032
Neg logit contributions
 bal-0.028
 Seth-0.027
 Tyler-0.027
ird-0.026
uka-0.026
Token.
Token ID13
Feature activation+1.24e-02

Pos logit contributions
 bal+0.095
 Tyler+0.095
ird+0.094
 Seth+0.094
uka+0.093
Neg logit contributions
rog-0.075
acle-0.070
 Buzz-0.069
arium-0.068
Buzz-0.068
Token
Token ID198
Feature activation-5.43e-03

Pos logit contributions
rog+0.018
acle+0.017
arium+0.017
Buzz+0.016
 Buzz+0.016
Neg logit contributions
 bal-0.020
 Seth-0.020
 Tyler-0.020
ird-0.019
uka-0.019
Token
Token ID198
Feature activation-5.41e-03

Pos logit contributions
 bal+0.008
 Seth+0.008
 Tyler+0.008
ird+0.008
uka+0.008
Neg logit contributions
rog-0.009
acle-0.008
arium-0.008
 Buzz-0.008
Buzz-0.008
Token"
Token ID1
Feature activation+1.72e-02

Pos logit contributions
 bal+0.007
 Seth+0.007
 Tyler+0.007
ird+0.007
 laund+0.007
Neg logit contributions
rog-0.009
acle-0.009
arium-0.009
 Buzz-0.008
atively-0.008
TokenBuzz
Token ID48230
Feature activation+3.80e-01

Pos logit contributions
rog+0.027
Buzz+0.026
acle+0.025
 Buzz+0.025
arium+0.025
Neg logit contributions
 bal-0.025
 Tyler-0.025
 Seth-0.025
isc-0.025
ird-0.024
Token!
Token ID0
Feature activation-9.51e-02

Pos logit contributions
rog+0.632
acle+0.619
arium+0.614
Buzz+0.585
atively+0.579
Neg logit contributions
 bal-0.530
 Seth-0.507
cest-0.503
 Tyler-0.502
ird-0.494
Token Buzz
Token ID15753
Feature activation+3.77e-01

Pos logit contributions
 bal+0.147
 Seth+0.142
 Tyler+0.142
 laund+0.142
ird+0.141
Neg logit contributions
rog-0.143
acle-0.136
 Buzz-0.135
arium-0.132
Buzz-0.131
Token!"
Token ID2474
Feature activation-4.34e-02

Pos logit contributions
rog+0.677
acle+0.659
arium+0.652
Buzz+0.622
atively+0.622
Neg logit contributions
 bal-0.485
cest-0.459
 Seth-0.454
 Tyler-0.454
ird-0.446
Token a
Token ID257
Feature activation+6.83e-02

Pos logit contributions
 Seth+0.056
 Tyler+0.055
 bal+0.053
 Su+0.051
 Sel+0.051
Neg logit contributions
rog-0.079
acle-0.077
arium-0.076
atively-0.070
Buzz-0.069
Token bee
Token ID20697
Feature activation+1.34e-01

Pos logit contributions
rog+0.069
acle+0.069
arium+0.069
 Buzz+0.060
atively+0.059
Neg logit contributions
 bal-0.137
 Seth-0.135
 Tyler-0.133
cest-0.131
 Sel-0.130
Token his
Token ID465
Feature activation-7.15e-02

Pos logit contributions
 bal+0.046
ird+0.046
 Seth+0.046
 laund+0.045
 Tyler+0.045
Neg logit contributions
acle-0.036
rog-0.035
arium-0.034
 Buzz-0.034
atively-0.033
Token name
Token ID1438
Feature activation-2.86e-02

Pos logit contributions
 bal+0.111
 Seth+0.103
 Tyler+0.102
isc+0.101
ird+0.101
Neg logit contributions
rog-0.110
acle-0.106
arium-0.105
Buzz-0.103
 Buzz-0.101
Token.
Token ID13
Feature activation-2.14e-03

Pos logit contributions
 Seth+0.048
 laund+0.048
uka+0.048
 Tyler+0.047
isc+0.047
Neg logit contributions
acle-0.038
rog-0.037
 Buzz-0.036
arium-0.036
atively-0.034
Token Now
Token ID2735
Feature activation-3.78e-02

Pos logit contributions
 bal+0.003
 Coc+0.002
 Sel+0.002
isc+0.002
 Whe+0.002
Neg logit contributions
acle-0.004
rog-0.004
arium-0.004
 nowhere-0.004
erie-0.004
Token,
Token ID11
Feature activation-3.52e-03

Pos logit contributions
 bal+0.050
 Seth+0.046
cest+0.045
 Tyler+0.045
 Sel+0.044
Neg logit contributions
rog-0.067
acle-0.067
arium-0.064
Buzz-0.060
atively-0.059
Token Buzz
Token ID15753
Feature activation+3.80e-01

Pos logit contributions
 bal+0.004
 Sel+0.003
 Super+0.003
cest+0.003
 Coc+0.003
Neg logit contributions
acle-0.007
rog-0.007
agged-0.007
arium-0.006
urious-0.006
Token was
Token ID373
Feature activation-6.06e-03

Pos logit contributions
rog+0.524
arium+0.515
acle+0.507
 Buzz+0.492
Buzz+0.488
Neg logit contributions
 Seth-0.625
 bal-0.619
 Tyler-0.614
ird-0.600
 laund-0.599
Token happy
Token ID3772
Feature activation+4.72e-02

Pos logit contributions
isc+0.012
 Seth+0.011
 Tyler+0.011
 laund+0.011
 Coc+0.011
Neg logit contributions
 Buzz-0.007
acle-0.007
arium-0.007
 nowhere-0.006
 Marie-0.006
Token because
Token ID780
Feature activation-5.30e-02

Pos logit contributions
rog+0.069
acle+0.066
arium+0.065
Buzz+0.063
 Buzz+0.062
Neg logit contributions
 bal-0.077
 Seth-0.074
 Tyler-0.074
cest-0.072
uka-0.071
Token he
Token ID339
Feature activation-1.39e-02

Pos logit contributions
 bal+0.078
 Seth+0.076
 Tyler+0.076
ird+0.074
uka+0.073
Neg logit contributions
rog-0.084
acle-0.081
arium-0.080
 Buzz-0.078
Buzz-0.077
Token could
Token ID714
Feature activation-9.10e-02

Pos logit contributions
 Seth+0.024
 bal+0.023
 Tyler+0.023
 laund+0.023
isc+0.022
Neg logit contributions
rog-0.019
arium-0.018
acle-0.018
 Buzz-0.018
Buzz-0.017
Token anymore
Token ID7471
Feature activation+1.02e-01

Pos logit contributions
 Seth+0.013
 bal+0.013
 Tyler+0.013
uka+0.013
ird+0.013
Neg logit contributions
rog-0.008
arium-0.008
acle-0.008
 Buzz-0.008
Buzz-0.007
Token.
Token ID13
Feature activation+8.36e-03

Pos logit contributions
rog+0.142
arium+0.136
acle+0.135
 Buzz+0.133
Buzz+0.126
Neg logit contributions
 Seth-0.169
 bal-0.168
uka-0.165
 Tyler-0.165
 laund-0.164
Token After
Token ID2293
Feature activation+2.72e-02

Pos logit contributions
acle+0.014
rog+0.014
arium+0.013
atively+0.013
isy+0.012
Neg logit contributions
 bal-0.011
 Sel-0.011
 Tyler-0.011
 Coc-0.011
 Seth-0.011
Token playing
Token ID2712
Feature activation-1.87e-02

Pos logit contributions
rog+0.046
acle+0.045
arium+0.042
atively+0.042
Buzz+0.041
Neg logit contributions
 bal-0.039
 Tyler-0.038
 Seth-0.037
uka-0.036
 Sel-0.036
Token,
Token ID11
Feature activation+3.05e-03

Pos logit contributions
 bal+0.026
 Tyler+0.024
 Seth+0.024
ird+0.024
 laund+0.023
Neg logit contributions
rog-0.030
acle-0.030
arium-0.029
Buzz-0.028
atively-0.027
Token Buzz
Token ID15753
Feature activation+3.80e-01

Pos logit contributions
acle+0.004
rog+0.004
agged+0.004
arium+0.004
atively+0.004
Neg logit contributions
 bal-0.005
 Super-0.005
 Coc-0.005
 Sel-0.005
 Stri-0.005
Tokeny
Token ID88
Feature activation+1.34e-01

Pos logit contributions
rog+0.498
acle+0.490
arium+0.453
atively+0.448
 Buzz+0.428
Neg logit contributions
 bal-0.667
cest-0.646
 Seth-0.631
 Tyler-0.628
ird-0.617
Token went
Token ID1816
Feature activation-7.18e-02

Pos logit contributions
rog+0.203
acle+0.195
arium+0.192
 Buzz+0.185
Buzz+0.185
Neg logit contributions
 bal-0.206
 Seth-0.199
 Tyler-0.198
ird-0.194
uka-0.193
Token back
Token ID736
Feature activation+1.75e-02

Pos logit contributions
 bal+0.096
 Seth+0.090
 Tyler+0.090
 laund+0.087
uka+0.086
Neg logit contributions
rog-0.126
acle-0.117
Buzz-0.115
arium-0.113
atively-0.111
Token to
Token ID284
Feature activation+2.17e-02

Pos logit contributions
rog+0.028
acle+0.027
Buzz+0.026
arium+0.025
atively+0.025
Neg logit contributions
 bal-0.025
 Tyler-0.024
 Seth-0.024
uka-0.023
 laund-0.023
Token the
Token ID262
Feature activation-4.11e-03

Pos logit contributions
rog+0.034
acle+0.033
arium+0.032
Buzz+0.031
 Buzz+0.031
Neg logit contributions
 bal-0.033
 Seth-0.032
 Tyler-0.031
ird-0.031
uka-0.031
Token she
Token ID673
Feature activation-1.90e-02

Pos logit contributions
rog+0.121
acle+0.120
arium+0.115
atively+0.107
Buzz+0.106
Neg logit contributions
 bal-0.086
 Seth-0.081
 Tyler-0.080
uka-0.077
 Sel-0.077
Token played
Token ID2826
Feature activation+1.32e-02

Pos logit contributions
 bal+0.030
 Seth+0.028
 Tyler+0.028
ird+0.028
uka+0.027
Neg logit contributions
rog-0.029
acle-0.028
arium-0.027
Buzz-0.026
 Buzz-0.026
Token.
Token ID13
Feature activation+3.26e-03

Pos logit contributions
rog+0.022
acle+0.021
arium+0.021
Buzz+0.020
atively+0.020
Neg logit contributions
 bal-0.018
 Seth-0.017
 Tyler-0.017
cest-0.017
ird-0.016
Token Lily
Token ID20037
Feature activation+1.58e-02

Pos logit contributions
acle+0.006
arium+0.005
rus+0.005
beard+0.005
 nowhere+0.005
Neg logit contributions
 bal-0.004
 Coc-0.004
 Sel-0.004
 Super-0.004
 Whe-0.004
Token loved
Token ID6151
Feature activation+3.18e-03

Pos logit contributions
rog+0.023
acle+0.022
arium+0.021
 Buzz+0.021
Buzz+0.021
Neg logit contributions
 bal-0.026
 Seth-0.025
 Tyler-0.025
ird-0.024
uka-0.024
Token Buzz
Token ID15753
Feature activation+3.80e-01

Pos logit contributions
rog+0.005
acle+0.005
arium+0.005
atively+0.005
Buzz+0.005
Neg logit contributions
 bal-0.005
 Seth-0.005
 Tyler-0.005
 Sel-0.004
uka-0.004
Token,
Token ID11
Feature activation+1.76e-03

Pos logit contributions
acle+0.706
rog+0.693
atively+0.665
arium+0.655
Buzz+0.636
Neg logit contributions
 bal-0.482
cest-0.444
ird-0.421
 Coc-0.406
 Tyler-0.400
Token and
Token ID290
Feature activation+1.42e-02

Pos logit contributions
rog+0.003
acle+0.003
arium+0.003
Buzz+0.003
 Buzz+0.003
Neg logit contributions
 bal-0.002
 Seth-0.002
 Tyler-0.002
ird-0.002
cest-0.002
Token Buzz
Token ID15753
Feature activation+3.80e-01

Pos logit contributions
acle+0.026
rog+0.026
arium+0.024
agged+0.023
atively+0.023
Neg logit contributions
 bal-0.018
 Seth-0.017
 Tyler-0.017
 Sel-0.016
 Coc-0.016
Token loved
Token ID6151
Feature activation+3.82e-03

Pos logit contributions
rog+0.530
arium+0.509
acle+0.504
 Buzz+0.491
Buzz+0.489
Neg logit contributions
 bal-0.631
 Seth-0.622
 Tyler-0.617
ird-0.602
uka-0.602
Token Lily
Token ID20037
Feature activation+1.70e-02

Pos logit contributions
rog+0.006
acle+0.006
arium+0.006
atively+0.005
Buzz+0.005
Neg logit contributions
 bal-0.006
 Seth-0.005
 Tyler-0.005
 Sel-0.005
uka-0.005
Token bee
Token ID20697
Feature activation+1.31e-01

Pos logit contributions
rog+0.142
acle+0.139
arium+0.135
 Buzz+0.128
Buzz+0.128
Neg logit contributions
 bal-0.162
 Seth-0.154
 Tyler-0.153
ird-0.151
cest-0.150
Token named
Token ID3706
Feature activation-7.53e-02

Pos logit contributions
acle+0.251
rog+0.251
atively+0.238
arium+0.236
Buzz+0.228
Neg logit contributions
 bal-0.149
cest-0.139
ird-0.134
 Seth-0.133
 Tyler-0.130
Token Buzz
Token ID15753
Feature activation+3.80e-01

Pos logit contributions
 Su+0.126
 Seth+0.122
 Sel+0.122
 Coc+0.122
 bal+0.120
Neg logit contributions
acle-0.108
atively-0.102
arium-0.098
rog-0.096
beard-0.094
Tokeny
Token ID88
Feature activation+1.31e-01

Pos logit contributions
acle+0.612
rog+0.612
arium+0.580
atively+0.567
Buzz+0.558
Neg logit contributions
 bal-0.544
cest-0.522
 Seth-0.514
 Tyler-0.506
ird-0.505
Token.
Token ID13
Feature activation+8.81e-03

Pos logit contributions
acle+0.235
rog+0.230
arium+0.224
atively+0.221
Buzz+0.215
Neg logit contributions
 bal-0.160
cest-0.150
 Seth-0.150
 Sel-0.146
 Tyler-0.145
Token Buzz
Token ID15753
Feature activation+3.80e-01

Pos logit contributions
acle+0.009
erie+0.009
arium+0.008
atively+0.008
work+0.008
Neg logit contributions
 Coc-0.016
 bal-0.015
 Whe-0.015
 Ther-0.015
 Stri-0.015
Tokeny
Token ID88
Feature activation+1.32e-01

Pos logit contributions
acle+0.548
atively+0.510
rog+0.502
arium+0.466
 Buzz+0.439
Neg logit contributions
cest-0.643
 bal-0.634
uka-0.583
isc-0.576
 Seth-0.575
Token loved
Token ID6151
Feature activation+5.28e-03

Pos logit contributions
acle+0.229
rog+0.223
atively+0.214
arium+0.212
Buzz+0.199
Neg logit contributions
 bal-0.175
cest-0.159
 Sel-0.157
 Tyler-0.155
 Seth-0.154
Token to
Token ID284
Feature activation+2.42e-02

Pos logit contributions
rog+0.008
acle+0.008
arium+0.008
atively+0.008
Buzz+0.007
Neg logit contributions
 bal-0.008
 Seth-0.008
 Tyler-0.008
uka-0.007
 laund-0.007
Token rush
Token ID10484
Feature activation-5.06e-02

Pos logit contributions
acle+0.037
rog+0.037
arium+0.036
atively+0.034
Buzz+0.032
Neg logit contributions
 bal-0.037
 Seth-0.034
ird-0.033
 roller-0.033
 laund-0.033
Token from
Token ID422
Feature activation-1.27e-01

Pos logit contributions
 bal+0.080
 Seth+0.075
 Tyler+0.075
cest+0.072
 Sel+0.072
Neg logit contributions
rog-0.077
acle-0.075
arium-0.074
Buzz-0.070
 Buzz-0.069
Token ribbon
Token ID29092
Feature activation-4.01e-02

Pos logit contributions
 bal+0.084
 Tyler+0.079
 Seth+0.079
ird+0.077
 laund+0.076
Neg logit contributions
rog-0.092
acle-0.089
arium-0.088
Buzz-0.086
 Buzz-0.085
Token for
Token ID329
Feature activation-7.89e-03

Pos logit contributions
 bal+0.064
 Seth+0.061
 Tyler+0.061
ird+0.060
uka+0.059
Neg logit contributions
rog-0.060
acle-0.057
arium-0.057
Buzz-0.054
 Buzz-0.054
Token being
Token ID852
Feature activation+5.68e-02

Pos logit contributions
 bal+0.011
 Tyler+0.011
 Seth+0.011
uka+0.011
 Sel+0.011
Neg logit contributions
rog-0.013
arium-0.012
acle-0.012
Buzz-0.012
 Buzz-0.011
Token the
Token ID262
Feature activation-2.32e-02

Pos logit contributions
rog+0.068
 Buzz+0.068
acle+0.066
arium+0.063
Buzz+0.062
Neg logit contributions
isc-0.101
 bal-0.099
 laund-0.098
 Seth-0.097
uka-0.096
Token best
Token ID1266
Feature activation-2.16e-01

Pos logit contributions
 Seth+0.032
 Tyler+0.031
 bal+0.031
uka+0.031
isc+0.031
Neg logit contributions
rog-0.038
acle-0.036
 Buzz-0.035
arium-0.035
Buzz-0.034
Token bal
Token ID3652
Feature activation-4.34e-01

Pos logit contributions
uka+0.380
 Seth+0.376
isc+0.364
 laund+0.363
 Tyler+0.362
Neg logit contributions
rog-0.265
acle-0.245
arium-0.238
 True-0.230
 Buzz-0.229
Tokenancer
Token ID8250
Feature activation-7.39e-02

Pos logit contributions
ird+0.519
 bal+0.518
uka+0.501
 Tyler+0.487
 Seth+0.471
Neg logit contributions
rog-0.820
acle-0.815
arium-0.793
 Buzz-0.776
Buzz-0.771
Token in
Token ID287
Feature activation+7.69e-02

