TOP ACTIVATIONS
MAX = 11.625

a fun ride at the carn ival . Twe ety thought
, Lily went to a carn ival with her mom my
, Max , to the carn ival . Everywhere they looked
ummy cotton candy and play carn ival games .
for taking her to the carn ival . They hugged her
excited to go to the carn ival with her mom and
, Lily went to a carn ival with her family .
Max loved being at the carn ival so much that he
and they walked through the carn ival gates , while Max
about we have our own carn ival at home ? We
that said " Welcome to Kinder g arten !"
was proud of John and Kinder g arten ers learned an
. She loved to have pic n ics with her family
family were ready to go pic n icking again . But
a family who really enjoyed pic n ics . They loved
They missed their walks and pic n ics near the cliff
favourite place to go for pic n ics . <|endoftext|> Once
be there to support her pic n ics -- no matter
see the bird and have pic n ics . <|endoftext|> Once
and nodded . He loved pic n ics and couldn 't

MIN ACTIVATIONS
MIN = -11.351

squ aw king and his sing . He had forgotten to
iron made a loud his sing sound and steam came out
the iron made a his sing sound and steam came out
lava bub bling and his sing . It was so hot
faster it went . Jo anne began to g iggle with
head and made a his sing sound . Tom and Sam
! The cat was his sing and grow ling . The
in the sky . Jo anne remembered the day she first
felt the healing power cour sing through his body .
there was a loud his sing noise . The mouse looked
!" Jo anne smiled and thanked the old
Years passed and Jo anne grew up . Now she
to other customers . Jo anne and Joey said goodbye as
. The cats were his sing , sw iping and me
And so , when Jo anne graduated from high school ,
into the hole . Jo anne saw the nut disappear into
The ball makes a his sing sound and goes flat .
wanted to go ," Jo anne said .
sc ow ling and his sing . She was scared ,
The bed made a his sing sound and started to go

INTERVAL 5.881 - 11.625
CONTAINS 1.920%

tower this time . <|endoftext|> Once upon a time , there
in pretty clothes . One day , Lily 's friend Emma
But her mom said , � � € � � No
<|endoftext|> Alice and her mom went to the grocery store .
. From that day on , the bird and

INTERVAL 0.137 - 5.881
CONTAINS 42.776%

lady nodded and said , " It 's not easy to
learned that climbing trees can be fun but also dangerous .
proud of him because he had been so brave and listened
busy with all of the other gears . Every day ,
ite in the sky with a license attached . He asked

INTERVAL -5.607 - 0.137
CONTAINS 53.233%

, it 's w obb ly . See ?"
don 't want my brother to suffer . Can we give
picks it up and kicks it hard . The ball flies
listen to each other . They do not realize that the
the garden . He was very careful so he didn 't

INTERVAL -11.351 - -5.607
CONTAINS 2.071%

and back , over and over again . He liked to
thought , and he came up with an idea . He
walked closer and stepped right up to it .
. She put the onions back into the ground and said
at each other . They shrugged and decided to go see
Token a
Token ID257
Feature activation+9.34e-01

Pos logit contributions
 days+0.161
ops+0.153
 weeks+0.147
 times+0.137
 months+0.134
Neg logit contributions
 sincere-0.075
 faint-0.073
 source-0.069
 widen-0.066
 fright-0.065
Token fun
Token ID1257
Feature activation+3.11e+00

Pos logit contributions
 days+0.047
 weeks+0.041
ops+0.038
 months+0.036
 times+0.036
Neg logit contributions
 sincere-0.041
 rapidly-0.040
 faint-0.040
 widen-0.040
Sad-0.039
Token ride
Token ID6594
Feature activation+3.98e+00

Pos logit contributions
 days+0.124
 weeks+0.119
ops+0.118
 months+0.107
 nights+0.095
Neg logit contributions
 source-0.149
 fright-0.149
 faint-0.148
ull-0.148
 rapidly-0.143
Token at
Token ID379
Feature activation-6.78e-01

Pos logit contributions
 days+0.207
 weeks+0.189
ops+0.172
 months+0.167
 times+0.164
Neg logit contributions
 rapidly-0.163
fly-0.159
 source-0.153
 faint-0.152
 sincere-0.151
Token the
Token ID262
Feature activation+1.93e+00

Pos logit contributions
 rapidly+0.027
 faint+0.027
 source+0.027
 sincere+0.027
 widen+0.027
Neg logit contributions
 days-0.035
 weeks-0.031
ops-0.030
 months-0.028
 times-0.028
Token carn
Token ID18466
Feature activation+1.16e+01

Pos logit contributions
 days+0.100
 weeks+0.088
ops+0.083
 months+0.078
 times+0.077
Neg logit contributions
 faint-0.082
 source-0.081
 sincere-0.080
 rapidly-0.079
 widen-0.079
Tokenival
Token ID2473
Feature activation+9.10e-01

Pos logit contributions
 days+0.584
 weeks+0.508
ops+0.471
 months+0.445
 times+0.444
Neg logit contributions
 sincere-0.515
 rapidly-0.508
 faint-0.505
 widen-0.504
Sad-0.496
Token.
Token ID13
Feature activation-4.71e-02

Pos logit contributions
 days+0.055
 weeks+0.051
ops+0.045
 nights+0.045
mm+0.044
Neg logit contributions
 source-0.030
 rapidly-0.028
fly-0.028
 clearly-0.027
 startled-0.026
Token Twe
Token ID24205
Feature activation-5.68e-01

Pos logit contributions
 sincere+0.002
 rapidly+0.002
 faint+0.002
fly+0.002
 widen+0.002
Neg logit contributions
 days-0.003
 weeks-0.002
ops-0.002
 months-0.002
 times-0.002
Tokenety
Token ID2963
Feature activation-2.82e+00

Pos logit contributions
 sincere+0.025
 faint+0.024
 widen+0.024
 rapidly+0.024
 source+0.023
Neg logit contributions
 days-0.029
 weeks-0.026
ops-0.024
 times-0.023
 months-0.022
Token thought
Token ID1807
Feature activation+1.86e+00

Pos logit contributions
 rapidly+0.096
 sincere+0.094
 startled+0.093
fly+0.092
 faint+0.090
Neg logit contributions
 days-0.167
 weeks-0.148
 times-0.138
ops-0.137
 months-0.135
Token,
Token ID11
Feature activation+1.82e-01

Pos logit contributions
 days+0.417
 weeks+0.384
 months+0.346
ops+0.342
 times+0.341
Neg logit contributions
 sincere-0.378
 faint-0.372
 startled-0.371
 rapidly-0.364
Sad-0.361
Token Lily
Token ID20037
Feature activation+2.12e+00

Pos logit contributions
 days+0.009
 weeks+0.008
ops+0.008
 months+0.008
 times+0.008
Neg logit contributions
 sincere-0.008
 faint-0.007
 rapidly-0.007
Sad-0.007
 source-0.007
Token went
Token ID1816
Feature activation+6.62e+00

Pos logit contributions
 days+0.116
 weeks+0.104
ops+0.098
 times+0.096
 months+0.093
Neg logit contributions
 startled-0.076
 sincere-0.075
 source-0.074
 faint-0.074
 rapidly-0.074
Token to
Token ID284
Feature activation-1.91e+00

Pos logit contributions
 days+0.397
 weeks+0.359
ops+0.349
 times+0.330
 months+0.324
Neg logit contributions
 source-0.223
 rapidly-0.217
 faint-0.216
 sincere-0.216
 widen-0.210
Token a
Token ID257
Feature activation+9.93e-01

Pos logit contributions
 sincere+0.100
 rapidly+0.100
itating+0.099
fly+0.098
 widen+0.097
Neg logit contributions
 days-0.083
 weeks-0.070
 times-0.060
 later-0.059
 months-0.059
Token carn
Token ID18466
Feature activation+1.16e+01

Pos logit contributions
 days+0.047
 weeks+0.040
ops+0.036
 months+0.035
 times+0.035
Neg logit contributions
 rapidly-0.046
 sincere-0.046
 widen-0.046
Sad-0.046
fly-0.045
Tokenival
Token ID2473
Feature activation+8.68e-01

Pos logit contributions
 days+0.578
 weeks+0.501
ops+0.467
 months+0.438
 times+0.434
Neg logit contributions
 sincere-0.515
 rapidly-0.512
 faint-0.512
 widen-0.509
fly-0.506
Token with
Token ID351
Feature activation+3.27e-01

Pos logit contributions
 days+0.057
 weeks+0.053
ops+0.050
 nights+0.048
mm+0.048
Neg logit contributions
 source-0.023
itating-0.019
 below-0.019
 startled-0.019
 rapidly-0.018
Token her
Token ID607
Feature activation+2.02e+00

Pos logit contributions
 days+0.019
 weeks+0.017
ops+0.016
 times+0.015
 months+0.015
Neg logit contributions
 sincere-0.012
 faint-0.012
 rapidly-0.011
 widen-0.011
 source-0.011
Token mom
Token ID1995
Feature activation-1.91e+00

Pos logit contributions
 days+0.116
 weeks+0.106
ops+0.097
 months+0.095
 times+0.093
Neg logit contributions
 sincere-0.075
 faint-0.071
 source-0.069
 rapidly-0.068
fly-0.068
Tokenmy
Token ID1820
Feature activation-2.65e+00

Pos logit contributions
 source+0.055
fly+0.050
itating+0.049
ff+0.048
bird+0.048
Neg logit contributions
 days-0.127
 weeks-0.116
ops-0.108
 months-0.106
 times-0.105
Token,
Token ID11
Feature activation+8.81e-02

Pos logit contributions
 source+0.136
 fright+0.126
 rapidly+0.125
 sincere+0.125
 faint+0.123
Neg logit contributions
 days-0.148
ops-0.144
 weeks-0.133
mm-0.120
 months-0.112
Token Max
Token ID5436
Feature activation+3.67e-01

Pos logit contributions
 days+0.005
 weeks+0.005
ops+0.005
 times+0.004
 months+0.004
Neg logit contributions
 faint-0.003
 sincere-0.003
 rapidly-0.003
 widen-0.003
 startled-0.003
Token,
Token ID11
Feature activation+9.58e-02

Pos logit contributions
 days+0.021
 weeks+0.019
 times+0.018
ops+0.018
 months+0.016
Neg logit contributions
fly-0.013
 rapidly-0.013
 source-0.013
ff-0.013
 startled-0.012
Token to
Token ID284
Feature activation-1.87e+00

Pos logit contributions
 days+0.005
 weeks+0.005
ops+0.005
 times+0.004
 months+0.004
Neg logit contributions
 sincere-0.004
 faint-0.004
 rapidly-0.004
 source-0.003
 widen-0.003
Token the
Token ID262
Feature activation+1.99e+00

Pos logit contributions
 sincere+0.075
 rapidly+0.074
 faint+0.074
 widen+0.073
Sad+0.072
Neg logit contributions
 days-0.102
 weeks-0.089
ops-0.084
 months-0.079
 times-0.079
Token carn
Token ID18466
Feature activation+1.16e+01

Pos logit contributions
 days+0.098
 weeks+0.085
ops+0.079
 times+0.074
 months+0.074
Neg logit contributions
 sincere-0.091
 faint-0.089
 rapidly-0.089
 widen-0.088
 source-0.088
Tokenival
Token ID2473
Feature activation+8.34e-01

Pos logit contributions
 days+0.597
 weeks+0.522
ops+0.481
 times+0.462
 months+0.458
Neg logit contributions
 sincere-0.504
 rapidly-0.492
 faint-0.485
itating-0.484
 widen-0.484
Token.
Token ID13
Feature activation-1.67e-02

Pos logit contributions
 days+0.049
 weeks+0.046
 nights+0.040
ops+0.040
 times+0.039
Neg logit contributions
 source-0.028
 rapidly-0.026
itating-0.025
fly-0.024
 clearly-0.024
Token Everywhere
Token ID48201
Feature activation+2.90e+00

Pos logit contributions
 sincere+0.001
fly+0.001
 rapidly+0.001
ull+0.001
 faint+0.001
Neg logit contributions
 days-0.001
 weeks-0.001
ops-0.001
 months-0.001
 times-0.001
Token they
Token ID484
Feature activation+4.09e+00

Pos logit contributions
 days+0.151
ops+0.143
 weeks+0.137
 cents+0.128
 times+0.126
Neg logit contributions
 silent-0.093
 faint-0.092
 startled-0.092
 rapidly-0.090
 Charlie-0.089
Token looked
Token ID3114
Feature activation-4.39e+00

Pos logit contributions
 days+0.219
 weeks+0.187
ops+0.176
 times+0.175
 choices+0.173
Neg logit contributions
 rapidly-0.155
bell-0.153
 widen-0.150
ff-0.150
 perplex-0.149
Tokenummy
Token ID13513
Feature activation-2.90e+00

Pos logit contributions
 days+0.150
 weeks+0.136
ops+0.123
 months+0.121
 nights+0.117
Neg logit contributions
 rapidly-0.092
 widen-0.091
 sincere-0.088
 faint-0.088
ff-0.087
Token cotton
Token ID15985
Feature activation+5.10e+00

Pos logit contributions
 flashes+0.114
 gasp+0.113
 record+0.110
 widen+0.109
 flashing+0.108
Neg logit contributions
 weeks-0.114
 days-0.113
ops-0.103
 months-0.094
ip-0.092
Token candy
Token ID18550
Feature activation+2.23e+00

Pos logit contributions
 days+0.213
 weeks+0.202
 nights+0.178
 months+0.168
have+0.162
Neg logit contributions
 rapidly-0.203
 hood-0.201
 widen-0.193
 flashes-0.189
 flashing-0.188
Token and
Token ID290
Feature activation+1.57e+00

Pos logit contributions
 days+0.122
 weeks+0.110
 nights+0.100
 months+0.096
 times+0.094
Neg logit contributions
 rapidly-0.083
fly-0.077
 widen-0.075
acle-0.074
 source-0.073
Token play
Token ID711
Feature activation+5.28e+00

Pos logit contributions
 days+0.075
ops+0.069
 weeks+0.068
 times+0.059
 months+0.059
Neg logit contributions
 faint-0.063
 sincere-0.062
 rapidly-0.062
 widen-0.061
 source-0.059
Token carn
Token ID18466
Feature activation+1.16e+01

Pos logit contributions
 days+0.272
 weeks+0.246
ops+0.237
 times+0.217
 months+0.216
Neg logit contributions
 rapidly-0.215
 sincere-0.210
 widen-0.199
 faint-0.199
 source-0.198
Tokenival
Token ID2473
Feature activation+8.28e-01

Pos logit contributions
 days+0.636
 weeks+0.562
ops+0.509
 times+0.505
 months+0.497
Neg logit contributions
 sincere-0.457
 rapidly-0.454
itating-0.452
 widen-0.442
 faint-0.432
Token games
Token ID1830
Feature activation+7.37e+00

Pos logit contributions
 days+0.047
 weeks+0.044
 nights+0.038
ops+0.038
 months+0.037
Neg logit contributions
 rapidly-0.027
 clearly-0.025
 source-0.025
fly-0.024
itating-0.023
Token.
Token ID13
Feature activation-2.60e-01

Pos logit contributions
 days+0.412
 weeks+0.379
ops+0.357
 times+0.341
 months+0.336
Neg logit contributions
 rapidly-0.248
 source-0.232
fly-0.225
 above-0.217
acle-0.216
Token
Token ID198
Feature activation-1.48e+00

Pos logit contributions
 sincere+0.007
 rapidly+0.007
 faint+0.007
 widen+0.007
Sad+0.007
Neg logit contributions
 days-0.017
 weeks-0.015
ops-0.015
 times-0.014
 months-0.014
Token
Token ID198
Feature activation-1.50e+00

Pos logit contributions
fly+0.065
 sincere+0.065
 widen+0.064
 rapidly+0.060
 source+0.059
Neg logit contributions
 days-0.078
 weeks-0.068
ops-0.064
 later-0.061
 day-0.061
Token for
Token ID329
Feature activation+2.54e+00