Pos logit contributions
 bal+0.113
 Seth+0.109
 Tyler+0.109
ird+0.107
uka+0.106
Neg logit contributions
rog-0.112
acle-0.108
arium-0.107
Buzz-0.103
 Buzz-0.103
Token the
Token ID262
Feature activation-2.45e-02

Pos logit contributions
rog+0.098
 Buzz+0.094
arium+0.094
acle+0.092
Buzz+0.087
Neg logit contributions
 bal-0.139
isc-0.136
ird-0.132
 laund-0.132
 Seth-0.130
Token competition
Token ID5449
Feature activation+5.45e-02

Pos logit contributions
 bal+0.041
 Seth+0.041
isc+0.040
 Tyler+0.039
uka+0.039
Neg logit contributions
rog-0.033
arium-0.032
acle-0.032
Buzz-0.030
 Buzz-0.030
Token.
Token ID13
Feature activation-2.30e-02

Pos logit contributions
rog+0.070
arium+0.069
acle+0.069
 Buzz+0.064
atively+0.062
Neg logit contributions
uka-0.093
 Seth-0.092
 bal-0.092
 laund-0.091
isc-0.091
Token made
Token ID925
Feature activation-1.33e-01

Pos logit contributions
 bal+0.138
ird+0.137
uka+0.136
 Seth+0.135
 Tyler+0.135
Neg logit contributions
acle-0.120
rog-0.119
arium-0.115
 Buzz-0.113
atively-0.111
Token him
Token ID683
Feature activation+3.47e-02

Pos logit contributions
ird+0.235
 bal+0.230
cest+0.228
uka+0.215
 laund+0.214
Neg logit contributions
acle-0.156
rog-0.152
atively-0.148
 Buzz-0.143
arium-0.137
Token squ
Token ID2809
Feature activation-1.10e-02

Pos logit contributions
rog+0.054
arium+0.052
acle+0.051
Buzz+0.049
 Buzz+0.048
Neg logit contributions
 bal-0.055
 Seth-0.051
cest-0.050
 Tyler-0.050
 Sel-0.049
Tokenint
Token ID600
Feature activation+7.98e-02

Pos logit contributions
 bal+0.017
 Seth+0.016
 Tyler+0.016
ird+0.016
cest+0.015
Neg logit contributions
rog-0.017
acle-0.017
arium-0.017
 Buzz-0.016
Buzz-0.016
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
rog+0.119
acle+0.115
arium+0.113
 Buzz+0.109
Buzz+0.109
Neg logit contributions
 bal-0.124
 Seth-0.120
 Tyler-0.120
ird-0.118
uka-0.117
Token Tyler
Token ID14886
Feature activation-4.32e-01

Pos logit contributions
cest+0.024
 bal+0.021
ird+0.021
 hairst+0.020
 pian+0.020
Neg logit contributions
acle-0.007
 True-0.007
<-0.006
rog-0.006
 upon-0.006
Token raced
Token ID32897
Feature activation-1.35e-01

Pos logit contributions
 bal+0.733
 Seth+0.714
 Tyler+0.708
ird+0.699
uka+0.697
Neg logit contributions
rog-0.581
acle-0.557
arium-0.548
 Buzz-0.529
Buzz-0.526
Token ahead
Token ID4058
Feature activation-8.00e-03

Pos logit contributions
ird+0.248
uka+0.237
 bal+0.237
cest+0.236
isc+0.235
Neg logit contributions
rog-0.167
acle-0.159
 Buzz-0.153
atively-0.148
arium-0.148
Token of
Token ID286
Feature activation-8.45e-02

Pos logit contributions
isc+0.015
ird+0.014
uka+0.014
 bal+0.014
cest+0.014
Neg logit contributions
rog-0.009
acle-0.009
 Buzz-0.009
arium-0.008
atively-0.008
Token his
Token ID465
Feature activation-9.15e-02

Pos logit contributions
 bal+0.168
ird+0.167
isc+0.163
cest+0.159
uka+0.151
Neg logit contributions
rog-0.090
acle-0.084
 Buzz-0.083
arium-0.079
 True-0.075
Token mom
Token ID1995
Feature activation-7.50e-02

Pos logit contributions
 bal+0.139
 Seth+0.136
 Tyler+0.134
ird+0.133
uka+0.133
Neg logit contributions
rog-0.140
acle-0.136
arium-0.133
 Buzz-0.128
Buzz-0.127
Token as
Token ID355
Feature activation+9.09e-02

Pos logit contributions
cest+0.109
 pian+0.105
 laund+0.105
ird+0.105
 bal+0.104
Neg logit contributions
acle-0.076
rog-0.075
 Buzz-0.070
arium-0.070
atively-0.069
Token he
Token ID339
Feature activation-2.85e-02

Pos logit contributions
 first+0.073
 next+0.061
 upon+0.059
 moment+0.056
 nowhere+0.055
Neg logit contributions
opl-0.186
 laund-0.185
 hairst-0.183
 paramed-0.182
ird-0.178
Token got
Token ID1392
Feature activation-3.46e-02

Pos logit contributions
isc+0.051
cest+0.051
 bal+0.051
 laund+0.050
uka+0.050
Neg logit contributions
rog-0.033
acle-0.031
arium-0.030
Buzz-0.030
atively-0.030
Token closer
Token ID5699
Feature activation+1.33e-01

Pos logit contributions
 bal+0.067
 Seth+0.065
 Tyler+0.065
uka+0.063
ird+0.063
Neg logit contributions
rog-0.040
acle-0.038
arium-0.038
Buzz-0.035
 Buzz-0.035
Token,
Token ID11
Feature activation-1.74e-02

Pos logit contributions
rog+0.198
acle+0.191
arium+0.188
 Buzz+0.181
Buzz+0.181
Neg logit contributions
 bal-0.209
 Seth-0.203
 Tyler-0.202
ird-0.198
uka-0.197
Token Tyler
Token ID14886
Feature activation-4.32e-01

Pos logit contributions
cest+0.035
ird+0.034
opl+0.033
isc+0.032
 bal+0.032
Neg logit contributions
 nowhere-0.015
acle-0.014
atively-0.014
 True-0.014
arium-0.013
Token felt
Token ID2936
Feature activation+2.05e-02

Pos logit contributions
 bal+0.726
cest+0.714
uka+0.713
 laund+0.708
isc+0.697
Neg logit contributions
acle-0.554
rog-0.541
atively-0.511
arium-0.509
 Buzz-0.506
Token his
Token ID465
Feature activation-8.51e-02

Pos logit contributions
rog+0.023
acle+0.023
 Buzz+0.023
Buzz+0.021
arium+0.021
Neg logit contributions
ird-0.038
isc-0.038
 Tyler-0.037
 Seth-0.037
 laund-0.037
Token heart
Token ID2612
Feature activation-2.54e-02

Pos logit contributions
 bal+0.136
 Tyler+0.128
 Seth+0.128
isc+0.126
ird+0.122
Neg logit contributions
rog-0.129
arium-0.128
Buzz-0.123
 Buzz-0.119
acle-0.118
Token start
Token ID923
Feature activation-5.18e-02

Pos logit contributions
 bal+0.036
 Seth+0.035
 Tyler+0.034
ird+0.034
cest+0.033
Neg logit contributions
rog-0.042
acle-0.040
arium-0.040
 Buzz-0.039
Buzz-0.038
Token to
Token ID284
Feature activation+6.01e-03

Pos logit contributions
 bal+0.089
uka+0.088
 Seth+0.088
 Tyler+0.088
ird+0.087
Neg logit contributions
rog-0.067
acle-0.066
arium-0.062
 Buzz-0.060
atively-0.060
Token like
Token ID588
Feature activation-1.44e-01

Pos logit contributions
ird+0.027
uka+0.026
 bal+0.026
 laund+0.025
isc+0.025
Neg logit contributions
acle-0.021
rog-0.020
 Buzz-0.020
arium-0.019
atively-0.018
Token a
Token ID257
Feature activation+5.68e-02

Pos logit contributions
 bal+0.247
ird+0.244
cest+0.236
 laund+0.235
isc+0.235
Neg logit contributions
rog-0.182
acle-0.177
 Buzz-0.175
arium-0.173
Buzz-0.165
Token giant
Token ID6175
Feature activation-2.29e-02

Pos logit contributions
rog+0.076
acle+0.075
arium+0.072
 Buzz+0.071
Buzz+0.070
Neg logit contributions
uka-0.094
 Seth-0.094
 Tyler-0.093
ird-0.093
isc-0.093
Token iron
Token ID6953
Feature activation-2.03e-01

Pos logit contributions
 Seth+0.036
 bal+0.036
 Tyler+0.036
uka+0.036
isc+0.035
Neg logit contributions
rog-0.032
acle-0.031
arium-0.031
 Buzz-0.030
Buzz-0.029
Token.
Token ID13
Feature activation-1.55e-02

Pos logit contributions
 Seth+0.328
uka+0.327
 Tyler+0.326
 bal+0.325
ird+0.323
Neg logit contributions
rog-0.279
acle-0.277
arium-0.258
 Buzz-0.254
atively-0.251
Token Tyler
Token ID14886
Feature activation-4.31e-01

Pos logit contributions
cest+0.038
 bal+0.034
ird+0.033
 hairst+0.033
 pian+0.033
Neg logit contributions
 True-0.009
acle-0.008
rog-0.007
 upon-0.007
<-0.006
Token couldn
Token ID3521
Feature activation-3.18e-02

Pos logit contributions
 bal+0.729
 Seth+0.708
 Tyler+0.702
uka+0.695
ird+0.694
Neg logit contributions
rog-0.585
acle-0.562
arium-0.550
 Buzz-0.534
Buzz-0.528
Token't
Token ID470
Feature activation+1.15e-01

Pos logit contributions
 bal+0.065
 Seth+0.064
cest+0.063
 Tyler+0.063
ird+0.063
Neg logit contributions
rog-0.032
acle-0.030
arium-0.029
 Buzz-0.028
Buzz-0.028
Token believe
Token ID1975
Feature activation+1.58e-02

Pos logit contributions
rog+0.161
acle+0.154
arium+0.152
 Buzz+0.146
Buzz+0.145
Neg logit contributions
 bal-0.191
 Seth-0.186
 Tyler-0.185
ird-0.181
uka-0.180
Token his
Token ID465
Feature activation-8.68e-02

Pos logit contributions
rog+0.021
acle+0.020
 Buzz+0.019
arium+0.019
atively+0.019
Neg logit contributions
ird-0.028
isc-0.028
 bal-0.028
 laund-0.027
uka-0.026
Token eyes
Token ID2951
Feature activation+1.32e-01

Pos logit contributions
 bal+0.182
 Seth+0.178
 Tyler+0.177
ird+0.174
uka+0.173
Neg logit contributions
rog-0.085
acle-0.079
arium-0.079
Buzz-0.074
 Buzz-0.074
Token was
Token ID373
Feature activation-1.73e-02

Pos logit contributions
rog+0.120
arium+0.113
acle+0.113
 Buzz+0.112
Buzz+0.108
Neg logit contributions
 bal-0.158
 Seth-0.152
 Tyler-0.151
ird-0.150
 laund-0.150
Token a
Token ID257
Feature activation+5.71e-02

Pos logit contributions
 bal+0.026
 Tyler+0.023
 Seth+0.023
uka+0.023
ird+0.022
Neg logit contributions
acle-0.030
rog-0.030
arium-0.028
atively-0.028
flies-0.025
Token little
Token ID1310
Feature activation+8.98e-02

Pos logit contributions
rog+0.061
arium+0.057
acle+0.056
Buzz+0.056
 Buzz+0.055
Neg logit contributions
 bal-0.112
 Seth-0.111
 Tyler-0.111
ird-0.109
isc-0.108
Token boy
Token ID2933
Feature activation+2.23e-02

Pos logit contributions
rog+0.127
acle+0.125
arium+0.121
atively+0.115
 Buzz+0.115
Neg logit contributions
 bal-0.149
 Seth-0.142
 Tyler-0.142
ird-0.139
cest-0.139
Token named
Token ID3706
Feature activation-9.72e-02

Pos logit contributions
rog+0.036
arium+0.034
 Buzz+0.033
Buzz+0.033
acle+0.032
Neg logit contributions
 bal-0.032
 Seth-0.032
 Tyler-0.032
isc-0.032
uka-0.031
Token Seth
Token ID20194
Feature activation-4.31e-01

Pos logit contributions
 Tyler+0.126
 Seth+0.124
 bal+0.122
uka+0.116
 Sel+0.115
Neg logit contributions
rog-0.174
acle-0.173
arium-0.169
atively-0.164
Buzz-0.160
Token.
Token ID13
Feature activation-8.49e-03

Pos logit contributions
 bal+0.635
 Seth+0.618
 Tyler+0.614
ird+0.603
uka+0.597
Neg logit contributions
rog-0.683
acle-0.661
arium-0.654
Buzz-0.629
 Buzz-0.628
Token Seth
Token ID20194
Feature activation-4.31e-01

Pos logit contributions
ird+0.019
 bal+0.018
 pian+0.016
 drummer+0.016
cest+0.016
Neg logit contributions
rog-0.006
acle-0.006
 One-0.006
agged-0.006
atively-0.005
Token loved
Token ID6151
Feature activation-7.69e-03

Pos logit contributions
 bal+0.634
 Seth+0.622
 Tyler+0.621
ird+0.606
uka+0.604
Neg logit contributions
rog-0.675
acle-0.659
arium-0.650
Buzz-0.618
 Buzz-0.613
Token watching
Token ID4964
Feature activation-5.44e-02

Pos logit contributions
ird+0.014
 bal+0.014
isc+0.014
 Seth+0.014
cest+0.013
Neg logit contributions
rog-0.009
 Buzz-0.009
arium-0.009
Buzz-0.008
acle-0.008
Token his
Token ID465
Feature activation-8.18e-02

Pos logit contributions
ird+0.097
 bal+0.094
uka+0.092
isc+0.092
cest+0.092
Neg logit contributions
rog-0.068
 Buzz-0.067
acle-0.064
arium-0.063
Buzz-0.062
Token little
Token ID1310
Feature activation+8.98e-02

Pos logit contributions
rog+0.061
arium+0.057
acle+0.056
Buzz+0.056
 Buzz+0.055
Neg logit contributions
 bal-0.112
 Seth-0.111
 Tyler-0.111
ird-0.109
isc-0.108
Token boy
Token ID2933
Feature activation+2.23e-02

Pos logit contributions
rog+0.127
acle+0.125
arium+0.121
atively+0.115
 Buzz+0.115
Neg logit contributions
 bal-0.149
 Seth-0.142
 Tyler-0.142
ird-0.139
cest-0.139
Token named
Token ID3706
Feature activation-9.72e-02

Pos logit contributions
rog+0.036
arium+0.034
 Buzz+0.033
Buzz+0.033
acle+0.032
Neg logit contributions
 bal-0.032
 Seth-0.032
 Tyler-0.032
isc-0.032
uka-0.031
Token Seth
Token ID20194
Feature activation-4.31e-01

Pos logit contributions
 Tyler+0.126
 Seth+0.124
 bal+0.122
uka+0.116
 Sel+0.115
Neg logit contributions
rog-0.174
acle-0.173
arium-0.169
atively-0.164
Buzz-0.160
Token.
Token ID13
Feature activation-8.49e-03

Pos logit contributions
 bal+0.635
 Seth+0.618
 Tyler+0.614
ird+0.603
uka+0.597
Neg logit contributions
rog-0.683
acle-0.661
arium-0.654
Buzz-0.629
 Buzz-0.628
Token Seth
Token ID20194
Feature activation-4.31e-01

Pos logit contributions
ird+0.019
 bal+0.018
 pian+0.016
 drummer+0.016
cest+0.016
Neg logit contributions
rog-0.006
acle-0.006
 One-0.006
agged-0.006
atively-0.005
Token loved
Token ID6151
Feature activation-7.69e-03

Pos logit contributions
 bal+0.634
 Seth+0.622
 Tyler+0.621
ird+0.606
uka+0.604
Neg logit contributions
rog-0.675
acle-0.659
arium-0.650
Buzz-0.618
 Buzz-0.613
Token watching
Token ID4964
Feature activation-5.44e-02

Pos logit contributions
ird+0.014
 bal+0.014
isc+0.014
 Seth+0.014
cest+0.013
Neg logit contributions
rog-0.009
 Buzz-0.009
arium-0.009
Buzz-0.008
acle-0.008
Token his
Token ID465
Feature activation-8.18e-02

Pos logit contributions
ird+0.097
 bal+0.094
uka+0.092
isc+0.092
cest+0.092
Neg logit contributions
rog-0.068
 Buzz-0.067
acle-0.064
arium-0.063
Buzz-0.062
Token favorite
Token ID4004
Feature activation-2.72e-02

Pos logit contributions
 bal+0.123
 Seth+0.121
 Tyler+0.119
ird+0.119
uka+0.118
Neg logit contributions
rog-0.125
acle-0.120
arium-0.119
 Buzz-0.115
Buzz-0.114
Token show
Token ID905
Feature activation-8.47e-02

Pos logit contributions
 bal+0.042
 Seth+0.041
 Tyler+0.041
ird+0.040
uka+0.040
Neg logit contributions
rog-0.041
arium-0.039
acle-0.039
 Buzz-0.038
Buzz-0.037
Token show
Token ID905
Feature activation-8.43e-02

Pos logit contributions
rog+0.055
Buzz+0.051
arium+0.051
acle+0.051
 Buzz+0.050
Neg logit contributions
 bal-0.037
 laund-0.036
 Tyler-0.035
 pian-0.035
 sax-0.034
Token started
Token ID2067
Feature activation-2.57e-02

Pos logit contributions
 bal+0.146
 Seth+0.144
uka+0.143
 Tyler+0.143
isc+0.142
Neg logit contributions
rog-0.104
arium-0.103
acle-0.102
atively-0.095
 Buzz-0.095
Token to
Token ID284
Feature activation+1.12e-02

Pos logit contributions
 bal+0.046
ird+0.046
uka+0.045
 Seth+0.044
isc+0.044
Neg logit contributions
rog-0.031
arium-0.030
acle-0.029
 Buzz-0.029
Buzz-0.027
Token freeze
Token ID16611
Feature activation-5.28e-02

Pos logit contributions
rog+0.017
acle+0.016
arium+0.016
Buzz+0.015
 Buzz+0.015
Neg logit contributions
 bal-0.018
 Seth-0.017
 Tyler-0.017
ird-0.017
uka-0.017
Token!
Token ID0
Feature activation-1.16e-01

Pos logit contributions
 bal+0.089
ird+0.089
uka+0.086
isc+0.085
 Seth+0.085
Neg logit contributions
rog-0.072
acle-0.069
arium-0.067
 Buzz-0.066
atively-0.064
Token Seth
Token ID20194
Feature activation-4.30e-01

Pos logit contributions
cest+0.251
 pian+0.239
ird+0.233
 bal+0.232
 hairst+0.221
Neg logit contributions
rog-0.084
acle-0.075
 One-0.075
<-0.069
agged-0.067
Token was
Token ID373
Feature activation-1.47e-02

Pos logit contributions
 bal+0.686
 Seth+0.669
 Tyler+0.667
ird+0.653
uka+0.647
Neg logit contributions
rog-0.631
acle-0.607
arium-0.599
Buzz-0.573
 Buzz-0.572
Token very
Token ID845
Feature activation-4.74e-02

Pos logit contributions
 bal+0.023
 Seth+0.022
 Tyler+0.022
ird+0.022
isc+0.022
Neg logit contributions
rog-0.022
acle-0.021
arium-0.021
 Buzz-0.020
Buzz-0.020
Token surprised
Token ID6655
Feature activation-4.28e-02

Pos logit contributions
 bal+0.078
 Seth+0.076
 Tyler+0.076
ird+0.074
uka+0.074
Neg logit contributions
rog-0.067
acle-0.065
arium-0.063
 Buzz-0.061
Buzz-0.061
Token and
Token ID290
Feature activation+6.69e-03

Pos logit contributions
ird+0.070
 bal+0.070
 Seth+0.068
uka+0.068
 Tyler+0.068
Neg logit contributions
rog-0.060
acle-0.057
arium-0.057
 Buzz-0.055
Buzz-0.053
Token felt
Token ID2936
Feature activation+2.39e-02

Pos logit contributions
rog+0.010
acle+0.009
arium+0.009
Buzz+0.009
 Buzz+0.009
Neg logit contributions
 bal-0.011
 Seth-0.010
 Tyler-0.010
ird-0.010
uka-0.010
Token was
Token ID373
Feature activation-1.80e-02

Pos logit contributions
 bal+0.055
 Seth+0.053
 Tyler+0.053
ird+0.052
uka+0.051
Neg logit contributions
rog-0.053
acle-0.051
arium-0.050
 Buzz-0.048
Buzz-0.048
Token a
Token ID257
Feature activation+5.65e-02

Pos logit contributions
 bal+0.030
ird+0.030
uka+0.029
 Seth+0.029
isc+0.029
Neg logit contributions
rog-0.024
acle-0.024
 Buzz-0.023
arium-0.023
Buzz-0.021
Token giant
Token ID6175
Feature activation-2.09e-02

Pos logit contributions
rog+0.077
acle+0.074
arium+0.071
 Buzz+0.069
Buzz+0.069
Neg logit contributions
 Seth-0.094
 Tyler-0.093
 bal-0.092
uka-0.092
ird-0.091
Token fish
Token ID5916
Feature activation+9.90e-02

Pos logit contributions
 Seth+0.033
uka+0.032
isc+0.032
 bal+0.032
 Tyler+0.032
Neg logit contributions
rog-0.029
acle-0.029
arium-0.028
 Buzz-0.027
Buzz-0.026
Token!
Token ID0
Feature activation-1.18e-01

Pos logit contributions
rog+0.149
acle+0.145
arium+0.142
 Buzz+0.137
Buzz+0.134
Neg logit contributions
 bal-0.150
 Seth-0.149
 Tyler-0.147
uka-0.146
 laund-0.145
Token Tyler
Token ID14886
Feature activation-4.30e-01

Pos logit contributions
cest+0.273
 bal+0.233
 pian+0.232
ird+0.232
 hairst+0.222
Neg logit contributions
 True-0.087
acle-0.085
rog-0.076
<-0.067
atively-0.065
Token gasped
Token ID45236
Feature activation+7.03e-02

Pos logit contributions
 bal+0.656
 Seth+0.642
 Tyler+0.640
ird+0.614
 Sel+0.613
Neg logit contributions
rog-0.658
arium-0.648
acle-0.630
Buzz-0.604
 Buzz-0.596
Token with
Token ID351
Feature activation+5.30e-03

Pos logit contributions
rog+0.114
arium+0.112
Buzz+0.108
acle+0.108
 Buzz+0.102
Neg logit contributions
 bal-0.103
 Tyler-0.100
 Seth-0.100
 Sel-0.094
cest-0.093
Token delight
Token ID10974
Feature activation-6.88e-02

Pos logit contributions
rog+0.008
acle+0.008
arium+0.007
 Buzz+0.007
Buzz+0.007
Neg logit contributions
 bal-0.009
 Seth-0.008
ird-0.008
uka-0.008
 Tyler-0.008
Token and
Token ID290
Feature activation-3.14e-03

Pos logit contributions
 bal+0.104
 Seth+0.100
 Tyler+0.100
cest+0.096
 Sel+0.095
Neg logit contributions
rog-0.109
arium-0.105
Buzz-0.103
acle-0.103
 Buzz-0.100
Token his
Token ID465
Feature activation-8.42e-02

Pos logit contributions
 bal+0.006
 laund+0.006
isc+0.005
ird+0.005
uka+0.005
Neg logit contributions
acle-0.004
 Buzz-0.004
rog-0.004
atively-0.004
arium-0.004
Token he
Token ID339
Feature activation-3.15e-02

Pos logit contributions
ird+0.007
 bal+0.007
isc+0.007
uka+0.007
 laund+0.007
Neg logit contributions
acle-0.006
 Buzz-0.006
arium-0.006
rog-0.006
atively-0.005
Token made
Token ID925
Feature activation-1.37e-01

Pos logit contributions
 bal+0.052
 Seth+0.051
 Tyler+0.051
 laund+0.050
ird+0.050
Neg logit contributions
acle-0.041
rog-0.041
arium-0.040
 Buzz-0.040
Buzz-0.039
Token a
Token ID257
Feature activation+5.27e-02

Pos logit contributions
 bal+0.223
 Seth+0.217
 Tyler+0.216
ird+0.212
uka+0.210
Neg logit contributions
rog-0.195
acle-0.188
arium-0.185
 Buzz-0.178
Buzz-0.177
Token bridge
Token ID7696
Feature activation-3.99e-02

Pos logit contributions
rog+0.074
acle+0.072
arium+0.070
Buzz+0.068
 Buzz+0.068
Neg logit contributions
 bal-0.085
 Seth-0.084
 Tyler-0.084
ird-0.083
uka-0.083
Token!
Token ID0
Feature activation-1.25e-01

Pos logit contributions
 bal+0.062
 Seth+0.061
 Tyler+0.061
ird+0.059
uka+0.059
Neg logit contributions
rog-0.059
acle-0.057
arium-0.056
 Buzz-0.054
Buzz-0.053
Token Tyler
Token ID14886
Feature activation-4.30e-01

Pos logit contributions
cest+0.229
 bal+0.222
 laund+0.216
 pian+0.216
ird+0.214
Neg logit contributions
rog-0.157
 Buzz-0.154
acle-0.148
Buzz-0.143
arium-0.141
Token was
Token ID373
Feature activation-2.68e-02

Pos logit contributions
 bal+0.722
 Seth+0.701
 Tyler+0.691
uka+0.688
isc+0.681
Neg logit contributions
rog-0.583
acle-0.559
arium-0.546
 Buzz-0.533
Buzz-0.530
Token so
Token ID523
Feature activation-8.68e-02

Pos logit contributions
isc+0.052
 bal+0.048
ird+0.048
uka+0.047
 laund+0.047
Neg logit contributions
 Buzz-0.029
acle-0.029
rog-0.026
 nowhere-0.025
atively-0.024
Token happy
Token ID3772
Feature activation+3.29e-02

Pos logit contributions
isc+0.159
 Tyler+0.157
 laund+0.156
 Seth+0.156
 pian+0.155
Neg logit contributions
acle-0.097
 Buzz-0.096
rog-0.095
Buzz-0.090
atively-0.087
Token.
Token ID13
Feature activation-2.33e-02

Pos logit contributions
rog+0.048
acle+0.046
arium+0.046
 Buzz+0.044
Buzz+0.043
Neg logit contributions
 bal-0.052
 Seth-0.051
ird-0.050
 Tyler-0.050
uka-0.050
Token He
Token ID679
Feature activation-7.91e-03

Pos logit contributions
cest+0.058
 pian+0.056
ird+0.055
 bal+0.054
 hairst+0.052
Neg logit contributions
rog-0.013
 True-0.013
 Buzz-0.013
acle-0.011
 Freddy-0.011
Token all
Token ID477
Feature activation+3.48e-02

Pos logit contributions
cest+0.037
opl+0.034
 North+0.033
 skysc+0.032
isc+0.031
Neg logit contributions
 upon-0.014
atively-0.012
 first-0.012
 True-0.012
 nowhere-0.012
Token of
Token ID286
Feature activation-7.64e-02

Pos logit contributions
arium+0.041
rog+0.041
 Buzz+0.038
acle+0.036
atively+0.035
Neg logit contributions
 bal-0.060
 laund-0.059
isc-0.058
ird-0.058
cest-0.058
Token a
Token ID257
Feature activation+5.60e-02

Pos logit contributions
 bal+0.132
cest+0.128
ird+0.124
isc+0.122
 laund+0.118
Neg logit contributions
rog-0.103
 Buzz-0.096
arium-0.096
acle-0.092
Buzz-0.089
Token sudden
Token ID4802
Feature activation-2.46e-02

Pos logit contributions
rog+0.082
acle+0.079
arium+0.078
Buzz+0.076
 Buzz+0.075
Neg logit contributions
 bal-0.087
 Seth-0.086
 Tyler-0.085
uka-0.084
isc-0.084
Token,
Token ID11
Feature activation-1.78e-02

Pos logit contributions
cest+0.043
 bal+0.042
uka+0.042
 laund+0.042
isc+0.041
Neg logit contributions
rog-0.028
 Buzz-0.028
arium-0.028
acle-0.027
atively-0.026
Token Tyler
Token ID14886
Feature activation-4.29e-01

Pos logit contributions
cest+0.031
opl+0.028
 bal+0.028
 North+0.027
ird+0.027
Neg logit contributions
arium-0.020
 nowhere-0.020
rog-0.019
atively-0.019
 True-0.019
Token saw
Token ID2497
Feature activation+1.20e-02

Pos logit contributions
 bal+0.725
 Seth+0.706
cest+0.704
uka+0.700
 laund+0.700
Neg logit contributions
acle-0.549
rog-0.544
arium-0.533
 Buzz-0.517
atively-0.505
Token a
Token ID257
Feature activation+5.50e-02

Pos logit contributions
rog+0.013
acle+0.012
 Buzz+0.012
arium+0.012
atively+0.011
Neg logit contributions
 bal-0.023
ird-0.023
cest-0.022
isc-0.022
 Seth-0.022
Token big
Token ID1263
Feature activation-7.49e-02

Pos logit contributions
rog+0.077
acle+0.075
arium+0.073
 Buzz+0.070
Buzz+0.070
Neg logit contributions
 bal-0.090
 Seth-0.088
 Tyler-0.087
uka-0.086
ird-0.086
Token black
Token ID2042
Feature activation-4.86e-02

Pos logit contributions
 bal+0.118
 Seth+0.114
 Tyler+0.114
ird+0.111
cest+0.110
Neg logit contributions
rog-0.111
acle-0.106
arium-0.105
Buzz-0.102
 Buzz-0.101
Token cloud
Token ID6279
Feature activation+1.84e-02

Pos logit contributions
 bal+0.076
 Tyler+0.070
ird+0.070
 Seth+0.070
 roller+0.069
Neg logit contributions
rog-0.074
arium-0.072
acle-0.070
Buzz-0.070
 Buzz-0.068
Token Next
Token ID7406
Feature activation+1.38e-01

Pos logit contributions
 bal+0.026
 Seth+0.025
 Tyler+0.025
ird+0.024
uka+0.024
Neg logit contributions
rog-0.021
acle-0.020
arium-0.020
 Buzz-0.019
Buzz-0.019
Token,
Token ID11
Feature activation-2.61e-02

Pos logit contributions
rog+0.199
acle+0.191
arium+0.190
 Buzz+0.182
Buzz+0.179
Neg logit contributions
 bal-0.223
 Seth-0.216
 Tyler-0.213
ird-0.211
uka-0.211
Token Bobby
Token ID17155
Feature activation-1.08e-02

Pos logit contributions
 bal+0.043
 Seth+0.042
uka+0.042
isc+0.042
cest+0.042
Neg logit contributions
rog-0.036
arium-0.035
acle-0.035
 Buzz-0.033
Buzz-0.032
Token and
Token ID290
Feature activation-6.76e-03

Pos logit contributions
 bal+0.018
 Seth+0.017
uka+0.017
ird+0.017
 laund+0.017
Neg logit contributions
rog-0.014
acle-0.014
arium-0.014
 Buzz-0.014
Buzz-0.013
Token then
Token ID788
Feature activation+2.96e-02

Pos logit contributions
 bal+0.012
 Seth+0.011
ird+0.011
uka+0.011
isc+0.011
Neg logit contributions
rog-0.009
arium-0.008
 Buzz-0.008
acle-0.008
Buzz-0.008
Token Tyler
Token ID14886
Feature activation-4.29e-01

Pos logit contributions
 Buzz+0.038
rog+0.037
arium+0.037
acle+0.034
Buzz+0.034
Neg logit contributions
isc-0.048
cest-0.048
uka-0.047
 laund-0.047
 bal-0.047
Token.
Token ID13
Feature activation-2.07e-02

Pos logit contributions
 bal+0.743
cest+0.729
uka+0.725
 Seth+0.716
 laund+0.702
Neg logit contributions
rog-0.515
arium-0.488
acle-0.487
 Buzz-0.482
Buzz-0.469
Token
Token ID198
Feature activation-3.39e-02

Pos logit contributions
 bal+0.037
cest+0.035
 Seth+0.035
ird+0.035
uka+0.035
Neg logit contributions
rog-0.027
acle-0.026
arium-0.025
 Buzz-0.025
Buzz-0.024
Token
Token ID198
Feature activation-3.39e-02

Pos logit contributions
 bal+0.056
 Seth+0.054
cest+0.054
isc+0.053
ird+0.053
Neg logit contributions
rog-0.048
arium-0.046
acle-0.045
Buzz-0.045
 Buzz-0.044
TokenWhen
Token ID2215
Feature activation-3.61e-02

Pos logit contributions
 bal+0.056
 Seth+0.055
isc+0.054
 Tyler+0.053
cest+0.053
Neg logit contributions
rog-0.047
arium-0.045
Buzz-0.045
acle-0.044
 Buzz-0.043
Token it
Token ID340
Feature activation-3.63e-02

Pos logit contributions
 bal+0.062
 Seth+0.060
ird+0.060
cest+0.059
uka+0.059
Neg logit contributions
rog-0.048
arium-0.046
acle-0.046
 Buzz-0.045
Buzz-0.043
Token so
Token ID523
Feature activation-8.32e-02

Pos logit contributions
 bal+0.008
 Seth+0.008
 Tyler+0.007
cest+0.007
 laund+0.007
Neg logit contributions
rog-0.008
arium-0.008
acle-0.008
Buzz-0.007
 Buzz-0.007
Token big
Token ID1263
Feature activation-7.50e-02

Pos logit contributions
 bal+0.107
 Seth+0.101
 Tyler+0.099
 Sel+0.098
cest+0.098
Neg logit contributions
rog-0.153
arium-0.148
acle-0.143
atively-0.133
Buzz-0.132
Token and
Token ID290
Feature activation+4.32e-04

Pos logit contributions
uka+0.139
ird+0.138
 bal+0.137
isc+0.137
 Seth+0.136
Neg logit contributions
acle-0.085
arium-0.083
 Buzz-0.082
rog-0.082
atively-0.075
Token bright
Token ID6016
Feature activation+8.20e-03

Pos logit contributions
rog+0.001
acle+0.001
arium+0.001
Buzz+0.001
 Buzz+0.001
Neg logit contributions
 bal-0.001
 Seth-0.001
 Tyler-0.001
ird-0.001
uka-0.001
Token and
Token ID290
Feature activation+9.57e-04

Pos logit contributions
rog+0.013
acle+0.012
arium+0.012
Buzz+0.011
 Buzz+0.011
Neg logit contributions
 bal-0.013
 Seth-0.012
 Tyler-0.012
ird-0.012
cest-0.012
Token Tyler
Token ID14886
Feature activation-4.29e-01

Pos logit contributions
rog+0.001
acle+0.001
arium+0.001
 Buzz+0.001
Buzz+0.001
Neg logit contributions
 bal-0.001
 Seth-0.001
 Tyler-0.001
ird-0.001
uka-0.001
Token was
Token ID373
Feature activation-2.46e-02

Pos logit contributions
 bal+0.673
 Seth+0.653
 Tyler+0.649
ird+0.638
uka+0.631
Neg logit contributions
rog-0.637
acle-0.612
arium-0.606
 Buzz-0.579
Buzz-0.579
Token scared
Token ID12008
Feature activation-1.34e-03

Pos logit contributions
 bal+0.035
 Seth+0.033
 Tyler+0.033
ird+0.032
cest+0.032
Neg logit contributions
rog-0.041
arium-0.040
acle-0.039
Buzz-0.038
 Buzz-0.037
Token.
Token ID13
Feature activation-9.41e-03

Pos logit contributions
uka+0.002
 bal+0.002
ird+0.002
isc+0.002
 laund+0.002
Neg logit contributions
rog-0.002
 Buzz-0.002
acle-0.002
arium-0.001
Buzz-0.001
Token
Token ID198
Feature activation-3.05e-02

Pos logit contributions
cest+0.021
 bal+0.019
ird+0.019
 pian+0.018
 hairst+0.018
Neg logit contributions
rog-0.009
acle-0.008
 True-0.008
 Buzz-0.008
arium-0.007
Token
Token ID198
Feature activation-3.17e-02