Pos logit contributions
 source+0.005
 over+0.005
bird+0.005
fly+0.005
 desperately+0.005
Neg logit contributions
 days-0.007
 weeks-0.006
ops-0.006
mm-0.006
 times-0.006
Token taking
Token ID2263
Feature activation+6.09e+00

Pos logit contributions
 days+0.127
ops+0.115
 weeks+0.111
 times+0.100
 months+0.099
Neg logit contributions
 sincere-0.113
 faint-0.105
Sad-0.105
 rapidly-0.103
 source-0.102
Token her
Token ID607
Feature activation+1.81e+00

Pos logit contributions
 days+0.326
ops+0.307
 weeks+0.291
 times+0.264
 months+0.261
Neg logit contributions
 fright-0.216
 rapidly-0.215
Sad-0.210
 widen-0.207
 sincere-0.207
Token to
Token ID284
Feature activation-2.04e+00

Pos logit contributions
 days+0.105
 weeks+0.099
ops+0.097
 months+0.092
mm+0.091
Neg logit contributions
 source-0.059
 fright-0.057
bird-0.048
itating-0.047
 menacing-0.046
Token the
Token ID262
Feature activation+1.72e+00

Pos logit contributions
 sincere+0.085
 faint+0.084
 widen+0.083
 rapidly+0.082
 source+0.081
Neg logit contributions
 days-0.108
 weeks-0.094
ops-0.092
 months-0.083
 times-0.083
Token carn
Token ID18466
Feature activation+1.15e+01

Pos logit contributions
 days+0.085
 weeks+0.074
ops+0.073
 times+0.066
 months+0.065
Neg logit contributions
 sincere-0.078
 source-0.076
 faint-0.076
 widen-0.073
 rapidly-0.073
Tokenival
Token ID2473
Feature activation+7.80e-01

Pos logit contributions
 days+0.603
 weeks+0.527
ops+0.486
 times+0.471
 months+0.465
Neg logit contributions
 sincere-0.492
 rapidly-0.479
itating-0.472
 faint-0.469
 widen-0.467
Token.
Token ID13
Feature activation-2.44e-01

Pos logit contributions
 days+0.042
 weeks+0.038
ops+0.035
 nights+0.033
 months+0.033
Neg logit contributions
 source-0.027
 rapidly-0.027
fly-0.026
 faint-0.026
 clearly-0.025
Token They
Token ID1119
Feature activation+2.98e-01

Pos logit contributions
 sincere+0.007
Sad+0.007
 rapidly+0.007
 faint+0.007
 widen+0.007
Neg logit contributions
 days-0.016
 weeks-0.014
ops-0.013
 times-0.013
 months-0.013
Token hugged
Token ID41130
Feature activation-1.58e+00

Pos logit contributions
 days+0.016
 weeks+0.014
ops+0.013
 times+0.013
 months+0.012
Neg logit contributions
 rapidly-0.012
 sincere-0.011
 widen-0.011
 perplex-0.011
fly-0.011
Token her
Token ID607
Feature activation+1.82e+00

Pos logit contributions
 rapidly+0.065
 sincere+0.063
Sad+0.063
 faint+0.062
 widen+0.062
Neg logit contributions
 days-0.081
ops-0.072
 weeks-0.072
 months-0.064
 nights-0.062
Token excited
Token ID6568
Feature activation+1.33e+00

Pos logit contributions
 days+0.119
 weeks+0.106
ops+0.099
 months+0.094
 times+0.094
Neg logit contributions
 sincere-0.081
 faint-0.079
 rapidly-0.079
 widen-0.078
Sad-0.077
Token to
Token ID284
Feature activation-2.02e+00

Pos logit contributions
 days+0.079
 weeks+0.074
ops+0.072
 months+0.067
 times+0.065
Neg logit contributions
 source-0.040
 faint-0.040
 rapidly-0.039
 startled-0.037
anne-0.036
Token go
Token ID467
Feature activation+5.13e+00

Pos logit contributions
 sincere+0.093
 rapidly+0.092
 faint+0.091
 widen+0.091
Sad+0.090
Neg logit contributions
 days-0.099
 weeks-0.086
ops-0.079
 times-0.075
 months-0.075
Token to
Token ID284
Feature activation-2.04e+00

Pos logit contributions
 days+0.289
 weeks+0.264
ops+0.254
 times+0.240
 months+0.236
Neg logit contributions
 source-0.190
 faint-0.182
 rapidly-0.178
 widen-0.178
 sincere-0.172
Token the
Token ID262
Feature activation+1.92e+00

Pos logit contributions
 sincere+0.088
 faint+0.087
 widen+0.086
 rapidly+0.086
 source+0.085
Neg logit contributions
 days-0.105
 weeks-0.092
ops-0.087
 months-0.081
 times-0.080
Token carn
Token ID18466
Feature activation+1.15e+01

Pos logit contributions
 days+0.087
 weeks+0.074
ops+0.067
 months+0.064
 times+0.063
Neg logit contributions
 sincere-0.095
 rapidly-0.094
Sad-0.093
 widen-0.093
fly-0.092
Tokenival
Token ID2473
Feature activation+7.50e-01

Pos logit contributions
 days+0.594
 weeks+0.520
ops+0.479
 times+0.460
 months+0.457
Neg logit contributions
 sincere-0.495
 rapidly-0.486
 faint-0.480
 widen-0.479
itating-0.478
Token with
Token ID351
Feature activation+1.49e-01

Pos logit contributions
 days+0.047
 weeks+0.044
 nights+0.039
ops+0.039
 months+0.038
Neg logit contributions
 source-0.023
itating-0.021
 rapidly-0.020
 clearly-0.020
 startled-0.019
Token her
Token ID607
Feature activation+2.00e+00

Pos logit contributions
 days+0.008
 weeks+0.007
ops+0.006
 months+0.006
 times+0.006
Neg logit contributions
 sincere-0.006
 rapidly-0.006
 faint-0.006
 widen-0.006
fly-0.006
Token mom
Token ID1995
Feature activation-2.01e+00

Pos logit contributions
 days+0.116
 weeks+0.107
ops+0.101
 months+0.097
 nights+0.096
Neg logit contributions
 sincere-0.070
 faint-0.067
 source-0.065
 rapidly-0.062
Sad-0.061
Token and
Token ID290
Feature activation+1.95e+00

Pos logit contributions
 source+0.055
Sad+0.052
ff+0.051
fly+0.051
itating+0.051
Neg logit contributions
 days-0.131
 weeks-0.120
ops-0.115
 months-0.110
 times-0.108
Token,
Token ID11
Feature activation-6.21e-01

Pos logit contributions
 days+0.392
 weeks+0.343
ops+0.318
 times+0.313
 months+0.297
Neg logit contributions
 startled-0.417
 rapidly-0.413
 faint-0.404
 sincere-0.404
fly-0.391
Token Lily
Token ID20037
Feature activation+2.24e+00

Pos logit contributions
 faint+0.025
 rapidly+0.024
 sincere+0.024
 source+0.024
fly+0.024
Neg logit contributions
 days-0.033
 weeks-0.029
ops-0.028
 times-0.027
 months-0.026
Token went
Token ID1816
Feature activation+6.10e+00

Pos logit contributions
 days+0.131
 weeks+0.117
ops+0.113
 times+0.110
 months+0.104
Neg logit contributions
 startled-0.073
ff-0.073
 rapidly-0.071
 sincere-0.070
anne-0.069
Token to
Token ID284
Feature activation-2.22e+00

Pos logit contributions
 days+0.345
 weeks+0.308
ops+0.295
 times+0.278
 months+0.276
Neg logit contributions
 sincere-0.226
 source-0.225
 rapidly-0.224
 faint-0.223
 widen-0.217
Token a
Token ID257
Feature activation+8.00e-01

Pos logit contributions
 sincere+0.118
 rapidly+0.116
itating+0.115
 widen+0.114
fly+0.114
Neg logit contributions
 days-0.096
 weeks-0.080
 times-0.069
 later-0.069
 day-0.068
Token carn
Token ID18466
Feature activation+1.15e+01