Pos logit contributions
cest+0.065
 bal+0.064
 pian+0.061
 laund+0.059
isc+0.059
Neg logit contributions
rog-0.031
Buzz-0.028
 Buzz-0.025
acle-0.025
arium-0.024
Token lot
Token ID1256
Feature activation-1.14e-01

Pos logit contributions
rog+0.090
acle+0.087
arium+0.087
Buzz+0.084
 Buzz+0.083
Neg logit contributions
 Seth-0.074
 bal-0.074
 Tyler-0.073
uka-0.071
cest-0.071
Token of
Token ID286
Feature activation-7.22e-02

Pos logit contributions
 bal+0.147
 Seth+0.136
ird+0.136
 Tyler+0.134
 laund+0.132
Neg logit contributions
rog-0.205
acle-0.201
arium-0.196
Buzz-0.190
 Buzz-0.190
Token fun
Token ID1257
Feature activation-4.65e-02

Pos logit contributions
 bal+0.112
 Seth+0.109
 Tyler+0.109
ird+0.106
uka+0.106
Neg logit contributions
rog-0.109
acle-0.104
arium-0.103
 Buzz-0.100
Buzz-0.099
Token today
Token ID1909
Feature activation-1.97e-02

Pos logit contributions
 bal+0.073
 Seth+0.071
 Tyler+0.070
ird+0.069
uka+0.069
Neg logit contributions
rog-0.069
acle-0.067
arium-0.066
 Buzz-0.063
Buzz-0.063
Token.
Token ID13
Feature activation-1.36e-02

Pos logit contributions
uka+0.036
 Seth+0.035
 bal+0.035
 Tyler+0.035
isc+0.035
Neg logit contributions
arium-0.023
rog-0.022
acle-0.022
 Buzz-0.021
atively-0.020
Token Tyler
Token ID14886
Feature activation-4.28e-01

Pos logit contributions
cest+0.031
 bal+0.028
 hairst+0.027
ird+0.026
 laund+0.026
Neg logit contributions
rog-0.010
arium-0.010
 True-0.010
 Buzz-0.009
acle-0.009
Token wanted
Token ID2227
Feature activation+2.52e-02

Pos logit contributions
 bal+0.684
 Seth+0.665
 Tyler+0.662
ird+0.649
uka+0.643
Neg logit contributions
rog-0.621
acle-0.597
arium-0.589
Buzz-0.565
 Buzz-0.565
Token to
Token ID284
Feature activation+1.14e-02

Pos logit contributions
rog+0.028
 Buzz+0.026
arium+0.026
acle+0.025
Buzz+0.024
Neg logit contributions
 bal-0.048
cest-0.048
ird-0.048
isc-0.047
 Seth-0.046
Token relax
Token ID8960
Feature activation+6.46e-02

Pos logit contributions
rog+0.014
 Buzz+0.013
acle+0.013
Buzz+0.013
arium+0.012
Neg logit contributions
 bal-0.020
uka-0.020
isc-0.020
cest-0.020
 Tyler-0.020
Token and
Token ID290
Feature activation-5.10e-03

Pos logit contributions
rog+0.085
acle+0.083
arium+0.082
 Buzz+0.080
Buzz+0.077
Neg logit contributions
 bal-0.110
 Seth-0.109
 Tyler-0.107
ird-0.107
isc-0.107
Token enjoy
Token ID2883
Feature activation-5.75e-03

Pos logit contributions
 bal+0.008
 Seth+0.007
ird+0.007
 Tyler+0.007
 Sel+0.007
Neg logit contributions
rog-0.008
acle-0.008
arium-0.008
Buzz-0.007
atively-0.007
Token dark
Token ID3223
Feature activation-6.50e-03

Pos logit contributions
 bal+0.004
ird+0.004
 Seth+0.004
isc+0.004
 Tyler+0.004
Neg logit contributions
rog-0.004
acle-0.004
arium-0.004
 Buzz-0.004
Buzz-0.004
Token storm
Token ID6388
Feature activation+3.92e-02

Pos logit contributions
 bal+0.010
 Seth+0.009
 Tyler+0.009
cest+0.009
ird+0.009
Neg logit contributions
rog-0.010
acle-0.010
arium-0.010
Buzz-0.009
 Buzz-0.009
Token clouds
Token ID15114
Feature activation+9.50e-03

Pos logit contributions
rog+0.061
acle+0.059
arium+0.058
 Buzz+0.056
Buzz+0.056
Neg logit contributions
 bal-0.058
 Seth-0.056
 Tyler-0.056
ird-0.055
uka-0.055
Token above
Token ID2029
Feature activation+1.40e-01

Pos logit contributions
rog+0.015
acle+0.014
arium+0.014
Buzz+0.014
 Buzz+0.014
Neg logit contributions
 bal-0.014
 Seth-0.014
 Tyler-0.014
ird-0.013
uka-0.013
Token.
Token ID13
Feature activation-1.71e-02

Pos logit contributions
rog+0.135
acle+0.134
 Buzz+0.129
atively+0.127
arium+0.118
Neg logit contributions
 bal-0.280
ird-0.279
cest-0.270
 laund-0.262
uka-0.259
Token Tyler
Token ID14886
Feature activation-4.27e-01

Pos logit contributions
cest+0.040
 bal+0.034
ird+0.034
 pian+0.033
 North+0.032
Neg logit contributions
 True-0.013
acle-0.012
rog-0.012
 Marie-0.012
 Amy-0.011
Token started
Token ID2067
Feature activation-2.53e-02

Pos logit contributions
 bal+0.658
 Seth+0.640
 Tyler+0.637
ird+0.620
 Sel+0.612
Neg logit contributions
rog-0.655
acle-0.631
arium-0.631
Buzz-0.596
 Buzz-0.594
Token to
Token ID284
Feature activation+7.48e-03

Pos logit contributions
 bal+0.043
 Seth+0.041
ird+0.041
 Tyler+0.041
uka+0.041
Neg logit contributions
rog-0.034
acle-0.033
arium-0.032
 Buzz-0.031
Buzz-0.031
Token worry
Token ID5490
Feature activation+1.09e-01

Pos logit contributions
rog+0.011
acle+0.010
arium+0.010
Buzz+0.010
 Buzz+0.009
Neg logit contributions
 bal-0.012
 Seth-0.012
 Tyler-0.012
 Sel-0.012
 laund-0.012
Token,
Token ID11
Feature activation-1.82e-02

Pos logit contributions
rog+0.164
acle+0.158
arium+0.155
 Buzz+0.150
Buzz+0.149
Neg logit contributions
 bal-0.168
 Seth-0.163
 Tyler-0.162
ird-0.159
uka-0.158
Token because
Token ID780
Feature activation-6.58e-02

Pos logit contributions
 bal+0.027
ird+0.026
 Seth+0.026
uka+0.026
 Tyler+0.026
Neg logit contributions
rog-0.028
acle-0.027
arium-0.027
 Buzz-0.026
Buzz-0.026
Token the
Token ID262
Feature activation-1.70e-02

Pos logit contributions
rog+0.014
acle+0.013
arium+0.013
 Buzz+0.013
Buzz+0.012
Neg logit contributions
 bal-0.015
 Seth-0.014
ird-0.014
cest-0.014
 Tyler-0.014
Token store
Token ID3650
Feature activation-9.38e-02

Pos logit contributions
isc+0.025
ird+0.025
 bal+0.025
cest+0.025
 Seth+0.025
Neg logit contributions
rog-0.025
acle-0.024
Buzz-0.023
 Buzz-0.023
arium-0.023
Token and
Token ID290
Feature activation-2.42e-03

Pos logit contributions
 bal+0.129
 Seth+0.127
 Tyler+0.126
 laund+0.123
ird+0.122
Neg logit contributions
rog-0.160
Buzz-0.154
 Buzz-0.147
acle-0.146
arium-0.145
Token got
Token ID1392
Feature activation-3.23e-02

Pos logit contributions
cest+0.004
 bal+0.004
 Seth+0.004
isc+0.004
 pian+0.004
Neg logit contributions
arium-0.003
rog-0.003
 Buzz-0.003
acle-0.003
Buzz-0.003
Token the
Token ID262
Feature activation-1.86e-02

Pos logit contributions
 bal+0.055
 Seth+0.053
 Tyler+0.053
cest+0.052
ird+0.052
Neg logit contributions
rog-0.044
acle-0.042
arium-0.042
 Buzz-0.041
Buzz-0.040
Token bal
Token ID3652
Feature activation-4.27e-01

Pos logit contributions
 Seth+0.028
cest+0.028
ird+0.028
 Tyler+0.028
 Cam+0.027
Neg logit contributions
rog-0.026
acle-0.024
Buzz-0.024
 Buzz-0.024
atively-0.023
Tokenm
Token ID76
Feature activation+3.04e-03

Pos logit contributions
 bal+0.589
ird+0.576
uka+0.568
 Tyler+0.558
 Seth+0.550
Neg logit contributions
acle-0.732
rog-0.730
arium-0.703
 Buzz-0.692
Buzz-0.678
Token.
Token ID13
Feature activation-2.10e-02

Pos logit contributions
rog+0.005
acle+0.004
arium+0.004
 Buzz+0.004
Buzz+0.004
Neg logit contributions
 Tyler-0.004
 Seth-0.004
 bal-0.004
 laund-0.004
ird-0.004
Token She
Token ID1375
Feature activation+7.17e-03

Pos logit contributions
cest+0.040
 pian+0.037
ird+0.037
 sax+0.037
 bal+0.037
Neg logit contributions
rog-0.026
 Buzz-0.025
acle-0.024
arium-0.024
Buzz-0.023
Token carefully
Token ID7773
Feature activation+1.20e-01

Pos logit contributions
rog+0.009
 Buzz+0.009
arium+0.009
acle+0.009
Buzz+0.009
Neg logit contributions
cest-0.012
 Seth-0.012
 Tyler-0.011
 bal-0.011
uka-0.011
Token rubbed
Token ID31862
Feature activation-4.17e-02

Pos logit contributions
rog+0.156
acle+0.155
arium+0.153
 Buzz+0.151
atively+0.146
Neg logit contributions
cest-0.200
 Seth-0.194
 Tyler-0.192
 bal-0.189
isc-0.189
Token started
Token ID2067
Feature activation-2.43e-02

Pos logit contributions
 bal+0.084
 Seth+0.082
 Tyler+0.081
ird+0.079
cest+0.078
Neg logit contributions
rog-0.086
acle-0.083
arium-0.082
Buzz-0.079
 Buzz-0.079
Token to
Token ID284
Feature activation+8.69e-03

Pos logit contributions
 bal+0.040
 Seth+0.039
ird+0.039
 Tyler+0.039
uka+0.039
Neg logit contributions
rog-0.033
acle-0.032
arium-0.032
 Buzz-0.031
Buzz-0.030
Token come
Token ID1282
Feature activation-4.55e-02

Pos logit contributions
rog+0.013
arium+0.013
acle+0.013
Buzz+0.012
 Buzz+0.012
Neg logit contributions
 bal-0.013
 Seth-0.013
 Tyler-0.013
 Sel-0.013
 laund-0.013
Token down
Token ID866
Feature activation-6.04e-02

Pos logit contributions
 bal+0.062
 Seth+0.060
 Tyler+0.059
cest+0.057
 Sel+0.057
Neg logit contributions
rog-0.078
arium-0.075
acle-0.074
Buzz-0.073
 Buzz-0.072
Token and
Token ID290
Feature activation-1.52e-03

Pos logit contributions
 bal+0.105
ird+0.104
uka+0.104
isc+0.101
cest+0.100
Neg logit contributions
acle-0.078
rog-0.077
arium-0.075
 Buzz-0.074
atively-0.073
Token Tyler
Token ID14886
Feature activation-4.27e-01

Pos logit contributions
ird+0.003
 bal+0.002
uka+0.002
cest+0.002
isc+0.002
Neg logit contributions
rog-0.002
arium-0.002
acle-0.002
 Buzz-0.002
Buzz-0.002
Token knew
Token ID2993
Feature activation-1.25e-01

Pos logit contributions
 bal+0.704
uka+0.684
 Seth+0.683
 Tyler+0.675
cest+0.672
Neg logit contributions
rog-0.574
acle-0.561
arium-0.545
 Buzz-0.538
Buzz-0.527
Token it
Token ID340
Feature activation-3.16e-02

Pos logit contributions
 bal+0.226
isc+0.220
ird+0.220
cest+0.219
 laund+0.214
Neg logit contributions
rog-0.143
arium-0.139
acle-0.138
 Buzz-0.137
atively-0.128
Token was
Token ID373
Feature activation-1.79e-02

Pos logit contributions
 bal+0.049
 Seth+0.047
 Tyler+0.047
ird+0.046
uka+0.046
Neg logit contributions
rog-0.048
acle-0.046
arium-0.046
Buzz-0.044
 Buzz-0.044
Token time
Token ID640
Feature activation+1.35e-02

Pos logit contributions
 bal+0.031
uka+0.031
ird+0.031
isc+0.031
 Tyler+0.030
Neg logit contributions
acle-0.023
rog-0.022
 Buzz-0.022
arium-0.022
Buzz-0.020
Token to
Token ID284
Feature activation+9.57e-03

Pos logit contributions
rog+0.020
acle+0.019
arium+0.019
Buzz+0.018
 Buzz+0.018
Neg logit contributions
 bal-0.021
 Seth-0.021
 Tyler-0.021
ird-0.020
uka-0.020
Token
Token ID198
Feature activation-3.35e-02

Pos logit contributions
cest+0.032
 bal+0.029
 pian+0.028
ird+0.028
 hairst+0.027
Neg logit contributions
rog-0.011
acle-0.011
 True-0.011
 Buzz-0.010
atively-0.009
Token
Token ID198
Feature activation-3.35e-02

Pos logit contributions
cest+0.075
 bal+0.073
 pian+0.071
 laund+0.068
ird+0.067
Neg logit contributions
rog-0.030
Buzz-0.026
 Buzz-0.024
acle-0.024
arium-0.023
TokenThe
Token ID464
Feature activation-2.20e-02

Pos logit contributions
cest+0.065
 bal+0.061
isc+0.060
 Es+0.058
 Jem+0.058
Neg logit contributions
rog-0.031
Buzz-0.030
<-0.028
acle-0.028
urious-0.027
Token monster
Token ID9234
Feature activation+3.90e-02

Pos logit contributions
 bal+0.026
 Tyler+0.024
 roller+0.023
 pian+0.022
 North+0.022
Neg logit contributions
rog-0.042
acle-0.041
arium-0.041
alk-0.040
agged-0.039
Token grabbed
Token ID13176
Feature activation-3.55e-02

Pos logit contributions
rog+0.060
arium+0.057
acle+0.057
Buzz+0.054
 Buzz+0.054
Neg logit contributions
 bal-0.061
 Seth-0.058
 Tyler-0.058
ird-0.056
 Sel-0.055
Token Tyler
Token ID14886
Feature activation-4.26e-01

Pos logit contributions
cest+0.067
ird+0.066
 bal+0.066
 laund+0.061
 North+0.061
Neg logit contributions
rog-0.040
acle-0.040
 True-0.039
 Buzz-0.037
atively-0.036
Token and
Token ID290
Feature activation-1.30e-03

Pos logit contributions
 bal+0.588
 Tyler+0.568
 Seth+0.563
ird+0.533
 Sel+0.531
Neg logit contributions
rog-0.729
arium-0.711
Buzz-0.699
acle-0.692
 Buzz-0.668
Token said
Token ID531
Feature activation-8.17e-03

Pos logit contributions
uka+0.002
cest+0.002
 bal+0.002
ird+0.002
opl+0.002
Neg logit contributions
 Buzz-0.002
acle-0.002
rog-0.002
atively-0.001
arium-0.001
Token,
Token ID11
Feature activation-1.62e-02

Pos logit contributions
 bal+0.013
 Seth+0.013
 Tyler+0.013
ird+0.012
uka+0.012
Neg logit contributions
rog-0.012
acle-0.012
arium-0.011
 Buzz-0.011
Buzz-0.011
Token "
Token ID366
Feature activation-7.10e-02

Pos logit contributions
 bal+0.022
 Seth+0.021
 Tyler+0.021
ird+0.021
uka+0.020
Neg logit contributions
rog-0.028
acle-0.027
arium-0.026
 Buzz-0.026
Buzz-0.025
TokenYou
Token ID1639
Feature activation-1.51e-02

Pos logit contributions
 bal+0.111
ird+0.110
cest+0.107
isc+0.104
 laund+0.104
Neg logit contributions
rog-0.099
Buzz-0.099
acle-0.092
 Buzz-0.090
arium-0.088
Token boy
Token ID2933
Feature activation+2.35e-02

Pos logit contributions
rog+0.134
acle+0.131
arium+0.127
Buzz+0.121
 Buzz+0.121
Neg logit contributions
 bal-0.159
 Seth-0.152
 Tyler-0.152
cest-0.148
ird-0.148
Token.
Token ID13
Feature activation-5.32e-03

Pos logit contributions
rog+0.037
arium+0.034
 Buzz+0.033
Buzz+0.033
acle+0.032
Neg logit contributions
 Tyler-0.036
 bal-0.035
 Seth-0.035
isc-0.035
 laund-0.035
Token He
Token ID679
Feature activation+2.79e-03

Pos logit contributions
 bal+0.008
 Seth+0.008
 Tyler+0.008
ird+0.008
uka+0.008
Neg logit contributions
rog-0.008
acle-0.008
arium-0.007
Buzz-0.007
 Buzz-0.007
Token was
Token ID373
Feature activation-1.26e-02

Pos logit contributions
rog+0.005
acle+0.004
arium+0.004
 Buzz+0.004
atively+0.004
Neg logit contributions
 bal-0.004
 Seth-0.004
 Tyler-0.004
uka-0.004
cest-0.004
Token called
Token ID1444
Feature activation-1.46e-01

Pos logit contributions
 bal+0.019
 Seth+0.019
 Tyler+0.019
ird+0.019
cest+0.018
Neg logit contributions
rog-0.019
acle-0.018
arium-0.018
 Buzz-0.018
Buzz-0.017
Token Tyler
Token ID14886
Feature activation-4.26e-01

Pos logit contributions
 Tyler+0.193
 Seth+0.192
 bal+0.185
 roller+0.179
 Sel+0.179
Neg logit contributions
rog-0.253
arium-0.246
Buzz-0.245
acle-0.243
atively-0.236
Token.
Token ID13
Feature activation-4.12e-03

Pos logit contributions
 bal+0.659
 Seth+0.638
 Tyler+0.633
ird+0.621
uka+0.618
Neg logit contributions
rog-0.652
acle-0.628
arium-0.619
 Buzz-0.597
Buzz-0.594
Token Tyler
Token ID14886
Feature activation-4.26e-01

Pos logit contributions
 bal+0.010
cest+0.009
ird+0.009
ele+0.009
 hairst+0.008
Neg logit contributions
 One-0.002
acle-0.002
 True-0.002
rog-0.002
arium-0.002
Token liked
Token ID8288
Feature activation+4.15e-02

Pos logit contributions
 bal+0.664
 Seth+0.650
 Tyler+0.649
ird+0.634
uka+0.624
Neg logit contributions
rog-0.634
acle-0.612
arium-0.602
Buzz-0.580
 Buzz-0.573
Token to
Token ID284
Feature activation+1.33e-02

Pos logit contributions
rog+0.051
arium+0.050
 Buzz+0.049
acle+0.048
Buzz+0.047
Neg logit contributions
 bal-0.074
ird-0.073
 Seth-0.073
isc-0.072
 Tyler-0.072
Token explore
Token ID7301
Feature activation+8.66e-03

Pos logit contributions
rog+0.018
acle+0.017
arium+0.017
 Buzz+0.017
Buzz+0.017
Neg logit contributions
 bal-0.023
 Seth-0.022
 Tyler-0.022
uka-0.022
ird-0.021
Token's
Token ID338
Feature activation-5.49e-02

Pos logit contributions
rog+0.020
acle+0.019
arium+0.019
atively+0.018
Buzz+0.018
Neg logit contributions
 bal-0.015
 Seth-0.014
 Tyler-0.014
ird-0.014
 Sel-0.013
Token good
Token ID922
Feature activation-1.24e-01

Pos logit contributions
 bal+0.096
 Seth+0.094
 Tyler+0.093
isc+0.093
ird+0.093
Neg logit contributions
rog-0.071
 Buzz-0.067
acle-0.067
arium-0.064
Buzz-0.062
Token for
Token ID329
Feature activation-5.68e-03

Pos logit contributions
 Seth+0.215
 Tyler+0.214
uka+0.212
 bal+0.212
 laund+0.211
Neg logit contributions
rog-0.157
acle-0.150
arium-0.147
 Buzz-0.146
atively-0.135
Token you
Token ID345
Feature activation+1.12e-01

Pos logit contributions
 bal+0.011
 Seth+0.010
 Tyler+0.010
ird+0.010
isc+0.010
Neg logit contributions
rog-0.007
acle-0.006
arium-0.006
 Buzz-0.006
Buzz-0.006
Token!"
Token ID2474
Feature activation-7.02e-02

Pos logit contributions
rog+0.183
acle+0.177
arium+0.175
Buzz+0.169
 Buzz+0.168
Neg logit contributions
 bal-0.160
 Seth-0.155
 Tyler-0.154
ird-0.152
cest-0.149
Token Tyler
Token ID14886
Feature activation-4.26e-01

Pos logit contributions
cest+0.171
 North+0.148
 bal+0.147
ird+0.145
uka+0.143
Neg logit contributions
rog-0.041
 True-0.040
acle-0.037
 Buzz-0.034
atively-0.034
Token couldn
Token ID3521
Feature activation-2.70e-02

Pos logit contributions
 bal+0.707
 Tyler+0.682
 Seth+0.680
ird+0.668
 Sel+0.657
Neg logit contributions
rog-0.600
arium-0.597
acle-0.582
Buzz-0.556
 Buzz-0.542
Token't
Token ID470
Feature activation+1.19e-01

Pos logit contributions
 bal+0.058
 Seth+0.056
cest+0.056
 Tyler+0.056
ird+0.056
Neg logit contributions
rog-0.024
acle-0.023
arium-0.022
 Buzz-0.022
Buzz-0.021
Token help
Token ID1037
Feature activation+3.92e-02

Pos logit contributions
arium+0.190
rog+0.183
acle+0.183
Buzz+0.171
 Buzz+0.171
Neg logit contributions
 bal-0.179
ird-0.172
 Seth-0.167
 Tyler-0.165
 Sel-0.162
Token but
Token ID475
Feature activation-6.30e-02

Pos logit contributions
rog+0.044
 Buzz+0.038
acle+0.035
 True+0.034
isy+0.032
Neg logit contributions
isc-0.078
ird-0.075
 bal-0.074
 laund-0.072
uka-0.072
Token g
Token ID308
Feature activation-4.88e-02

Pos logit contributions
 bal+0.103
 Tyler+0.099
 Seth+0.097
ird+0.095
 Sel+0.093
Neg logit contributions
rog-0.090
arium-0.089
acle-0.088
Buzz-0.085
beard-0.080
Token
Token ID198
Feature activation-3.43e-02

Pos logit contributions
cest+0.075
 bal+0.073
 pian+0.070
 laund+0.067
ird+0.066
Neg logit contributions
rog-0.030
acle-0.027
Buzz-0.026
 Buzz-0.025
arium-0.025
Token"
Token ID1
Feature activation-6.13e-03

Pos logit contributions
cest+0.066
 bal+0.063
 North+0.063
isc+0.061
 Es+0.061
Neg logit contributions
rog-0.033
acle-0.032
Buzz-0.029
atively-0.028
urious-0.028
TokenWe
Token ID1135
Feature activation-2.99e-02

Pos logit contributions
cest+0.010
 bal+0.010
isc+0.010
ird+0.010
 Seth+0.009
Neg logit contributions
Buzz-0.008
rog-0.008
 Buzz-0.008
 nowhere-0.007
acle-0.007
Token must
Token ID1276
Feature activation-4.89e-02

Pos logit contributions
 bal+0.042
ird+0.041
 Seth+0.040
 Tyler+0.040
isc+0.039
Neg logit contributions
rog-0.050
acle-0.049
arium-0.049
Buzz-0.047
atively-0.046
Token get
Token ID651
Feature activation-4.40e-02

Pos logit contributions
 bal+0.076
 Seth+0.075
 Tyler+0.074
ird+0.073
 laund+0.071
Neg logit contributions
rog-0.073
arium-0.070
acle-0.070
Buzz-0.067
 Buzz-0.067
Token Tyler
Token ID14886
Feature activation-4.26e-01

Pos logit contributions
 bal+0.055
 Seth+0.053
 Tyler+0.052
uka+0.051
 Sel+0.050
Neg logit contributions
rog-0.082
acle-0.080
arium-0.079
atively-0.075
Buzz-0.075
Token out
Token ID503
Feature activation-1.29e-01

Pos logit contributions
 bal+0.654
 Seth+0.634
 Tyler+0.629
ird+0.625
isc+0.607
Neg logit contributions
rog-0.654
acle-0.627
arium-0.627
Buzz-0.604
 Buzz-0.596
Token of
Token ID286
Feature activation-8.11e-02

Pos logit contributions
 bal+0.197
 Seth+0.191
 Tyler+0.189
uka+0.187
 laund+0.186
Neg logit contributions
rog-0.194
acle-0.189
arium-0.188
 Buzz-0.181
Buzz-0.177
Token the
Token ID262
Feature activation-2.40e-02

Pos logit contributions
 bal+0.139
ird+0.131
 Seth+0.130
isc+0.130
uka+0.129
Neg logit contributions
rog-0.111
acle-0.109
arium-0.108
 Buzz-0.105
Buzz-0.100
Token fire
Token ID2046
Feature activation+4.08e-02

Pos logit contributions
 bal+0.035
 Tyler+0.034
 Seth+0.034
ird+0.033
uka+0.033
Neg logit contributions
rog-0.038
acle-0.038
arium-0.038
 Buzz-0.036
Buzz-0.036
Token!"
Token ID2474
Feature activation-6.69e-02

Pos logit contributions
rog+0.063
acle+0.060
arium+0.060
Buzz+0.058
 Buzz+0.058
Neg logit contributions
 bal-0.062
 Seth-0.060
 Tyler-0.059
ird-0.058
cest-0.058
Token a
Token ID257
Feature activation+5.44e-02

Pos logit contributions
rog+0.454
acle+0.438
arium+0.430
flies+0.409
atively+0.408
Neg logit contributions
 bal-0.212
 roller-0.193
 Tyler-0.191
ird-0.190
 Seth-0.189
Token time
Token ID640
Feature activation+1.03e-02

Pos logit contributions
acle+0.103
rog+0.102
atively+0.100
flies+0.099
 Buzz+0.096
Neg logit contributions
 bal-0.065
ird-0.059
 roller-0.057
 Tyler-0.055
 pian-0.054
Token there
Token ID612
Feature activation+8.76e-02

Pos logit contributions
acle+0.019
rog+0.019
Buzz+0.019
arium+0.018
atively+0.018
Neg logit contributions
 bal-0.013
 Tyler-0.012
 Seth-0.011
ird-0.011
 Su-0.011
Token was
Token ID373
Feature activation-1.89e-02

Pos logit contributions
rog+0.110
arium+0.104
 Buzz+0.104
acle+0.102
Buzz+0.099
Neg logit contributions
 bal-0.158
 Seth-0.151
cest-0.151
ird-0.151
 laund-0.150
Token a
Token ID257
Feature activation+5.57e-02

Pos logit contributions
 bal+0.028
 Tyler+0.026
 Seth+0.026
uka+0.025
 Su+0.025
Neg logit contributions
acle-0.032
rog-0.031
arium-0.030
atively-0.030
flies-0.027
Token True
Token ID6407
Feature activation+3.11e-01

Pos logit contributions
rog+0.059
arium+0.055
Buzz+0.054
acle+0.054
 Buzz+0.053
Neg logit contributions
 bal-0.110
 Seth-0.109
 Tyler-0.108
ird-0.108
isc-0.107
Token who
Token ID508
Feature activation+1.48e-02

Pos logit contributions
rog+0.444
arium+0.423
acle+0.413
 Buzz+0.410
Buzz+0.405
Neg logit contributions
 bal-0.507
 Seth-0.505
 Tyler-0.501
ird-0.490
 laund-0.490
Token was
Token ID373
Feature activation-1.83e-02

Pos logit contributions
rog+0.024
acle+0.024
arium+0.023
atively+0.022
 Buzz+0.022
Neg logit contributions
 bal-0.022
 Seth-0.021
 Tyler-0.020
isc-0.020
uka-0.020
Token very
Token ID845
Feature activation-4.90e-02

Pos logit contributions
 bal+0.027
 Seth+0.026
 Tyler+0.026
ird+0.026
uka+0.026
Neg logit contributions
rog-0.029
acle-0.028
arium-0.027
 Buzz-0.027
Buzz-0.026
Token spoiled
Token ID34781
Feature activation-4.33e-02

Pos logit contributions
 bal+0.070
 Seth+0.066
uka+0.065
 Tyler+0.065
isc+0.063
Neg logit contributions
rog-0.081
acle-0.080
arium-0.079
atively-0.075
Buzz-0.074
Token.
Token ID13
Feature activation-8.09e-03

Pos logit contributions
uka+0.081
 Seth+0.081
ird+0.080
 Tyler+0.080
isc+0.080
Neg logit contributions
rog-0.049
 Buzz-0.046
acle-0.045
arium-0.045
Buzz-0.040
Token his
Token ID465
Feature activation-7.81e-02

Pos logit contributions
 bal+0.071
 Seth+0.069
 Tyler+0.068
uka+0.065
cest+0.065
Neg logit contributions
rog-0.084
acle-0.081
arium-0.080
Buzz-0.077
 Buzz-0.077
Token paw
Token ID41827
Feature activation-2.32e-02

Pos logit contributions
 bal+0.110
cest+0.097
 Tyler+0.095
isc+0.094
 sax+0.094
Neg logit contributions
arium-0.132
rog-0.127
Buzz-0.126
 Buzz-0.118
|-0.117
Token to
Token ID284
Feature activation+1.30e-02

Pos logit contributions
 bal+0.035
 Seth+0.031
 Tyler+0.031
cest+0.030
 Sel+0.030
Neg logit contributions
rog-0.039
arium-0.037
Buzz-0.036
acle-0.036
 Buzz-0.034
Token get
Token ID651
Feature activation-3.71e-02

Pos logit contributions
rog+0.023
arium+0.023
acle+0.022
Buzz+0.021
acky+0.021
Neg logit contributions
 Seth-0.016
 bal-0.016
 Tyler-0.016
cest-0.015
 Sel-0.015
Token the
Token ID262
Feature activation-1.42e-02

Pos logit contributions
ird+0.074
 bal+0.074
 Seth+0.073
 Tyler+0.073
 laund+0.073
Neg logit contributions
rog-0.037
 Buzz-0.036
acle-0.035
arium-0.034
Buzz-0.034
Token frog
Token ID21264
Feature activation+2.15e-01

Pos logit contributions
 bal+0.023
cest+0.021
 roller+0.020
 Super+0.020
 Seth+0.019
Neg logit contributions
rog-0.021
arium-0.021
acle-0.021
atively-0.020
agged-0.020
Token's
Token ID338
Feature activation-4.47e-02

Pos logit contributions
rog+0.371
acle+0.356
Buzz+0.351
arium+0.349
atively+0.343
Neg logit contributions
 bal-0.302
 Seth-0.269
 Tyler-0.267
cest-0.266
ird-0.254
Token attention
Token ID3241
Feature activation+4.63e-02

Pos logit contributions
 bal+0.062
isc+0.057
cest+0.056
 Seth+0.056
 roller+0.053
Neg logit contributions
arium-0.076
rog-0.076
Buzz-0.074
acle-0.070
 Buzz-0.070
Token.
Token ID13
Feature activation-8.01e-03

Pos logit contributions
rog+0.066
acle+0.064
arium+0.063
 Buzz+0.060
Buzz+0.059
Neg logit contributions
 bal-0.075
 Seth-0.073
 Tyler-0.073
ird-0.072
uka-0.072
Token
Token ID198
Feature activation-2.47e-02

Pos logit contributions
 bal+0.013
 Seth+0.012
 Tyler+0.012
ird+0.012
uka+0.012
Neg logit contributions
rog-0.012
acle-0.011
arium-0.011
 Buzz-0.011
Buzz-0.011
Token
Token ID198
Feature activation-2.51e-02

Pos logit contributions
 bal+0.039
 Seth+0.038
 Tyler+0.037
ird+0.037
cest+0.037
Neg logit contributions
rog-0.037
acle-0.035
arium-0.035
Buzz-0.034
 Buzz-0.034
Token?"
Token ID1701
Feature activation-4.75e-02

Pos logit contributions
rog+0.104
acle+0.100
atively+0.097
Buzz+0.097
arium+0.095
Neg logit contributions
 bal-0.082
ird-0.078
 Seth-0.077
cest-0.077
 Tyler-0.074
Token
Token ID198
Feature activation-1.65e-02

Pos logit contributions
 bal+0.073
 Seth+0.071
 Tyler+0.071
ird+0.069
uka+0.068
Neg logit contributions
rog-0.073
acle-0.071
arium-0.069
Buzz-0.067
 Buzz-0.066
Token
Token ID198
Feature activation-1.72e-02

Pos logit contributions
 bal+0.028
cest+0.027
 Seth+0.026
ird+0.026
 Tyler+0.026
Neg logit contributions
rog-0.023
arium-0.022
acle-0.022
Buzz-0.022
 Buzz-0.021
TokenThe
Token ID464
Feature activation-8.63e-03

Pos logit contributions
 bal+0.025
 Seth+0.024
 Tyler+0.024
ird+0.024
 laund+0.023
Neg logit contributions
rog-0.028
acle-0.027
arium-0.027
 Buzz-0.026
Buzz-0.025
Token j
Token ID474
Feature activation-1.50e-01

Pos logit contributions
 bal+0.011
 Seth+0.011
uka+0.010
 Tyler+0.010
 laund+0.010
Neg logit contributions
rog-0.016
arium-0.015
acle-0.015
 Buzz-0.014
Buzz-0.014
Tokenolly
Token ID5098
Feature activation+2.30e-01

Pos logit contributions
 bal+0.317
uka+0.291
isc+0.290
ird+0.288
 Seth+0.284
Neg logit contributions
acle-0.151
atively-0.138
 Buzz-0.136
rog-0.136
Buzz-0.132
Token man
Token ID582
Feature activation-2.66e-02

Pos logit contributions
acle+0.388
arium+0.383
rog+0.379
agged+0.354
Buzz+0.353
Neg logit contributions
 bal-0.335
 Seth-0.296
isc-0.287
 Tyler-0.284
ird-0.283
Token smiled
Token ID13541
Feature activation+1.45e-01

Pos logit contributions
 bal+0.040
ird+0.037
 Seth+0.036
 Tyler+0.036
 Sel+0.035
Neg logit contributions
rog-0.042
arium-0.040
acle-0.040
alk-0.040
Buzz-0.039
Token and
Token ID290
Feature activation+1.07e-02

Pos logit contributions
rog+0.222
acle+0.210
arium+0.209
Buzz+0.202
 Buzz+0.200
Neg logit contributions
 bal-0.227
 Seth-0.218
 Tyler-0.216
cest-0.211
ird-0.209
Token said
Token ID531
Feature activation+1.33e-03

Pos logit contributions
rog+0.014
acle+0.014
arium+0.013
 Buzz+0.013
Buzz+0.013
Neg logit contributions
 bal-0.018
ird-0.018
 Seth-0.018
uka-0.018
 Tyler-0.018
Token,
Token ID11
Feature activation-6.25e-03

Pos logit contributions
rog+0.002
acle+0.002
arium+0.002
Buzz+0.002
 Buzz+0.002
Neg logit contributions
 bal-0.002
 Seth-0.002
 Tyler-0.002
ird-0.002
uka-0.002
Token get
Token ID651
Feature activation-3.17e-02

Pos logit contributions
 bal+0.089
 Seth+0.087
cest+0.086
 Tyler+0.085
ird+0.085
Neg logit contributions
rog-0.087
arium-0.083
acle-0.082
Buzz-0.080
 Buzz-0.080
Token.
Token ID13
Feature activation-5.17e-03

Pos logit contributions
 bal+0.051
 Seth+0.050
 Tyler+0.049
uka+0.048
ird+0.048
Neg logit contributions
rog-0.046
acle-0.044
arium-0.044
 Buzz-0.042
Buzz-0.042
Token
Token ID220
Feature activation+5.15e-02