Pos logit contributions
 days+0.043
 weeks+0.037
ops+0.034
 months+0.033
 times+0.033
Neg logit contributions
 sincere-0.033
 rapidly-0.032
 widen-0.032
Sad-0.032
 faint-0.032
Tokenival
Token ID2473
Feature activation+7.53e-01

Pos logit contributions
 days+0.578
 weeks+0.502
ops+0.465
 months+0.440
 times+0.439
Neg logit contributions
 sincere-0.511
 rapidly-0.504
 faint-0.500
 widen-0.499
Sad-0.492
Token with
Token ID351
Feature activation+1.23e-01

Pos logit contributions
 days+0.048
 weeks+0.044
ops+0.043
mm+0.040
 nights+0.040
Neg logit contributions
 source-0.020
 rapidly-0.017
 below-0.017
 above-0.017
itating-0.017
Token her
Token ID607
Feature activation+2.00e+00

Pos logit contributions
 days+0.007
ops+0.006
 weeks+0.006
 times+0.006
 months+0.006
Neg logit contributions
 sincere-0.004
 faint-0.004
 rapidly-0.004
 aw-0.004
Maria-0.004
Token family
Token ID1641
Feature activation+9.74e-01

Pos logit contributions
 days+0.118
 weeks+0.108
ops+0.099
 months+0.097
 nights+0.096
Neg logit contributions
 sincere-0.071
 faint-0.067
 source-0.065
fly-0.064
 rapidly-0.063
Token.
Token ID13
Feature activation-4.82e-01

Pos logit contributions
 days+0.058
 weeks+0.054
ops+0.054
 nights+0.049
 times+0.049
Neg logit contributions
 source-0.029
bird-0.025
 sincere-0.024
fly-0.024
itating-0.024
Token Max
Token ID5436
Feature activation+1.13e-01

Pos logit contributions
 sincere+0.013
fly+0.013
 rapidly+0.012
 faint+0.012
ull+0.012
Neg logit contributions
 days-0.016
 weeks-0.014
ops-0.013
 months-0.012
 day-0.012
Token loved
Token ID6151
Feature activation-5.84e-01

Pos logit contributions
 days+0.006
 weeks+0.005
ops+0.005
 times+0.005
 months+0.004
Neg logit contributions
 rapidly-0.005
 sincere-0.005
 faint-0.005
 widen-0.005
fly-0.005
Token being
Token ID852
Feature activation+5.15e-01

Pos logit contributions
 faint+0.022
 rapidly+0.022
 sincere+0.021
 source+0.021
 fright+0.021
Neg logit contributions
 days-0.032
ops-0.029
 weeks-0.028
 months-0.025
 times-0.025
Token at
Token ID379
Feature activation-8.12e-01

Pos logit contributions
 days+0.028
 weeks+0.024
ops+0.022
 months+0.021
 times+0.021
Neg logit contributions
 sincere-0.021
 widen-0.021
 rapidly-0.021
 faint-0.021
Sad-0.020
Token the
Token ID262
Feature activation+1.86e+00

Pos logit contributions
 source+0.029
 faint+0.028
 fright+0.028
 rapidly+0.027
 sincere+0.026
Neg logit contributions
 days-0.044
ops-0.042
 weeks-0.039
ip-0.035
 months-0.035
Token carn
Token ID18466
Feature activation+1.15e+01

Pos logit contributions
 days+0.092
 weeks+0.082
ops+0.075
 nights+0.070
 times+0.070
Neg logit contributions
 source-0.087
 faint-0.079
 widen-0.079
 sincere-0.077
 rapidly-0.075
Tokenival
Token ID2473
Feature activation+7.26e-01

Pos logit contributions
 days+0.621
 weeks+0.547
ops+0.495
 times+0.491
 months+0.482
Neg logit contributions
 sincere-0.466
 rapidly-0.457
itating-0.456
 widen-0.443
 faint-0.443
Token so
Token ID523
Feature activation+2.01e+00

Pos logit contributions
 days+0.037
 weeks+0.033
ops+0.031
 months+0.028
 nights+0.028
Neg logit contributions
 rapidly-0.029
 source-0.028
fly-0.028
 faint-0.028
 widen-0.027
Token much
Token ID881
Feature activation+2.07e+00

Pos logit contributions
 days+0.110
 weeks+0.098
ops+0.095
 months+0.087
 times+0.087
Neg logit contributions
 rapidly-0.078
 sincere-0.078
 faint-0.077
 widen-0.074
Sad-0.073
Token that
Token ID326
Feature activation+3.53e-02

Pos logit contributions
 days+0.108
ops+0.102
 weeks+0.098
 cand+0.087
 months+0.085
Neg logit contributions
 rapidly-0.077
 faint-0.077
 source-0.073
 widen-0.071
 clearly-0.071
Token he
Token ID339
Feature activation+2.51e+00

Pos logit contributions
 days+0.002
ops+0.002
 weeks+0.001
 cand+0.001
ip+0.001
Neg logit contributions
 faint-0.001
 sincere-0.001
 rapidly-0.001
 startled-0.001
 aw-0.001
Token and
Token ID290
Feature activation+1.76e+00

Pos logit contributions
 faint+0.072
 source+0.072
 rapidly+0.071
 widen+0.070
 sincere+0.070
Neg logit contributions
 days-0.084
 weeks-0.073
ops-0.070
 months-0.063
 times-0.063
Token they
Token ID484
Feature activation+3.88e+00

Pos logit contributions
 days+0.094
 weeks+0.082
ops+0.076
 months+0.073
 times+0.073
Neg logit contributions
 sincere-0.072
 rapidly-0.071
 widen-0.070
 faint-0.070
Sad-0.069
Token walked
Token ID6807
Feature activation+4.66e+00

Pos logit contributions
 days+0.203
 weeks+0.176
ops+0.164
 times+0.158
 months+0.154
Neg logit contributions
 rapidly-0.164
 sincere-0.163
fly-0.160
 widen-0.159
 faint-0.156
Token through
Token ID832
Feature activation-4.95e+00

Pos logit contributions
 days+0.266
 weeks+0.236
ops+0.224
 times+0.211
 months+0.210
Neg logit contributions
 sincere-0.175
 rapidly-0.175
 faint-0.172
 widen-0.171
 source-0.169
Token the
Token ID262
Feature activation+1.82e+00

Pos logit contributions
 faint+0.176
 rapidly+0.175
 source+0.175
 sincere+0.174
 widen+0.168
Neg logit contributions
 days-0.278
ops-0.258
 weeks-0.248
 times-0.219
 nights-0.218
Token carn
Token ID18466
Feature activation+1.14e+01

Pos logit contributions
 days+0.086
 weeks+0.077
ops+0.075
 times+0.065
 later+0.065
Neg logit contributions
 source-0.083
 faint-0.081
 widen-0.079
 sincere-0.079
 hood-0.078
Tokenival
Token ID2473
Feature activation+7.14e-01

Pos logit contributions
 days+0.581
 weeks+0.506
ops+0.467
 times+0.446
 months+0.443
Neg logit contributions
 sincere-0.503
 rapidly-0.494
 faint-0.489
 widen-0.487
itating-0.483
Token gates
Token ID17435
Feature activation-5.94e-01

Pos logit contributions
 days+0.039
 weeks+0.036
ops+0.034
mm+0.033
ip+0.031
Neg logit contributions
 source-0.026
 rapidly-0.025
 clearly-0.023
 faint-0.023
itating-0.023
Token,
Token ID11
Feature activation-1.51e-01

Pos logit contributions
 source+0.023
 rapidly+0.023
 faint+0.023
itating+0.023
 widen+0.022
Neg logit contributions
 days-0.032
 weeks-0.028
ops-0.028
 times-0.025
 cand-0.025
Token while
Token ID981
Feature activation+3.23e+00

Pos logit contributions
 source+0.006
 sincere+0.006
 faint+0.006
 rapidly+0.006
 widen+0.006
Neg logit contributions
 days-0.008
ops-0.007
 weeks-0.007
 times-0.006
 months-0.006
Token Max
Token ID5436
Feature activation-3.37e-02