Pos logit contributions
cest+0.011
 pian+0.011
 bal+0.010
ird+0.010
 laund+0.010
Neg logit contributions
acle-0.005
arium-0.005
rog-0.005
 Buzz-0.005
 True-0.004
Token
Token ID198
Feature activation-1.98e-02

Pos logit contributions
rog+0.063
acle+0.061
 Buzz+0.060
arium+0.058
Buzz+0.057
Neg logit contributions
cest-0.092
 bal-0.092
 laund-0.089
 pian-0.089
 Seth-0.087
Token
Token ID198
Feature activation-1.98e-02

Pos logit contributions
 bal+0.037
cest+0.036
ird+0.036
 pian+0.036
 laund+0.035
Neg logit contributions
rog-0.023
Buzz-0.022
 Buzz-0.022
acle-0.022
arium-0.021
TokenTrue
Token ID17821
Feature activation+2.66e-01

Pos logit contributions
 Sel+0.038
isc+0.038
 bal+0.038
ird+0.038
cest+0.038
Neg logit contributions
rog-0.019
Buzz-0.019
acle-0.018
isy-0.017
arium-0.016
Token to
Token ID284
Feature activation+1.88e-02

Pos logit contributions
rog+0.470
acle+0.440
arium+0.434
Buzz+0.422
atively+0.409
Neg logit contributions
 bal-0.364
 Tyler-0.329
 Seth-0.328
 Sel-0.316
ird-0.316
Token his
Token ID465
Feature activation-7.09e-02

Pos logit contributions
rog+0.032
acle+0.031
arium+0.031
Buzz+0.030
 Buzz+0.030
Neg logit contributions
 bal-0.025
 Seth-0.025
 Tyler-0.024
ird-0.024
uka-0.024
Token mom
Token ID1995
Feature activation-6.42e-02

Pos logit contributions
 bal+0.090
 Tyler+0.086
 Seth+0.085
ird+0.083
cest+0.082
Neg logit contributions
rog-0.129
acle-0.123
Buzz-0.121
arium-0.121
 Buzz-0.118
Token's
Token ID338
Feature activation-3.92e-02

Pos logit contributions
 bal+0.101
 Seth+0.098
 Tyler+0.098
ird+0.096
uka+0.095
Neg logit contributions
rog-0.096
acle-0.092
arium-0.090
Buzz-0.088
 Buzz-0.087
Token words
Token ID2456
Feature activation+1.29e-01

Pos logit contributions
 bal+0.048
 roller+0.045
ird+0.044
 laund+0.044
 Tyler+0.044
Neg logit contributions
rog-0.074
Buzz-0.073
acle-0.069
arium-0.068
 Buzz-0.067
Token
Token ID198
Feature activation-3.34e-02

Pos logit contributions
 bal+0.059
cest+0.057
ird+0.056
 laund+0.055
 pian+0.055
Neg logit contributions
rog-0.042
Buzz-0.039
arium-0.038
 Buzz-0.038
acle-0.037
TokenJake
Token ID43930
Feature activation-1.35e-01

Pos logit contributions
 bal+0.056
isc+0.056
cest+0.056
ird+0.054
 Es+0.052
Neg logit contributions
rog-0.045
Buzz-0.044
arium-0.038
 Buzz-0.037
acky-0.036
Token thought
Token ID1807
Feature activation+1.71e-01

Pos logit contributions
 bal+0.201
 Tyler+0.197
 Seth+0.196
ird+0.192
 Sel+0.186
Neg logit contributions
rog-0.213
acle-0.203
arium-0.202
Buzz-0.194
 Buzz-0.193
Token for
Token ID329
Feature activation-5.39e-03

Pos logit contributions
rog+0.230
acle+0.219
arium+0.217
 Buzz+0.211
atively+0.203
Neg logit contributions
 bal-0.292
cest-0.281
 Seth-0.281
ird-0.278
 laund-0.277
Token a
Token ID257
Feature activation+4.77e-02

Pos logit contributions
 Tyler+0.008
 Seth+0.008
 Sel+0.007
uka+0.007
 roller+0.007
Neg logit contributions
rog-0.009
arium-0.009
acle-0.009
Buzz-0.009
 Buzz-0.008
Token moment
Token ID2589
Feature activation+2.60e-01

Pos logit contributions
acle+0.042
rog+0.040
arium+0.039
 Buzz+0.035
Buzz+0.035
Neg logit contributions
 bal-0.105
 Tyler-0.100
 Seth-0.099
 roller-0.099
ird-0.098
Token and
Token ID290
Feature activation-4.99e-03

Pos logit contributions
rog+0.333
acle+0.321
arium+0.314
 Buzz+0.302
atively+0.289
Neg logit contributions
 bal-0.449
 Seth-0.445
uka-0.440
isc-0.439
 laund-0.438
Token then
Token ID788
Feature activation+2.89e-02

Pos logit contributions
 bal+0.008
 Seth+0.008
 Tyler+0.008
ird+0.008
uka+0.008
Neg logit contributions
rog-0.007
acle-0.006
arium-0.006
 Buzz-0.006
Buzz-0.006
Token he
Token ID339
Feature activation-2.65e-02

Pos logit contributions
rog+0.032
 Buzz+0.032
acle+0.032
arium+0.032
atively+0.030
Neg logit contributions
 laund-0.052
isc-0.051
cest-0.050
 bal-0.049
uka-0.049
Token decided
Token ID3066
Feature activation-8.48e-02

Pos logit contributions
 bal+0.043
 Seth+0.042
 Tyler+0.042
cest+0.041
 laund+0.041
Neg logit contributions
rog-0.037
acle-0.036
arium-0.035
 Buzz-0.034
Buzz-0.034
Token to
Token ID284
Feature activation+5.60e-03

Pos logit contributions
 bal+0.143
 Seth+0.139
 Tyler+0.138
ird+0.137
uka+0.136
Neg logit contributions
rog-0.116
acle-0.113
arium-0.110
 Buzz-0.106
Buzz-0.104
Token because
Token ID780
Feature activation-6.33e-02

Pos logit contributions
rog+0.105
arium+0.101
acle+0.101
 Buzz+0.098
Buzz+0.094
Neg logit contributions
 bal-0.131
 Seth-0.130
ird-0.128
 Tyler-0.128
uka-0.128
Token her
Token ID607
Feature activation-3.83e-02

Pos logit contributions
 bal+0.095
 Seth+0.092
 Tyler+0.091
ird+0.090
isc+0.089
Neg logit contributions
rog-0.098
arium-0.094
acle-0.094
 Buzz-0.092
Buzz-0.090
Token favorite
Token ID4004
Feature activation-2.32e-02

Pos logit contributions
 bal+0.047
 Tyler+0.044
 Seth+0.044
 laund+0.043
ird+0.042
Neg logit contributions
rog-0.073
acle-0.069
Buzz-0.069
arium-0.069
 Buzz-0.067
Token toy
Token ID13373
Feature activation-1.33e-01

Pos logit contributions
 bal+0.031
 Seth+0.029
ird+0.029
 Tyler+0.029
cest+0.028
Neg logit contributions
rog-0.041
acle-0.040
arium-0.039
Buzz-0.038
 Buzz-0.038
Token had
Token ID550
Feature activation+6.22e-02

Pos logit contributions
 bal+0.214
 Seth+0.209
 Tyler+0.208
uka+0.204
ird+0.203
Neg logit contributions
rog-0.191
acle-0.185
arium-0.183
 Buzz-0.175
Buzz-0.174
Token been
Token ID587
Feature activation+6.66e-02

Pos logit contributions
acle+0.080
rog+0.078
arium+0.077
 Buzz+0.074
atively+0.073
Neg logit contributions
 bal-0.107
 Tyler-0.105
uka-0.104
 Seth-0.103
ird-0.102
Token ruined
Token ID20484
Feature activation-2.30e-02

Pos logit contributions
rog+0.089
acle+0.087
arium+0.086
 Buzz+0.082
Buzz+0.080
Neg logit contributions
 bal-0.113
 Tyler-0.110
 Seth-0.110
uka-0.108
isc-0.107
Token by
Token ID416
Feature activation+8.35e-02

Pos logit contributions
 bal+0.039
uka+0.038
 Seth+0.038
 Tyler+0.038
ird+0.037
Neg logit contributions
rog-0.030
acle-0.030
arium-0.029
 Buzz-0.029
atively-0.027
Token the
Token ID262
Feature activation-2.51e-02

Pos logit contributions
rog+0.131
acle+0.126
arium+0.126
Buzz+0.122
 Buzz+0.117
Neg logit contributions
 bal-0.124
 Seth-0.124
 Tyler-0.122
 Sel-0.118
 laund-0.117
Token rain
Token ID6290
Feature activation+2.34e-02

Pos logit contributions
 bal+0.038
 Seth+0.035
 laund+0.035
 roller+0.035
 Tyler+0.034
Neg logit contributions
rog-0.041
arium-0.039
acle-0.039
Buzz-0.037
 Buzz-0.037
Token.
Token ID13
Feature activation-1.56e-02

Pos logit contributions
rog+0.032
acle+0.031
arium+0.030
 Buzz+0.029
atively+0.028
Neg logit contributions
 bal-0.039
uka-0.038
 Seth-0.038
 Tyler-0.038
 Sel-0.037
Tokendrops
Token ID49253
Feature activation-1.20e-01

Pos logit contributions
rog+0.041
acle+0.039
arium+0.039
Buzz+0.038
 Buzz+0.037
Neg logit contributions
 bal-0.038
 Seth-0.036
 Tyler-0.036
 laund-0.035
ird-0.035
Token falling
Token ID7463
Feature activation-1.11e-01

Pos logit contributions
 bal+0.159
 Seth+0.154
 Tyler+0.153
uka+0.150
ird+0.150
Neg logit contributions
rog-0.205
acle-0.200
arium-0.197
 Buzz-0.192
Buzz-0.190
Token from
Token ID422
Feature activation-1.39e-01

Pos logit contributions
 bal+0.173
uka+0.172
ird+0.172
 Tyler+0.170
 Seth+0.169
Neg logit contributions
rog-0.162
acle-0.159
arium-0.153
 Buzz-0.152
atively-0.148
Token the
Token ID262
Feature activation-3.73e-02

Pos logit contributions
 bal+0.203
 Seth+0.198
 Tyler+0.196
 laund+0.190
uka+0.190
Neg logit contributions
rog-0.223
acle-0.216
arium-0.211
Buzz-0.204
 Buzz-0.200
Token sky
Token ID6766
Feature activation+3.58e-02

Pos logit contributions
 bal+0.065
 Tyler+0.064
 Seth+0.064
uka+0.063
ird+0.063
Neg logit contributions
rog-0.048
acle-0.047
arium-0.045
 Buzz-0.044
Buzz-0.044
Token and
Token ID290
Feature activation+6.83e-03

Pos logit contributions
rog+0.053
acle+0.051
arium+0.050
 Buzz+0.048
Buzz+0.048
Neg logit contributions
 bal-0.056
 Seth-0.055
 Tyler-0.055
ird-0.054
uka-0.053
Token she
Token ID673
Feature activation-2.59e-02

Pos logit contributions
rog+0.012
acle+0.011
arium+0.011
Buzz+0.010
atively+0.010
Neg logit contributions
 bal-0.010
 Seth-0.009
 Tyler-0.009
 Sel-0.009
 laund-0.009
Token wanted
Token ID2227
Feature activation+3.07e-02

Pos logit contributions
 bal+0.038
 Seth+0.035
ird+0.035
 Tyler+0.035
 Sel+0.034
Neg logit contributions
rog-0.043
acle-0.043
arium-0.042
 Buzz-0.038
Buzz-0.038
Token to
Token ID284
Feature activation+1.14e-02

Pos logit contributions
rog+0.043
acle+0.041
arium+0.041
 Buzz+0.039
Buzz+0.039
Neg logit contributions
 bal-0.051
 Seth-0.050
 Tyler-0.049
ird-0.048
uka-0.048
Token catch
Token ID4929
Feature activation+9.03e-03

Pos logit contributions
rog+0.017
acle+0.017
arium+0.016
 Buzz+0.016
Buzz+0.016
Neg logit contributions
 bal-0.018
 Seth-0.017
 Tyler-0.017
ird-0.017
uka-0.017
Token one
Token ID530
Feature activation+4.43e-02

Pos logit contributions
rog+0.013
acle+0.012
arium+0.012
 Buzz+0.012
Buzz+0.012
Neg logit contributions
 bal-0.015
 Seth-0.014
 Tyler-0.014
ird-0.014
uka-0.014
Token for
Token ID329
Feature activation-4.17e-04

Pos logit contributions
 Seth+0.194
uka+0.193
 bal+0.193
 Tyler+0.192
 laund+0.187
Neg logit contributions
rog-0.158
acle-0.151
arium-0.151
 Buzz-0.146
Buzz-0.137
Token them
Token ID606
Feature activation+7.56e-02

Pos logit contributions
 bal+0.001
 Seth+0.001
 Tyler+0.001
ird+0.001
uka+0.001
Neg logit contributions
rog-0.001
acle-0.001
arium-0.001
Buzz-0.001
 Buzz-0.001
Token.
Token ID13
Feature activation-1.37e-03

Pos logit contributions
rog+0.114
acle+0.110
arium+0.109
 Buzz+0.105
Buzz+0.104
Neg logit contributions
 bal-0.117
 Seth-0.113
 Tyler-0.112
ird-0.110
uka-0.110
Token She
Token ID1375
Feature activation+1.77e-02

Pos logit contributions
cest+0.003
 bal+0.003
 laund+0.003
ird+0.002
 roller+0.002
Neg logit contributions
 Buzz-0.002
rog-0.001
arium-0.001
acle-0.001
Buzz-0.001
Token says
Token ID1139
Feature activation-1.91e-02

Pos logit contributions
rog+0.029
acle+0.028
arium+0.028
Buzz+0.027
 Buzz+0.027
Neg logit contributions
 bal-0.026
 Seth-0.025
 Tyler-0.025
ird-0.024
uka-0.024
Token some
Token ID617
Feature activation+8.37e-02

Pos logit contributions
 bal+0.030
 Seth+0.029
 Tyler+0.029
ird+0.028
uka+0.028
Neg logit contributions
rog-0.029
acle-0.028
arium-0.027
Buzz-0.026
 Buzz-0.026
Token dogs
Token ID6844
Feature activation-6.16e-02

Pos logit contributions
rog+0.126
acle+0.124
arium+0.122
Buzz+0.115
 Buzz+0.115
Neg logit contributions
 bal-0.131
 Seth-0.126
 Tyler-0.125
ird-0.123
 laund-0.121
Token are
Token ID389
Feature activation-1.13e-02

Pos logit contributions
 bal+0.084
 Seth+0.082
 Tyler+0.082
ird+0.079
cest+0.078
Neg logit contributions
rog-0.102
acle-0.100
arium-0.098
Buzz-0.095
atively-0.094
Token too
Token ID1165
Feature activation+1.51e-01

Pos logit contributions
 bal+0.019
 Seth+0.018
 Tyler+0.018
ird+0.018
uka+0.018
Neg logit contributions
rog-0.016
acle-0.015
arium-0.015
 Buzz-0.014
Buzz-0.014
Token big
Token ID1263
Feature activation-7.33e-02

Pos logit contributions
rog+0.223
acle+0.214
arium+0.212
 Buzz+0.204
Buzz+0.203
Neg logit contributions
 bal-0.239
 Seth-0.232
 Tyler-0.231
ird-0.227
uka-0.226
Token or
Token ID393
Feature activation-1.19e-01

Pos logit contributions
 Seth+0.135
 bal+0.134
uka+0.133
 Tyler+0.132
 laund+0.132
Neg logit contributions
arium-0.084
rog-0.083
acle-0.081
 Buzz-0.079
Buzz-0.071
Token twisted
Token ID19074
Feature activation-6.21e-02

Pos logit contributions
ird+0.098
 bal+0.096
 Tyler+0.091
 Seth+0.091
 Sel+0.088
Neg logit contributions
rog-0.104
arium-0.101
acle-0.095
 Buzz-0.095
Buzz-0.094
Token the
Token ID262
Feature activation-1.25e-02

Pos logit contributions
 bal+0.100
 Seth+0.096
ird+0.096
 Tyler+0.095
uka+0.095
Neg logit contributions
rog-0.091
acle-0.088
arium-0.087
 Buzz-0.084
Buzz-0.083
Token balloon
Token ID21190
Feature activation+3.46e-03

Pos logit contributions
 roller+0.015
 bal+0.014
cest+0.014
ird+0.014
 laund+0.014
Neg logit contributions
rog-0.024
Buzz-0.023
acky-0.023
 Buzz-0.022
arium-0.022
Token very
Token ID845
Feature activation-4.39e-02

Pos logit contributions
rog+0.005
arium+0.005
acle+0.005
Buzz+0.005
 Buzz+0.005
Neg logit contributions
 bal-0.005
 Seth-0.005
 Tyler-0.005
ird-0.005
cest-0.005
Token fast
Token ID3049
Feature activation+4.74e-03

Pos logit contributions
 bal+0.068
 Seth+0.061
 Sel+0.060
 Tyler+0.060
 Es+0.060
Neg logit contributions
arium-0.066
rog-0.065
acle-0.063
Buzz-0.058
 Buzz-0.058
Token and
Token ID290
Feature activation+1.15e-02

Pos logit contributions
rog+0.007
acle+0.007
arium+0.007
 Buzz+0.006
Buzz+0.006
Neg logit contributions
 bal-0.008
 Seth-0.007
 Tyler-0.007
uka-0.007
ird-0.007
Token very
Token ID845
Feature activation-4.39e-02

Pos logit contributions
acle+0.015
 Buzz+0.014
rog+0.013
arium+0.013
atively+0.013
Neg logit contributions
uka-0.020
 bal-0.020
ird-0.020
isc-0.020
 laund-0.020
Token hard
Token ID1327
Feature activation+9.19e-02

Pos logit contributions
 bal+0.074
 Seth+0.070
 Tyler+0.070
ird+0.068
cest+0.068
Neg logit contributions
rog-0.062
arium-0.059
acle-0.058
Buzz-0.056
 Buzz-0.055
Token.
Token ID13
Feature activation+4.28e-03