Pos logit contributions
 days+0.159
ops+0.143
 weeks+0.138
 times+0.132
 cand+0.125
Neg logit contributions
 faint-0.135
 sincere-0.134
 rapidly-0.131
 source-0.127
 widen-0.126
Token about
Token ID546
Feature activation-4.45e+00

Pos logit contributions
 days+0.363
 weeks+0.320
ops+0.300
 months+0.285
 times+0.282
Neg logit contributions
 sincere-0.271
 faint-0.270
 rapidly-0.265
 widen-0.263
 source-0.256
Token we
Token ID356
Feature activation+3.11e+00

Pos logit contributions
 faint+0.177
 sincere+0.177
 source+0.169
 investigate+0.167
fly+0.167
Neg logit contributions
 days-0.227
ops-0.216
 weeks-0.203
 times-0.185
 nights-0.177
Token have
Token ID423
Feature activation+1.67e+00

Pos logit contributions
 days+0.166
 weeks+0.145
ops+0.136
 months+0.128
 times+0.128
Neg logit contributions
 sincere-0.130
 rapidly-0.128
 faint-0.127
 widen-0.127
 source-0.124
Token our
Token ID674
Feature activation+2.15e+00

Pos logit contributions
 days+0.094
ops+0.090
 weeks+0.085
 times+0.078
 months+0.076
Neg logit contributions
 sincere-0.056
 source-0.056
 faint-0.055
 rapidly-0.053
 fright-0.052
Token own
Token ID898
Feature activation+3.99e-01

Pos logit contributions
 days+0.096
ops+0.094
 weeks+0.092
 months+0.080
ip+0.080
Neg logit contributions
 sincere-0.089
 fright-0.088
 source-0.087
 faint-0.086
 hood-0.082
Token carn
Token ID18466
Feature activation+1.14e+01

Pos logit contributions
 days+0.020
 weeks+0.018
ops+0.018
 months+0.016
 nights+0.016
Neg logit contributions
 source-0.016
 faint-0.016
 sincere-0.016
 hood-0.016
 fright-0.015
Tokenival
Token ID2473
Feature activation+6.24e-01

Pos logit contributions
 days+0.679
 weeks+0.610
 times+0.571
ops+0.554
 months+0.548
Neg logit contributions
 sincere-0.381
itating-0.371
 rapidly-0.353
 perplex-0.344
 source-0.333
Token at
Token ID379
Feature activation-8.39e-01

Pos logit contributions
 days+0.034
 weeks+0.030
ops+0.029
 times+0.026
 months+0.026
Neg logit contributions
fly-0.022
 source-0.022
 faint-0.021
 sincere-0.021
 rapidly-0.021
Token home
Token ID1363
Feature activation-1.78e+00

Pos logit contributions
 source+0.035
 faint+0.034
 sincere+0.033
 widen+0.033
 rapidly+0.033
Neg logit contributions
 days-0.044
ops-0.038
 weeks-0.038
 times-0.034
 months-0.033
Token?
Token ID30
Feature activation-2.20e-01

Pos logit contributions
 faint+0.060
 source+0.060
 sincere+0.059
itating+0.058
 rapidly+0.058
Neg logit contributions
 days-0.105
 weeks-0.093
ops-0.090
 times-0.085
 months-0.083
Token We
Token ID775
Feature activation+2.30e+00

Pos logit contributions
 sincere+0.009
 rapidly+0.009
 faint+0.009
 widen+0.009
Sad+0.009
Neg logit contributions
 days-0.012
 weeks-0.011
ops-0.010
 times-0.009
 months-0.009
Token that
Token ID326
Feature activation+2.33e-01

Pos logit contributions
 sincere+0.088
 faint+0.086
 rapidly+0.086
 widen+0.086
 source+0.084
Neg logit contributions
 days-0.085
 weeks-0.073
ops-0.068
 months-0.063
 times-0.063
Token said
Token ID531
Feature activation+8.29e-01

Pos logit contributions
 days+0.011
 weeks+0.010
ops+0.009
 months+0.009
 times+0.009
Neg logit contributions
 sincere-0.011
 rapidly-0.010
 widen-0.010
 faint-0.010
Sad-0.010
Token "
Token ID366
Feature activation+1.13e+00

Pos logit contributions
 days+0.049
 weeks+0.044
ops+0.041
 times+0.040
 months+0.039
Neg logit contributions
 sincere-0.030
 faint-0.029
 widen-0.028
 rapidly-0.028
fly-0.028
TokenWelcome
Token ID14618
Feature activation+4.64e+00

Pos logit contributions
 days+0.068
 weeks+0.061
ops+0.056
 times+0.054
 months+0.054
Neg logit contributions
 widen-0.038
 faint-0.038
 rapidly-0.038
itating-0.038
Sad-0.038
Token to
Token ID284
Feature activation-1.95e+00

Pos logit contributions
 days+0.289
 weeks+0.264
ops+0.252
 months+0.238
 nights+0.238
Neg logit contributions
fly-0.148
 source-0.144
ff-0.137
 faint-0.136
itating-0.134
Token Kinder
Token ID46832
Feature activation+1.10e+01

Pos logit contributions
 faint+0.071
 sincere+0.071
 rapidly+0.068
 source+0.068
 widen+0.067
Neg logit contributions
 days-0.108
ops-0.097
 weeks-0.096
 months-0.085
 nights-0.085
Tokeng
Token ID70
Feature activation+1.60e+00

Pos logit contributions
 days+0.601
 weeks+0.527
ops+0.498
 times+0.493
 nights+0.479
Neg logit contributions
 sincere-0.404
Sad-0.402
 rapidly-0.401
itating-0.399
 widen-0.394
Tokenarten
Token ID23996
Feature activation-7.77e-01

Pos logit contributions
 days+0.098
 weeks+0.088
ops+0.080
 nights+0.079
 months+0.079
Neg logit contributions
itating-0.050
 rapidly-0.050
 source-0.050
 faint-0.050
 sincere-0.050
Token!"
Token ID2474
Feature activation-1.41e+00

Pos logit contributions
itating+0.028
 source+0.028
 widen+0.027
 rapidly+0.027
 sincere+0.027
Neg logit contributions
 days-0.044
 weeks-0.039
ops-0.036
 nights-0.035
 times-0.035
Token
Token ID198
Feature activation-1.64e+00

Pos logit contributions
 sincere+0.045
 rapidly+0.045
 faint+0.044
 widen+0.044
Sad+0.043
Neg logit contributions
 days-0.088
 weeks-0.079
ops-0.074
 months-0.071
 times-0.071
Token
Token ID198
Feature activation-1.64e+00

Pos logit contributions
fly+0.086
 sincere+0.081
 widen+0.081
sing+0.081
 rapidly+0.078
Neg logit contributions
 days-0.075
 weeks-0.063
 later-0.058
 months-0.055
 day-0.054
Token was
Token ID373
Feature activation-1.79e+00

Pos logit contributions
 widen+0.136
 sincere+0.135
 faint+0.135
 rapidly+0.133
Sad+0.132
Neg logit contributions
 days-0.153
 weeks-0.132
ops-0.121
 times-0.117
 months-0.115
Token proud
Token ID6613
Feature activation-1.62e+00

Pos logit contributions
fly+0.080
 rapidly+0.078
Sad+0.077
 fuse+0.076
 widen+0.076
Neg logit contributions
 days-0.087
 weeks-0.076
 months-0.066
 later-0.066
 times-0.065
Token of
Token ID286
Feature activation-2.35e+00

Pos logit contributions
 faint+0.053
 sincere+0.051
 rapidly+0.050
 source+0.049
 startled+0.049
Neg logit contributions
 days-0.091
ops-0.089
 weeks-0.083
 months-0.076
 nights-0.073
Token John
Token ID1757
Feature activation-3.60e+00

Pos logit contributions
 sincere+0.056
 rapidly+0.054
 faint+0.053
 widen+0.052
Sad+0.052
Neg logit contributions
 days-0.166
 weeks-0.151
ops-0.146
 months-0.138
 times-0.137
Token and
Token ID290
Feature activation+1.56e+00

Pos logit contributions
fly+0.128
 sincere+0.125
 rapidly+0.123
anne+0.123
 source+0.122
Neg logit contributions
 days-0.190
 weeks-0.172
ops-0.167
 months-0.154
 nights-0.150
Token Kinder
Token ID46832
Feature activation+1.09e+01