Pos logit contributions
rog+0.144
acle+0.138
arium+0.137
Buzz+0.132
 Buzz+0.132
Neg logit contributions
 bal-0.138
 Seth-0.134
 Tyler-0.133
ird-0.130
uka-0.129
Token They
Token ID1119
Feature activation+8.05e-02

Pos logit contributions
rog+0.005
acle+0.005
arium+0.005
 Buzz+0.005
Buzz+0.004
Neg logit contributions
 bal-0.008
 Seth-0.008
 Tyler-0.008
ird-0.008
uka-0.008
Token made
Token ID925
Feature activation-1.28e-01

Pos logit contributions
rog+0.101
acle+0.099
arium+0.095
Buzz+0.093
 Buzz+0.093
Neg logit contributions
 bal-0.143
 Seth-0.139
isc-0.137
 Tyler-0.137
cest-0.137
Token way
Token ID835
Feature activation-1.43e-01

Pos logit contributions
 bal+0.028
 Seth+0.028
 Tyler+0.027
ird+0.027
uka+0.027
Neg logit contributions
rog-0.027
arium-0.026
acle-0.026
 Buzz-0.025
Buzz-0.025
Token,
Token ID11
Feature activation-1.61e-02

Pos logit contributions
 bal+0.221
 Seth+0.215
 Tyler+0.213
ird+0.209
uka+0.208
Neg logit contributions
rog-0.215
acle-0.207
arium-0.204
 Buzz-0.197
Buzz-0.196
Token the
Token ID262
Feature activation-3.39e-02

Pos logit contributions
 bal+0.026
ird+0.025
 Seth+0.025
 Tyler+0.025
uka+0.025
Neg logit contributions
rog-0.023
 Buzz-0.022
arium-0.022
acle-0.022
Buzz-0.021
Token bird
Token ID6512
Feature activation+6.83e-02

Pos logit contributions
 bal+0.047
 roller+0.043
 laund+0.042
ird+0.042
 Seth+0.041
Neg logit contributions
rog-0.062
arium-0.060
acle-0.058
beard-0.056
Buzz-0.056
Token could
Token ID714
Feature activation-1.09e-01

Pos logit contributions
rog+0.106
acle+0.102
arium+0.101
Buzz+0.097
 Buzz+0.097
Neg logit contributions
 bal-0.104
 Seth-0.099
 Tyler-0.098
ird-0.097
cest-0.096
Token stay
Token ID2652
Feature activation+8.74e-03

Pos logit contributions
 bal+0.150
 Seth+0.145
 Tyler+0.143
ird+0.142
 Sel+0.137
Neg logit contributions
rog-0.184
arium-0.177
acle-0.173
Buzz-0.169
 Buzz-0.165
Token for
Token ID329
Feature activation-1.00e-02

Pos logit contributions
rog+0.012
acle+0.012
arium+0.012
 Buzz+0.011
Buzz+0.011
Neg logit contributions
 bal-0.015
 Seth-0.014
 Tyler-0.014
ird-0.014
uka-0.014
Token longer
Token ID2392
Feature activation+1.11e-02

Pos logit contributions
 bal+0.015
 Seth+0.014
 Tyler+0.014
ird+0.014
 Sel+0.014
Neg logit contributions
rog-0.016
acle-0.016
arium-0.015
Buzz-0.015
atively-0.015
Token and
Token ID290
Feature activation-1.81e-03

Pos logit contributions
rog+0.016
acle+0.015
arium+0.015
 Buzz+0.015
Buzz+0.014
Neg logit contributions
 bal-0.018
 Seth-0.018
 Tyler-0.017
uka-0.017
isc-0.017
Token have
Token ID423
Feature activation+2.23e-02

Pos logit contributions
 bal+0.003
 Seth+0.003
 Tyler+0.003
ird+0.003
uka+0.003
Neg logit contributions
rog-0.003
acle-0.003
arium-0.003
Buzz-0.003
 Buzz-0.002
Token a
Token ID257
Feature activation+5.27e-02

Pos logit contributions
rog+0.036
acle+0.035
arium+0.034
Buzz+0.033
atively+0.032
Neg logit contributions
 bal-0.032
 Seth-0.032
 Tyler-0.031
ird-0.031
 laund-0.030
Token years
Token ID812
Feature activation+1.23e-01

Pos logit contributions
rog+0.035
arium+0.031
acle+0.029
Buzz+0.029
 Buzz+0.028
Neg logit contributions
 Seth-0.096
 Tyler-0.096
isc-0.095
 bal-0.095
uka-0.094
Token old
Token ID1468
Feature activation+6.96e-02

Pos logit contributions
rog+0.140
acle+0.133
arium+0.131
 Buzz+0.124
Buzz+0.124
Neg logit contributions
 bal-0.237
 Seth-0.232
 Tyler-0.231
ird-0.227
uka-0.226
Token.
Token ID13
Feature activation-2.16e-03

Pos logit contributions
rog+0.078
 Buzz+0.069
acle+0.068
arium+0.066
Buzz+0.064
Neg logit contributions
 bal-0.129
uka-0.129
 Seth-0.129
isc-0.128
ird-0.128
Token One
Token ID1881
Feature activation+1.11e-01

Pos logit contributions
 bal+0.004
cest+0.004
ird+0.004
 laund+0.004
 Seth+0.004
Neg logit contributions
rog-0.003
acle-0.003
arium-0.003
 Buzz-0.002
Buzz-0.002
Token day
Token ID1110
Feature activation+3.03e-02

Pos logit contributions
rog+0.159
acle+0.154
arium+0.151
 Buzz+0.145
Buzz+0.145
Neg logit contributions
 bal-0.183
 Seth-0.177
 Tyler-0.176
ird-0.173
uka-0.172
Token he
Token ID339
Feature activation-2.28e-02

Pos logit contributions
rog+0.031
acle+0.029
arium+0.029
 Buzz+0.028
atively+0.028
Neg logit contributions
isc-0.059
 laund-0.059
 North-0.058
cest-0.058
 pian-0.058
Token was
Token ID373
Feature activation-1.28e-02

Pos logit contributions
 bal+0.036
 Seth+0.036
 Tyler+0.035
ird+0.035
 Sel+0.035
Neg logit contributions
rog-0.032
arium-0.032
acle-0.031
Buzz-0.030
 Buzz-0.030
Token walking
Token ID6155
Feature activation+8.52e-02

Pos logit contributions
 bal+0.020
 Seth+0.020
 Tyler+0.020
cest+0.020
isc+0.020
Neg logit contributions
rog-0.018
acle-0.017
arium-0.017
 Buzz-0.017
Buzz-0.016
Token around
Token ID1088
Feature activation+3.27e-02

Pos logit contributions
acle+0.139
rog+0.136
arium+0.134
Buzz+0.128
atively+0.125
Neg logit contributions
 bal-0.126
 Seth-0.117
 Tyler-0.115
cest-0.113
 Sel-0.112
Token the
Token ID262
Feature activation-1.55e-02

Pos logit contributions
rog+0.058
acle+0.058
Buzz+0.055
arium+0.054
atively+0.054
Neg logit contributions
 Tyler-0.041
 bal-0.041
 Seth-0.040
 Sel-0.039
uka-0.039
Token city
Token ID1748
Feature activation-1.00e-01

Pos logit contributions
 bal+0.026
ird+0.026
 Seth+0.026
 Tyler+0.026
isc+0.025
Neg logit contributions
rog-0.021
arium-0.021
acle-0.020
Buzz-0.019
 Buzz-0.019
Token told
Token ID1297
Feature activation-6.19e-02

Pos logit contributions
 bal+0.093
 Seth+0.090
isc+0.090
uka+0.089
 Tyler+0.089
Neg logit contributions
rog-0.064
acle-0.060
 Buzz-0.060
arium-0.060
Buzz-0.057
Token everyone
Token ID2506
Feature activation-4.51e-02

Pos logit contributions
 bal+0.095
 Seth+0.092
 Tyler+0.090
 Sel+0.089
 laund+0.087
Neg logit contributions
rog-0.096
acle-0.096
arium-0.095
Buzz-0.087
atively-0.086
Token what
Token ID644
Feature activation+5.33e-02

Pos logit contributions
 bal+0.068
 Tyler+0.065
 Seth+0.065
 Sel+0.063
cest+0.063
Neg logit contributions
acle-0.070
rog-0.070
arium-0.066
Buzz-0.065
atively-0.064
Token to
Token ID284
Feature activation+1.28e-02

Pos logit contributions
rog+0.066
 Buzz+0.065
Buzz+0.062
arium+0.062
 True+0.058
Neg logit contributions
isc-0.095
 Seth-0.094
 bal-0.094
 Tyler-0.093
cest-0.092
Token do
Token ID466
Feature activation-1.31e-02

Pos logit contributions
rog+0.019
acle+0.018
arium+0.018
 Buzz+0.017
Buzz+0.017
Neg logit contributions
 bal-0.020
 Seth-0.020
 Tyler-0.020
ird-0.019
uka-0.019
Token.
Token ID13
Feature activation-8.91e-03

Pos logit contributions
 Seth+0.023
 bal+0.023
 Tyler+0.022
isc+0.022
uka+0.022
Neg logit contributions
rog-0.017
arium-0.017
acle-0.016
 Buzz-0.015
Buzz-0.015
Token One
Token ID1881
Feature activation+1.09e-01

Pos logit contributions
 Sel+0.013
 Seth+0.012
 Tyler+0.012
 bal+0.012
 Es+0.012
Neg logit contributions
acle-0.014
rog-0.014
arium-0.013
atively-0.013
Buzz-0.013
Token day
Token ID1110
Feature activation+2.58e-02

Pos logit contributions
acle+0.206
atively+0.193
rog+0.191
arium+0.182
Buzz+0.178
Neg logit contributions
 bal-0.147
cest-0.128
uka-0.124
ird-0.124
 Seth-0.122
Token,
Token ID11
Feature activation-5.80e-03

Pos logit contributions
rog+0.033
 Buzz+0.031
arium+0.031
acle+0.030
Buzz+0.030
Neg logit contributions
 Seth-0.045
 bal-0.044
 Tyler-0.044
cest-0.044
uka-0.044
Token she
Token ID673
Feature activation-2.74e-02

Pos logit contributions
 bal+0.007
 Sel+0.007
 Seth+0.006
 Es+0.006
 Tyler+0.006
Neg logit contributions
acle-0.011
rog-0.011
arium-0.010
beard-0.010
alk-0.010
Token decided
Token ID3066
Feature activation-8.69e-02

Pos logit contributions
 bal+0.048
 Seth+0.047
 Tyler+0.047
 Sel+0.046
isc+0.046
Neg logit contributions
arium-0.035
rog-0.035
acle-0.033
Buzz-0.033
 Buzz-0.032
Token stories
Token ID3923
Feature activation+1.18e-01

Pos logit contributions
 bal+0.042
 pian+0.038
 laund+0.038
cest+0.037
 roller+0.037
Neg logit contributions
acle-0.046
rog-0.045
arium-0.043
Buzz-0.042
atively-0.042
Token with
Token ID351
Feature activation-1.75e-03

Pos logit contributions
acle+0.153
rog+0.151
arium+0.149
 Buzz+0.140
atively+0.139
Neg logit contributions
 Seth-0.203
 bal-0.201
uka-0.199
 Tyler-0.199
 laund-0.195
Token her
Token ID607
Feature activation-3.55e-02

Pos logit contributions
 bal+0.003
 Seth+0.003
cest+0.003
ird+0.003
 Tyler+0.003
Neg logit contributions
rog-0.002
acle-0.002
arium-0.002
 Buzz-0.002
Buzz-0.002
Token mom
Token ID1995
Feature activation-7.08e-02

Pos logit contributions
 bal+0.052
 Tyler+0.050
 Seth+0.049
ird+0.048
 Sel+0.048
Neg logit contributions
rog-0.057
acle-0.055
arium-0.054
Buzz-0.053
 Buzz-0.052
Token and
Token ID290
Feature activation+1.92e-04

Pos logit contributions
 bal+0.123
 Seth+0.120
uka+0.118
 laund+0.118
 Tyler+0.117
Neg logit contributions
rog-0.091
arium-0.088
acle-0.088
 Buzz-0.084
Buzz-0.078
Token dad
Token ID9955
Feature activation-1.03e-01

Pos logit contributions
 Buzz+0.000
arium+0.000
rog+0.000
acle+0.000
 Marie+0.000
Neg logit contributions
 bal-0.000
ird-0.000
isc-0.000
uka-0.000
 Seth-0.000
Token and
Token ID290
Feature activation+1.12e-03

Pos logit contributions
 bal+0.162
 Seth+0.158
 Tyler+0.157
ird+0.153
uka+0.153
Neg logit contributions
rog-0.152
acle-0.147
arium-0.145
 Buzz-0.139
Buzz-0.138
Token they
Token ID484
Feature activation+2.99e-02

Pos logit contributions
 Buzz+0.001
rog+0.001
arium+0.001
acle+0.001
atively+0.001
Neg logit contributions
 bal-0.002
uka-0.002
isc-0.002
 Seth-0.002
 laund-0.002
Token praised
Token ID15342
Feature activation-1.17e-01

Pos logit contributions
rog+0.036
acle+0.035
arium+0.035
 Buzz+0.034
Buzz+0.033
Neg logit contributions
 bal-0.055
 Seth-0.053
 Tyler-0.052
uka-0.052
cest-0.052
Token her
Token ID607
Feature activation-3.25e-02

Pos logit contributions
 Tyler+0.159
 bal+0.157
 Seth+0.157
 Sel+0.154
 Es+0.147
Neg logit contributions
rog-0.198
acle-0.196
arium-0.195
Buzz-0.185
atively-0.176
Token for
Token ID329
Feature activation-6.12e-03

Pos logit contributions
 bal+0.051
 Seth+0.049
 Tyler+0.049
ird+0.048
uka+0.048
Neg logit contributions
rog-0.049
acle-0.047
arium-0.046
Buzz-0.045
 Buzz-0.044
Token day
Token ID1110
Feature activation+3.50e-02

Pos logit contributions
rog+0.150
arium+0.140
acle+0.134
 Buzz+0.132
Buzz+0.132
Neg logit contributions
 Seth-0.217
 Tyler-0.217
 bal-0.214
ird-0.210
uka-0.209
Token,
Token ID11
Feature activation+2.35e-03

Pos logit contributions
rog+0.042
 Buzz+0.040
arium+0.039
acle+0.038
Buzz+0.037
Neg logit contributions
 Seth-0.063
isc-0.062
 bal-0.062
 Tyler-0.062
uka-0.062
Token a
Token ID257
Feature activation+6.55e-02

Pos logit contributions
rog+0.004
acle+0.004
arium+0.004
Buzz+0.004
 Buzz+0.003
Neg logit contributions
 bal-0.003
 Seth-0.003
 Tyler-0.003
uka-0.003
 Sel-0.003
Token man
Token ID582
Feature activation-2.48e-02

Pos logit contributions
rog+0.065
arium+0.060
Buzz+0.058
acle+0.058
 Buzz+0.057
Neg logit contributions
 Seth-0.134
 Tyler-0.132
isc-0.131
ird-0.128
 bal-0.128
Token with
Token ID351
Feature activation+2.02e-02

Pos logit contributions
 bal+0.040
 Tyler+0.040
 Seth+0.040
isc+0.039
uka+0.039
Neg logit contributions
rog-0.034
arium-0.034
acle-0.032
 Buzz-0.032
Buzz-0.032
Token an
Token ID281
Feature activation-4.07e-02

Pos logit contributions
rog+0.025
acle+0.024
arium+0.023
 Buzz+0.023
Buzz+0.023
Neg logit contributions
 bal-0.036
 Seth-0.035
 Tyler-0.035
ird-0.035
 laund-0.035
Token ugly
Token ID13400
Feature activation+1.90e-02

Pos logit contributions
 Tyler+0.069
 bal+0.069
 Seth+0.069
uka+0.067
ird+0.066
Neg logit contributions
rog-0.054
acle-0.051
arium-0.049
 Buzz-0.048
atively-0.046
Token face
Token ID1986
Feature activation+9.81e-02

Pos logit contributions
rog+0.029
acle+0.028
arium+0.027
 Buzz+0.026
atively+0.026
Neg logit contributions
 Seth-0.028
 Tyler-0.028
 bal-0.028
uka-0.027
isc-0.027
Token came
Token ID1625
Feature activation-1.95e-02

Pos logit contributions
rog+0.109
acle+0.105
 Buzz+0.102
arium+0.101
atively+0.098
Neg logit contributions
 Tyler-0.181
uka-0.177
 Seth-0.176
isc-0.175
 laund-0.170
Token to
Token ID284
Feature activation+2.32e-02

Pos logit contributions
 bal+0.031
 Seth+0.030
 Tyler+0.030
ird+0.029
uka+0.029
Neg logit contributions
rog-0.029
acle-0.028
arium-0.027
 Buzz-0.026
Buzz-0.026
Token the
Token ID262
Feature activation-1.39e-02

Pos logit contributions
rog+0.035
acle+0.034
arium+0.033
Buzz+0.032
 Buzz+0.032
Neg logit contributions
 bal-0.036
 Seth-0.035
 Tyler-0.035
ird-0.034
uka-0.034
Token him
Token ID683
Feature activation+2.86e-02

Pos logit contributions
 bal+0.016
uka+0.016
 Tyler+0.016
 laund+0.016
 Seth+0.016
Neg logit contributions
rog-0.012
acle-0.011
 Buzz-0.011
arium-0.010
Buzz-0.010
Token to
Token ID284
Feature activation+1.30e-03

Pos logit contributions
rog+0.042
acle+0.040
arium+0.040
 Buzz+0.038
Buzz+0.038
Neg logit contributions
 bal-0.045
 Seth-0.044
 Tyler-0.044
ird-0.043
uka-0.042
Token wipe
Token ID19916
Feature activation-3.21e-02

Pos logit contributions
rog+0.002
 Buzz+0.002
arium+0.002
acle+0.001
Buzz+0.001
Neg logit contributions
 bal-0.002
isc-0.002
uka-0.002
 laund-0.002
ird-0.002
Token it
Token ID340
Feature activation-3.90e-02

Pos logit contributions
ird+0.067
 pian+0.064
 bal+0.063
 laund+0.063
isc+0.062
Neg logit contributions
rog-0.031
 Buzz-0.028
acle-0.027
ly-0.027
 itself-0.027
Token off
Token ID572
Feature activation-1.93e-01