Pos logit contributions
 days+0.081
ops+0.075
 weeks+0.073
 months+0.064
 times+0.062
Neg logit contributions
 sincere-0.065
 rapidly-0.062
 faint-0.062
 startled-0.060
ull-0.060
Tokeng
Token ID70
Feature activation+1.31e+00

Pos logit contributions
 days+0.557
 weeks+0.485
ops+0.457
 times+0.437
 months+0.426
Neg logit contributions
 sincere-0.462
 rapidly-0.457
Sad-0.454
 widen-0.453
 faint-0.443
Tokenarten
Token ID23996
Feature activation-9.33e-01

Pos logit contributions
 days+0.076
 weeks+0.068
ops+0.064
 months+0.061
 times+0.061
Neg logit contributions
 sincere-0.048
 faint-0.048
 widen-0.047
 rapidly-0.047
Sad-0.047
Tokeners
Token ID364
Feature activation+7.70e-01

Pos logit contributions
 sincere+0.043
 rapidly+0.042
 faint+0.042
 widen+0.041
fly+0.041
Neg logit contributions
 days-0.045
 weeks-0.039
ops-0.036
 months-0.034
 times-0.034
Token learned
Token ID4499
Feature activation+2.61e+00

Pos logit contributions
 days+0.040
 weeks+0.035
ops+0.032
 times+0.031
 nights+0.031
Neg logit contributions
 sincere-0.032
fly-0.030
 rapidly-0.030
 source-0.029
 faint-0.029
Token an
Token ID281
Feature activation-1.88e-01

Pos logit contributions
 days+0.139
 weeks+0.122
ops+0.116
 months+0.108
 times+0.107
Neg logit contributions
 sincere-0.107
 rapidly-0.106
 faint-0.106
 widen-0.104
 source-0.103
Token.
Token ID13
Feature activation-1.17e-01

Pos logit contributions
 days+0.092
 weeks+0.076
ops+0.068
 times+0.065
 months+0.064
Neg logit contributions
 sincere-0.119
 widen-0.118
 rapidly-0.118
 faint-0.117
itating-0.117
Token She
Token ID1375
Feature activation-1.09e+00

Pos logit contributions
 sincere+0.003
 rapidly+0.003
 faint+0.003
 widen+0.003
Sad+0.003
Neg logit contributions
 days-0.008
 weeks-0.007
ops-0.006
 months-0.006
 times-0.006
Token loved
Token ID6151
Feature activation-2.90e-01

Pos logit contributions
 sincere+0.039
 faint+0.038
 rapidly+0.037
Sad+0.037
 widen+0.037
Neg logit contributions
 days-0.063
 weeks-0.057
ops-0.054
 times-0.053
 months-0.052
Token to
Token ID284
Feature activation-1.92e+00

Pos logit contributions
 faint+0.008
 source+0.008
 rapidly+0.008
 sincere+0.008
 fright+0.008
Neg logit contributions
 days-0.017
ops-0.017
 weeks-0.016
 months-0.015
 times-0.014
Token have
Token ID423
Feature activation+2.26e+00

Pos logit contributions
 sincere+0.082
 faint+0.081
 widen+0.081
 rapidly+0.080
Sad+0.078
Neg logit contributions
 days-0.100
 weeks-0.088
ops-0.082
 months-0.078
 times-0.077
Token pic
Token ID8301
Feature activation+1.08e+01

Pos logit contributions
 days+0.099
ops+0.090
 weeks+0.087
 times+0.078
 months+0.077
Neg logit contributions
 faint-0.103
Sad-0.102
 rapidly-0.102
 widen-0.100
 sincere-0.099
Tokenn
Token ID77
Feature activation+5.41e+00

Pos logit contributions
 days+0.371
 weeks+0.301
ops+0.262
 months+0.248
 times+0.244
Neg logit contributions
 sincere-0.646
 rapidly-0.639
 widen-0.638
 faint-0.637
Sad-0.636
Tokenics
Token ID873
Feature activation+2.90e+00

Pos logit contributions
 days+0.289
 weeks+0.254
ops+0.234
 months+0.225
 times+0.223
Neg logit contributions
 sincere-0.222
 rapidly-0.219
 faint-0.217
 widen-0.217
itating-0.214
Token with
Token ID351
Feature activation+3.13e-01

Pos logit contributions
 days+0.155
 weeks+0.139
ops+0.136
 times+0.124
 months+0.124
Neg logit contributions
 rapidly-0.113
 sincere-0.112
 source-0.109
 faint-0.108
 widen-0.107
Token her
Token ID607
Feature activation+2.17e+00

Pos logit contributions
 days+0.017
 weeks+0.015
ops+0.014
 months+0.013
 times+0.013
Neg logit contributions
 sincere-0.013
 rapidly-0.013
 faint-0.013
 widen-0.013
Sad-0.012
Token family
Token ID1641
Feature activation+1.29e+00

Pos logit contributions
 days+0.102
 weeks+0.093
ops+0.088
 months+0.082
 times+0.080
Neg logit contributions
 sincere-0.098
 faint-0.094
 source-0.092
 rapidly-0.092
fly-0.092
Token family
Token ID1641
Feature activation+1.20e+00

Pos logit contributions
 days+0.096
 weeks+0.087
ops+0.084
 months+0.078
 times+0.078
Neg logit contributions
 sincere-0.081
 faint-0.077
 rapidly-0.075
 source-0.073
fly-0.073
Token were
Token ID547
Feature activation-1.52e-01

Pos logit contributions
 days+0.060
 weeks+0.053
ops+0.050
 times+0.049
 months+0.046
Neg logit contributions
 sincere-0.049
 rapidly-0.048
ull-0.047
 source-0.046
fly-0.046
Token ready
Token ID3492
Feature activation+4.64e+00

Pos logit contributions
 sincere+0.007
 rapidly+0.007
 faint+0.007
 widen+0.007
 source+0.006
Neg logit contributions
 days-0.008
 weeks-0.007
ops-0.006
 times-0.006
 months-0.006
Token to
Token ID284
Feature activation-2.02e+00

Pos logit contributions
 days+0.263
 weeks+0.237
ops+0.237
 times+0.216
 months+0.214
Neg logit contributions
 faint-0.165
 source-0.164
 rapidly-0.162
 widen-0.155
 sincere-0.152
Token go
Token ID467
Feature activation+5.16e+00

Pos logit contributions
 sincere+0.097
 rapidly+0.097
itating+0.097
Sad+0.096
 faint+0.095
Neg logit contributions
 days-0.093
 weeks-0.079
ops-0.073
 times-0.068
 months-0.068
Token pic
Token ID8301
Feature activation+1.07e+01

Pos logit contributions
 days+0.285
 weeks+0.258
ops+0.242
 times+0.231
 months+0.228
Neg logit contributions
 source-0.196
 rapidly-0.193
 widen-0.192
 faint-0.192
 sincere-0.191
Tokenn
Token ID77
Feature activation+5.27e+00

Pos logit contributions
 days+0.398
 weeks+0.330
ops+0.290
 times+0.276
 months+0.276
Neg logit contributions
 widen-0.605
 sincere-0.603
 source-0.603
 faint-0.602
Sad-0.601
Tokenicking
Token ID7958
Feature activation-3.04e+00

Pos logit contributions
 days+0.297
 weeks+0.264
ops+0.236
 months+0.234
 times+0.232
Neg logit contributions
itating-0.199
 rapidly-0.198
 sincere-0.196
 widen-0.196
 faint-0.195
Token again
Token ID757
Feature activation-4.28e+00

Pos logit contributions
 rapidly+0.123
 faint+0.118
 source+0.117
 widen+0.116
 fright+0.114
Neg logit contributions
 days-0.160
 weeks-0.144
ops-0.139
 months-0.126
 times-0.122
Token.
Token ID13
Feature activation-3.51e-01

Pos logit contributions
 faint+0.169
 rapidly+0.166
 source+0.164
fly+0.160
 widen+0.156
Neg logit contributions
 days-0.217
ops-0.203
 weeks-0.193
 cand-0.177
 times-0.172
Token But
Token ID887
Feature activation-6.61e-01