Pos logit contributions
 bal+0.063
 Seth+0.063
 Tyler+0.063
uka+0.062
ird+0.061
Neg logit contributions
rog-0.054
acle-0.053
arium-0.051
 Buzz-0.050
Buzz-0.049
Token.
Token ID13
Feature activation-1.38e-02

Pos logit contributions
 bal+0.332
uka+0.326
 Seth+0.324
ird+0.323
 Tyler+0.322
Neg logit contributions
rog-0.255
acle-0.253
arium-0.244
 Buzz-0.242
Buzz-0.228
Token
Token ID198
Feature activation-3.15e-02

Pos logit contributions
cest+0.025
 bal+0.025
ird+0.024
 laund+0.024
 Seth+0.024
Neg logit contributions
rog-0.017
 Buzz-0.016
acle-0.016
arium-0.016
Buzz-0.015
Token
Token ID198
Feature activation-3.08e-02

Pos logit contributions
 bal+0.052
 Seth+0.051
 Tyler+0.050
ird+0.050
cest+0.049
Neg logit contributions
rog-0.044
acle-0.042
arium-0.042
Buzz-0.040
 Buzz-0.040
TokenThe
Token ID464
Feature activation-1.88e-02

Pos logit contributions
 bal+0.049
 Seth+0.048
 Tyler+0.048
ird+0.047
uka+0.046
Neg logit contributions
rog-0.045
acle-0.043
arium-0.043
Buzz-0.042
 Buzz-0.041
Token little
Token ID1310
Feature activation+8.38e-02

Pos logit contributions
 bal+0.032
 roller+0.029
 Seth+0.029
 laund+0.029
isc+0.028
Neg logit contributions
rog-0.028
arium-0.027
acle-0.027
 Buzz-0.026
Buzz-0.025
Token boy
Token ID2933
Feature activation+2.23e-02

Pos logit contributions
acle+0.159
rog+0.156
arium+0.154
atively+0.150
Buzz+0.148
Neg logit contributions
 bal-0.108
 Seth-0.098
cest-0.097
 Ther-0.093
 roller-0.092
Token could
Token ID714
Feature activation-1.06e-01

Pos logit contributions
 bal+0.041
 Seth+0.039
 Tyler+0.039
ird+0.039
uka+0.038
Neg logit contributions
rog-0.054
acle-0.052
arium-0.052
 Buzz-0.050
Buzz-0.050
Token talk
Token ID1561
Feature activation+9.55e-02

Pos logit contributions
 bal+0.170
 Seth+0.165
 Tyler+0.165
uka+0.163
cest+0.162
Neg logit contributions
rog-0.154
acle-0.150
arium-0.143
 Buzz-0.142
Buzz-0.140
Token to
Token ID284
Feature activation+7.94e-03

Pos logit contributions
rog+0.110
acle+0.108
arium+0.107
 Buzz+0.103
atively+0.098
Neg logit contributions
uka-0.175
 bal-0.174
isc-0.173
 Seth-0.173
 Tyler-0.171
Token her
Token ID607
Feature activation-4.05e-02

Pos logit contributions
rog+0.010
 Buzz+0.010
arium+0.010
acle+0.009
Buzz+0.009
Neg logit contributions
 bal-0.014
isc-0.013
cest-0.013
 laund-0.013
uka-0.013
Token friends
Token ID2460
Feature activation-2.53e-03

Pos logit contributions
 bal+0.064
uka+0.064
 Seth+0.063
ird+0.062
 Tyler+0.061
Neg logit contributions
rog-0.056
arium-0.055
acle-0.054
 Buzz-0.053
atively-0.050
Token even
Token ID772
Feature activation-2.23e-01

Pos logit contributions
 bal+0.004
 Seth+0.004
 Tyler+0.004
uka+0.004
isc+0.004
Neg logit contributions
rog-0.004
acle-0.003
arium-0.003
 Buzz-0.003
Buzz-0.003
Token longer
Token ID2392
Feature activation+1.39e-02

Pos logit contributions
 bal+0.345
 Seth+0.336
 Tyler+0.334
ird+0.327
uka+0.325
Neg logit contributions
rog-0.336
acle-0.323
arium-0.320
 Buzz-0.308
Buzz-0.307
Token.
Token ID13
Feature activation-1.48e-02

Pos logit contributions
rog+0.021
acle+0.020
arium+0.020
 Buzz+0.019
Buzz+0.019
Neg logit contributions
 bal-0.021
 Seth-0.021
 Tyler-0.021
uka-0.020
ird-0.020
Token So
Token ID1406
Feature activation+2.20e-02

Pos logit contributions
 bal+0.020
 Tyler+0.020
 Seth+0.020
 Sel+0.019
ird+0.019
Neg logit contributions
rog-0.025
acle-0.025
arium-0.023
Buzz-0.023
atively-0.022
Token she
Token ID673
Feature activation-3.12e-02

Pos logit contributions
rog+0.032
acle+0.031
arium+0.031
 Buzz+0.030
Buzz+0.029
Neg logit contributions
 bal-0.035
 Seth-0.034
 Tyler-0.034
ird-0.034
uka-0.034
Token decided
Token ID3066
Feature activation-8.90e-02

Pos logit contributions
 bal+0.047
 Seth+0.046
 Tyler+0.046
uka+0.045
ird+0.045
Neg logit contributions
rog-0.048
acle-0.046
arium-0.046
Buzz-0.044
 Buzz-0.044
Token agreed
Token ID4987
Feature activation+1.53e-01

Pos logit contributions
 bal+0.057
 Seth+0.055
 Tyler+0.055
ird+0.055
 Sel+0.053
Neg logit contributions
rog-0.059
acle-0.056
arium-0.055
Buzz-0.053
 Buzz-0.053
Token and
Token ID290
Feature activation-5.04e-03

Pos logit contributions
rog+0.226
acle+0.217
arium+0.215
Buzz+0.207
 Buzz+0.206
Neg logit contributions
 bal-0.244
 Seth-0.237
 Tyler-0.236
ird-0.230
uka-0.228
Token kindly
Token ID26820
Feature activation+1.83e-01

Pos logit contributions
 bal+0.009
cest+0.009
 pian+0.009
 laund+0.009
uka+0.009
Neg logit contributions
 Buzz-0.006
rog-0.006
arium-0.006
acle-0.006
atively-0.005
Token gave
Token ID2921
Feature activation-1.12e-01

Pos logit contributions
acle+0.250
rog+0.249
arium+0.237
atively+0.233
 Buzz+0.232
Neg logit contributions
 bal-0.301
uka-0.293
 Seth-0.291
 Tyler-0.288
isc-0.287
Token Little
Token ID7703
Feature activation-1.98e-01

Pos logit contributions
 bal+0.172
cest+0.170
ird+0.165
 pian+0.157
 laund+0.155
Neg logit contributions
rog-0.170
arium-0.157
 Buzz-0.156
acle-0.152
beard-0.148
Token Johnny
Token ID15470
Feature activation-2.57e-01

Pos logit contributions
 bal+0.162
ird+0.148
 Seth+0.145
cest+0.144
uka+0.143
Neg logit contributions
rog-0.442
acle-0.429
arium-0.423
 Buzz-0.413
Buzz-0.409
Token the
Token ID262
Feature activation-1.87e-02

Pos logit contributions
 bal+0.415
 Seth+0.401
 Tyler+0.400
isc+0.387
uka+0.387
Neg logit contributions
rog-0.375
acle-0.363
arium-0.357
Buzz-0.345
 Buzz-0.340
Token zipper
Token ID48992
Feature activation-2.48e-01

Pos logit contributions
 bal+0.023
 Seth+0.022
 Tyler+0.022
uka+0.022
ird+0.022
Neg logit contributions
rog-0.033
acle-0.032
arium-0.031
atively-0.030
 Buzz-0.030
Token.
Token ID13
Feature activation-2.33e-02

Pos logit contributions
 bal+0.388
 Seth+0.375
 Tyler+0.373
ird+0.367
uka+0.362
Neg logit contributions
rog-0.372
acle-0.355
arium-0.353
Buzz-0.341
 Buzz-0.340
Token
Token ID220
Feature activation+3.99e-02

Pos logit contributions
cest+0.048
 bal+0.046
 pian+0.044
 hairst+0.043
 sax+0.043
Neg logit contributions
 Buzz-0.021
rog-0.021
acle-0.021
arium-0.020
 Freddie-0.019
Token
Token ID198
Feature activation-3.47e-02

Pos logit contributions
rog+0.047
acle+0.045
 Buzz+0.044
arium+0.043
Buzz+0.041
Neg logit contributions
 bal-0.074
cest-0.073
 pian-0.072
 laund-0.071
 roller-0.069
Token Grand
Token ID5675
Feature activation-3.10e-01

Pos logit contributions
 bal+0.031
cest+0.031
isc+0.031
ird+0.031
uka+0.030
Neg logit contributions
 Buzz-0.024
rog-0.024
arium-0.023
acle-0.023
Buzz-0.022
Tokenma
Token ID2611
Feature activation+3.77e-02

Pos logit contributions
ird+0.376
uka+0.349
 Tyler+0.349
 Su+0.333
 Seth+0.330
Neg logit contributions
acle-0.623
Buzz-0.604
rog-0.597
 Buzz-0.590
arium-0.580
Token got
Token ID1392
Feature activation-3.71e-02

Pos logit contributions
rog+0.055
acle+0.053
arium+0.052
 Buzz+0.051
Buzz+0.050
Neg logit contributions
 bal-0.059
 Seth-0.058
 Tyler-0.057
 laund-0.056
uka-0.056
Token out
Token ID503
Feature activation-1.33e-01

Pos logit contributions
cest+0.058
 bal+0.057
 Seth+0.056
 Tyler+0.056
ird+0.056
Neg logit contributions
rog-0.053
 Buzz-0.052
acle-0.051
arium-0.050
Buzz-0.049
Token three
Token ID1115
Feature activation+3.68e-02

Pos logit contributions
 bal+0.186
 Seth+0.180
 Tyler+0.179
ird+0.174
uka+0.174
Neg logit contributions
rog-0.225
acle-0.217
arium-0.214
Buzz-0.207
 Buzz-0.205
Token m
Token ID285
Feature activation-2.51e-01

Pos logit contributions
rog+0.053
acle+0.050
arium+0.050
 Buzz+0.048
Buzz+0.048
Neg logit contributions
 bal-0.060
 Seth-0.058
 Tyler-0.058
uka-0.056
isc-0.056
Tokenugs
Token ID10339
Feature activation-1.07e-01

Pos logit contributions
 bal+0.331
 Seth+0.317
ird+0.316
 Tyler+0.313
uka+0.308
Neg logit contributions
rog-0.449
arium-0.441
acle-0.440
 Buzz-0.421
Buzz-0.420
Token and
Token ID290
Feature activation-3.09e-03

Pos logit contributions
 bal+0.159
 Seth+0.155
 Tyler+0.154
uka+0.150
ird+0.150
Neg logit contributions
rog-0.167
acle-0.162
arium-0.160
 Buzz-0.155
Buzz-0.153
Token poured
Token ID19036
Feature activation+1.95e-02

Pos logit contributions
cest+0.005
 bal+0.005
isc+0.005
uka+0.005
 laund+0.005
Neg logit contributions
 Buzz-0.004
rog-0.004
Buzz-0.004
arium-0.003
atively-0.003
Token a
Token ID257
Feature activation+4.84e-02

Pos logit contributions
rog+0.025
acle+0.024
 Buzz+0.023
arium+0.023
Buzz+0.023
Neg logit contributions
 bal-0.034
 Seth-0.033
 Tyler-0.033
ird-0.033
cest-0.033
Token big
Token ID1263
Feature activation-7.93e-02

Pos logit contributions
rog+0.074
acle+0.071
arium+0.070
Buzz+0.068
 Buzz+0.068
Neg logit contributions
 bal-0.073
 Seth-0.072
 Tyler-0.072
uka-0.070
ird-0.070
Token Her
Token ID2332
Feature activation+8.53e-03

Pos logit contributions
 bal+0.020
 Seth+0.020
 Tyler+0.020
ird+0.019
 Sel+0.019
Neg logit contributions
rog-0.022
arium-0.021
acle-0.021
Buzz-0.020
atively-0.019
Token nos
Token ID43630
Feature activation+3.27e-02

Pos logit contributions
rog+0.015
acle+0.014
arium+0.014
Buzz+0.014
 Buzz+0.014
Neg logit contributions
 bal-0.012
 Seth-0.011
 Tyler-0.011
ird-0.011
 laund-0.011
Tokeny
Token ID88
Feature activation+1.22e-01

Pos logit contributions
acle+0.042
rog+0.042
arium+0.042
 Buzz+0.039
Buzz+0.039
Neg logit contributions
 bal-0.058
 Seth-0.058
 Tyler-0.057
cest-0.056
isc-0.055
Token cat
Token ID3797
Feature activation-4.20e-02

Pos logit contributions
rog+0.190
arium+0.188
acle+0.186
Buzz+0.177
 Buzz+0.174
Neg logit contributions
 bal-0.191
 Seth-0.180
 Tyler-0.178
isc-0.172
 Sel-0.172
Token,
Token ID11
Feature activation-1.51e-02

Pos logit contributions
 bal+0.064
 Seth+0.062
 Tyler+0.062
 Sel+0.059
ird+0.059
Neg logit contributions
rog-0.066
arium-0.064
acle-0.063
Buzz-0.060
 Buzz-0.058
Token Mitt
Token ID16627
Feature activation-2.77e-01

Pos logit contributions
 bal+0.023
 Seth+0.022
 Tyler+0.022
ird+0.022
uka+0.022
Neg logit contributions
rog-0.023
acle-0.022
arium-0.022
Buzz-0.021
 Buzz-0.021
Tokenens
Token ID641
Feature activation+3.88e-02

Pos logit contributions
 bal+0.451
 Seth+0.436
 Tyler+0.435
isc+0.422
ird+0.422
Neg logit contributions
rog-0.401
acle-0.394
arium-0.387
Buzz-0.367
 Buzz-0.363
Token,
Token ID11
Feature activation-1.61e-02

Pos logit contributions
rog+0.061
arium+0.058
acle+0.058
Buzz+0.055
 Buzz+0.054
Neg logit contributions
 bal-0.058
 Tyler-0.057
 Seth-0.057
ird-0.055
 Sel-0.054
Token was
Token ID373
Feature activation-1.86e-02

Pos logit contributions
 bal+0.025
 Seth+0.025
 Tyler+0.024
ird+0.024
uka+0.024
Neg logit contributions
rog-0.024
acle-0.023
arium-0.023
Buzz-0.022
 Buzz-0.022
Token following
Token ID1708
Feature activation+4.81e-02

Pos logit contributions
 bal+0.030
 Seth+0.029
ird+0.028
isc+0.028
 Tyler+0.028
Neg logit contributions
rog-0.027
acle-0.026
 Buzz-0.026
arium-0.026
Buzz-0.025
Token her
Token ID607
Feature activation-4.04e-02

Pos logit contributions
acle+0.081
arium+0.081
rog+0.080
Buzz+0.077
atively+0.075
Neg logit contributions
 Tyler-0.065
 bal-0.064
 Seth-0.064
 Sel-0.061
 laund-0.060
Token help
Token ID1037
Feature activation+4.02e-02

Pos logit contributions
rog+0.007
acle+0.007
arium+0.007
Buzz+0.006
 Buzz+0.006
Neg logit contributions
 bal-0.007
 Seth-0.007
 Tyler-0.007
ird-0.007
uka-0.007
Token the
Token ID262
Feature activation-2.45e-02

Pos logit contributions
rog+0.046
 Buzz+0.043
Buzz+0.041
acle+0.037
 True+0.037
Neg logit contributions
 bal-0.077
 laund-0.075
cest-0.075
 pian-0.074
isc-0.073
Token cut
Token ID2005
Feature activation-1.31e-01

Pos logit contributions
 bal+0.033
 Seth+0.032
 Tyler+0.032
ird+0.031
uka+0.031
Neg logit contributions
rog-0.042
acle-0.041
arium-0.040
 Buzz-0.039
Buzz-0.039
Token heal
Token ID12035
Feature activation+5.03e-02

Pos logit contributions
 bal+0.205
 Tyler+0.201
 Seth+0.201
 laund+0.197
uka+0.196
Neg logit contributions
rog-0.191
acle-0.181
 Buzz-0.176
arium-0.176
Buzz-0.174
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
rog+0.071
acle+0.067
 Buzz+0.066
arium+0.066
Buzz+0.065
Neg logit contributions
 bal-0.082
 Seth-0.080
 Tyler-0.080
 laund-0.079
uka-0.079
Token Cand
Token ID15518
Feature activation-2.40e-01

Pos logit contributions
cest+0.021
 bal+0.019
 laund+0.019
uka+0.019
ird+0.019
Neg logit contributions
 Buzz-0.014
rog-0.014
acle-0.013
 True-0.013
Buzz-0.013
Tokenace
Token ID558
Feature activation+7.76e-02

Pos logit contributions
 bal+0.385
 Seth+0.367
uka+0.366
isc+0.364
ird+0.362
Neg logit contributions
acle-0.365
arium-0.349
rog-0.340
 Buzz-0.330
Buzz-0.320
Token was
Token ID373
Feature activation-2.07e-02

Pos logit contributions
rog+0.136
acle+0.135
arium+0.131
 Buzz+0.119
atively+0.118
Neg logit contributions
 bal-0.108
ird-0.101
 Seth-0.096
 Tyler-0.095
 Sel-0.095
Token so
Token ID523
Feature activation-8.74e-02

Pos logit contributions
 bal+0.032
 Seth+0.032
 Tyler+0.031
isc+0.031
uka+0.031
Neg logit contributions
rog-0.031
acle-0.030
arium-0.029
 Buzz-0.029
Buzz-0.028
Token proud
Token ID6613
Feature activation-8.65e-02

Pos logit contributions
 bal+0.117
ird+0.109
cest+0.104
uka+0.103
 Seth+0.103
Neg logit contributions
rog-0.160
arium-0.155
acle-0.153
atively-0.142
Buzz-0.139
Token of
Token ID286
Feature activation-8.11e-02

Pos logit contributions
uka+0.158
 laund+0.157
 Seth+0.157
ird+0.156
isc+0.155
Neg logit contributions
 Buzz-0.099
rog-0.099
arium-0.098
acle-0.091
Buzz-0.087