Pos logit contributions
 sincere+0.012
 rapidly+0.012
 faint+0.012
 widen+0.012
fly+0.011
Neg logit contributions
 days-0.021
 weeks-0.019
ops-0.018
 months-0.017
 times-0.017
Token a
Token ID257
Feature activation+9.24e-01

Pos logit contributions
 sincere+0.046
 rapidly+0.045
 faint+0.045
 widen+0.045
Sad+0.044
Neg logit contributions
 days-0.075
 weeks-0.067
ops-0.063
 months-0.060
 times-0.060
Token family
Token ID1641
Feature activation+1.20e+00

Pos logit contributions
 days+0.044
 weeks+0.038
ops+0.035
 months+0.033
 times+0.033
Neg logit contributions
 sincere-0.043
 rapidly-0.043
 widen-0.042
itating-0.042
 faint-0.042
Token who
Token ID508
Feature activation-1.08e+00

Pos logit contributions
 days+0.069
 weeks+0.064
ops+0.063
 months+0.057
 times+0.055
Neg logit contributions
ull-0.041
 sincere-0.041
fly-0.040
 faint-0.040
 source-0.040
Token really
Token ID1107
Feature activation-2.26e+00

Pos logit contributions
 sincere+0.034
 widen+0.033
 faint+0.033
 rapidly+0.032
fly+0.032
Neg logit contributions
 days-0.066
 weeks-0.061
ops-0.058
 times-0.056
 months-0.054
Token enjoyed
Token ID8359
Feature activation+7.20e-01

Pos logit contributions
 sincere+0.072
 rapidly+0.070
ff+0.070
 faint+0.069
 widen+0.069
Neg logit contributions
 days-0.134
 weeks-0.125
ops-0.115
 months-0.112
 times-0.112
Token pic
Token ID8301
Feature activation+1.07e+01

Pos logit contributions
ops+0.035
 days+0.034
 weeks+0.032
 times+0.029
 months+0.028
Neg logit contributions
 sincere-0.029
 faint-0.029
 rapidly-0.028
ull-0.027
 source-0.027
Tokenn
Token ID77
Feature activation+5.30e+00

Pos logit contributions
 days+0.376
 weeks+0.311
ops+0.266
 months+0.259
 times+0.253
Neg logit contributions
Sad-0.611
 sincere-0.611
 rapidly-0.610
 widen-0.610
 faint-0.607
Tokenics
Token ID873
Feature activation+2.79e+00

Pos logit contributions
 days+0.291
 weeks+0.257
ops+0.234
 months+0.229
 times+0.226
Neg logit contributions
 sincere-0.207
 rapidly-0.207
 faint-0.204
itating-0.204
 widen-0.203
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
 days+0.145
 weeks+0.132
ops+0.127
 months+0.116
 times+0.115
Neg logit contributions
 rapidly-0.111
 sincere-0.110
 source-0.107
 faint-0.105
fly-0.105
Token They
Token ID1119
Feature activation+7.89e-01

Pos logit contributions
 days+0.006
 weeks+0.005
ops+0.005
 months+0.004
 day+0.004
Neg logit contributions
 sincere-0.004
 rapidly-0.004
itating-0.004
fly-0.004
 widen-0.004
Token loved
Token ID6151
Feature activation-3.99e-01

Pos logit contributions
 days+0.047
ops+0.044
 weeks+0.043
 times+0.040
 choices+0.039
Neg logit contributions
 rapidly-0.023
 sincere-0.023
ull-0.022
fly-0.021
 widen-0.021
Token They
Token ID1119
Feature activation+4.10e-01

Pos logit contributions
 sincere+0.008
 rapidly+0.008
 widen+0.007
 faint+0.007
fly+0.007
Neg logit contributions
 days-0.014
 weeks-0.012
ops-0.012
 months-0.011
 times-0.011
Token missed
Token ID6825
Feature activation-2.27e+00

Pos logit contributions
 days+0.021
 weeks+0.018
ops+0.017
 months+0.016
 times+0.016
Neg logit contributions
 sincere-0.018
 rapidly-0.018
 faint-0.018
 widen-0.018
Sad-0.017
Token their
Token ID511
Feature activation+1.48e+00

Pos logit contributions
 sincere+0.083
 faint+0.081
 rapidly+0.080
 fright+0.080
 source+0.077
Neg logit contributions
 days-0.119
ops-0.118
 weeks-0.109
 months-0.096
 cand-0.094
Token walks
Token ID11114
Feature activation+5.00e+00

Pos logit contributions
ops+0.072
 days+0.071
 weeks+0.065
 months+0.059
mm+0.057
Neg logit contributions
 faint-0.060
 source-0.060
 sincere-0.058
 fright-0.056
 rapidly-0.055
Token and
Token ID290
Feature activation+1.48e+00

Pos logit contributions
 days+0.244
 weeks+0.218
ops+0.216
 times+0.194
 months+0.191
Neg logit contributions
 rapidly-0.210
fly-0.204
 source-0.201
itating-0.199
 faint-0.198
Token pic
Token ID8301
Feature activation+1.06e+01

Pos logit contributions
 days+0.075
ops+0.074
 weeks+0.068
ip+0.062
 cents+0.060
Neg logit contributions
 sincere-0.058
 faint-0.058
 fright-0.056
fly-0.054
 source-0.054
Tokenn
Token ID77
Feature activation+5.19e+00

Pos logit contributions
 days+0.385
 weeks+0.318
ops+0.280
 months+0.270
 times+0.260
Neg logit contributions
Sad-0.608
 sincere-0.605
 rapidly-0.602
 widen-0.599
 faint-0.594
Tokenics
Token ID873
Feature activation+2.72e+00

Pos logit contributions
 days+0.292
 weeks+0.258
ops+0.237
 months+0.231
 times+0.230
Neg logit contributions
 sincere-0.197
 rapidly-0.195
 faint-0.192
 widen-0.191
Sad-0.191
Token near
Token ID1474
Feature activation-3.52e+00

Pos logit contributions
 days+0.139
 weeks+0.125
ops+0.125
 times+0.111
 months+0.111
Neg logit contributions
 rapidly-0.109
 sincere-0.106
fly-0.105
 source-0.103
 fright-0.102
Token the
Token ID262
Feature activation+1.84e+00

Pos logit contributions
 faint+0.141
 sincere+0.140
 rapidly+0.138
 source+0.137
 widen+0.135
Neg logit contributions
 days-0.185
 weeks-0.164
ops-0.162
 months-0.145
 times-0.143
Token cliff
Token ID19516
Feature activation-4.60e-01

Pos logit contributions
 days+0.105
 weeks+0.093
ops+0.086
 months+0.083
 times+0.083
Neg logit contributions
 sincere-0.071
Sad-0.069
 rapidly-0.069
 widen-0.069
 faint-0.068
Token favourite
Token ID12507
Feature activation+7.89e-01

Pos logit contributions
 days+0.070
ops+0.066
 weeks+0.064
 months+0.057
 times+0.054
Neg logit contributions
 faint-0.057
 sincere-0.056
 source-0.056
 rapidly-0.054
fly-0.053
Token place
Token ID1295
Feature activation+1.17e+00

Pos logit contributions
ops+0.035
 days+0.035
 weeks+0.033
ip+0.030
 months+0.029
Neg logit contributions
 source-0.033
 faint-0.033
 rapidly-0.032
 fright-0.032
fly-0.031
Token to
Token ID284
Feature activation-2.09e+00

Pos logit contributions
 days+0.058
 weeks+0.052
ops+0.049
 months+0.045
 times+0.045
Neg logit contributions
 faint-0.050
 rapidly-0.050
 sincere-0.049
 source-0.049
fly-0.049
Token go
Token ID467
Feature activation+5.11e+00

Pos logit contributions
 sincere+0.084
 faint+0.083
 rapidly+0.083
 widen+0.083
 source+0.080
Neg logit contributions
 days-0.112
 weeks-0.099
ops-0.094
 months-0.088
 times-0.087
Token for
Token ID329
Feature activation+2.46e+00

Pos logit contributions
 days+0.264
 weeks+0.235
ops+0.228
 times+0.208
 months+0.204
Neg logit contributions
 rapidly-0.214
 faint-0.212
 source-0.210
 sincere-0.209
 widen-0.208
Token pic
Token ID8301
Feature activation+1.06e+01

Pos logit contributions
 days+0.126
ops+0.124
 weeks+0.113
 times+0.104
ip+0.102
Neg logit contributions
 faint-0.090
 sincere-0.087
 fright-0.086
 rapidly-0.086
 source-0.084
Tokenn
Token ID77
Feature activation+5.26e+00

Pos logit contributions
 days+0.390
 weeks+0.324
ops+0.287
 months+0.275
 times+0.275
Neg logit contributions
 widen-0.593
Sad-0.592
 rapidly-0.590
 faint-0.588
 source-0.585
Tokenics
Token ID873
Feature activation+2.71e+00

Pos logit contributions
 days+0.270
 weeks+0.236
ops+0.212
 months+0.207
 times+0.205
Neg logit contributions
 rapidly-0.224
itating-0.223
 sincere-0.222
 faint-0.222
 widen-0.221
Token.
Token ID13
Feature activation-4.49e-01

Pos logit contributions
 days+0.143
 weeks+0.128
ops+0.127
 times+0.114
 months+0.113
Neg logit contributions
 rapidly-0.105
 source-0.101
 sincere-0.101
fly-0.100
 faint-0.099
Token<|endoftext|>
Token ID50256
Feature activation+2.27e+00

Pos logit contributions
 sincere+0.014
 rapidly+0.014
 faint+0.013
 widen+0.013
Sad+0.013
Neg logit contributions
 days-0.029
 weeks-0.026
ops-0.024
 months-0.023
 times-0.023
TokenOnce
Token ID7454
Feature activation+6.45e+00

Pos logit contributions
 days+0.130
 weeks+0.116
ops+0.108
 times+0.105
 months+0.103
Neg logit contributions
 sincere-0.082
 rapidly-0.081
 faint-0.081
 widen-0.080
 source-0.080
Token be
Token ID307
Feature activation+4.06e-01

Pos logit contributions
 sincere+0.022
 faint+0.021
 widen+0.021
fly+0.021
 source+0.020
Neg logit contributions
 days-0.035
ops-0.032
 weeks-0.032
 months-0.028
 times-0.028
Token there
Token ID612
Feature activation-2.51e-01

Pos logit contributions
 days+0.024
ops+0.022
 weeks+0.021
 times+0.019
 months+0.019
Neg logit contributions
 sincere-0.014
 faint-0.014
 rapidly-0.014
Sad-0.014
 widen-0.014
Token to
Token ID284
Feature activation-2.12e+00

Pos logit contributions
 faint+0.010
 rapidly+0.010
 source+0.010
fly+0.009
 sincere+0.009
Neg logit contributions
 days-0.012
ops-0.012
 weeks-0.011
 cand-0.010
 times-0.010
Token support
Token ID1104
Feature activation+2.38e+00

Pos logit contributions
 sincere+0.088
 rapidly+0.088
 faint+0.087
 widen+0.087
itating+0.086
Neg logit contributions
 days-0.111
 weeks-0.097
ops-0.089
 times-0.086
 months-0.086
Token her
Token ID607
Feature activation+1.70e+00

Pos logit contributions
 days+0.125
 weeks+0.111
ops+0.108
 months+0.098
 times+0.096
Neg logit contributions
 rapidly-0.095
 faint-0.095
 sincere-0.094
Sad-0.092
 widen-0.092
Token pic
Token ID8301
Feature activation+1.06e+01

Pos logit contributions
 days+0.085
ops+0.080
 weeks+0.078
 months+0.068
 nights+0.064
Neg logit contributions
 faint-0.069
 sincere-0.068
 source-0.067
fly-0.066
 rapidly-0.064
Tokenn
Token ID77
Feature activation+5.11e+00

Pos logit contributions
 days+0.376
 weeks+0.312
ops+0.285
 months+0.262
 times+0.254
Neg logit contributions
 sincere-0.604
Sad-0.604
 faint-0.602
 rapidly-0.602
 widen-0.599
Tokenics
Token ID873
Feature activation+2.64e+00

Pos logit contributions
 days+0.291
 weeks+0.260
 months+0.233
ops+0.229
 times+0.228
Neg logit contributions
itating-0.191
 rapidly-0.186
 sincere-0.186
 faint-0.185
 widen-0.184
Token--
Token ID438
Feature activation-1.97e+00

Pos logit contributions
 days+0.135
ops+0.125
 weeks+0.121
 months+0.107
 times+0.104
Neg logit contributions
 rapidly-0.103
 source-0.100
fly-0.099
 sincere-0.098
 faint-0.097
Tokenno
Token ID3919
Feature activation+1.38e+00

Pos logit contributions
itating+0.068
 rapidly+0.067
Sad+0.067
 faint+0.066
 sincere+0.066
Neg logit contributions
 days-0.120
 weeks-0.106
ops-0.100
 months-0.096
 times-0.095
Token matter
Token ID2300
Feature activation+2.82e-02

Pos logit contributions
 days+0.058
 weeks+0.051
ops+0.051
 cand+0.048
 nights+0.046
Neg logit contributions
 faint-0.060
 sincere-0.060
 fright-0.058
Sad-0.058
ull-0.058
Token see
Token ID766
Feature activation-3.28e+00

Pos logit contributions
 sincere+0.082
 rapidly+0.080
 faint+0.080
 widen+0.080
 source+0.078
Neg logit contributions
 days-0.106
 weeks-0.094
ops-0.088
 months-0.083
 times-0.083
Token the
Token ID262
Feature activation+1.72e+00

Pos logit contributions
 sincere+0.138
 faint+0.136
 rapidly+0.136
 widen+0.134
 source+0.132
Neg logit contributions
 days-0.171
 weeks-0.151
ops-0.145
 months-0.133
 times-0.131
Token bird
Token ID6512
Feature activation-4.70e+00

Pos logit contributions
 days+0.096
 weeks+0.084
ops+0.078
 months+0.075
 times+0.075
Neg logit contributions
 sincere-0.068
 rapidly-0.067
 faint-0.066
 widen-0.066
Sad-0.065
Token and
Token ID290
Feature activation+1.70e+00

Pos logit contributions
fly+0.201
 sincere+0.193
 faint+0.192
 widen+0.192
 source+0.188
Neg logit contributions
 days-0.253
 weeks-0.227
ops-0.210
 months-0.199
 times-0.193
Token have
Token ID423
Feature activation+1.91e+00

Pos logit contributions
 days+0.087
 weeks+0.077
ops+0.075
 times+0.068
 months+0.067
Neg logit contributions
 sincere-0.072
 faint-0.072
fly-0.071
 rapidly-0.071
 widen-0.070
Token pic
Token ID8301
Feature activation+1.06e+01

Pos logit contributions
 days+0.095
 weeks+0.083
ops+0.080
 times+0.073
 months+0.073
Neg logit contributions
 sincere-0.083
 faint-0.082
 rapidly-0.082
 widen-0.081
Sad-0.080
Tokenn
Token ID77
Feature activation+5.22e+00

Pos logit contributions
 days+0.367
 weeks+0.299
ops+0.264
 months+0.250
 times+0.246
Neg logit contributions
 sincere-0.618
 widen-0.616
Sad-0.612
 rapidly-0.612
 faint-0.610
Tokenics
Token ID873
Feature activation+2.68e+00

Pos logit contributions
 days+0.292
 weeks+0.259
ops+0.233
 months+0.233
 times+0.230
Neg logit contributions
 sincere-0.201
 rapidly-0.198
itating-0.198
Sad-0.196
 faint-0.195
Token.
Token ID13
Feature activation-1.36e-01

Pos logit contributions
 days+0.137
 weeks+0.124
ops+0.124
 times+0.111
 months+0.110
Neg logit contributions
 rapidly-0.106
 sincere-0.104
 source-0.103
fly-0.102
 faint-0.099
Token<|endoftext|>
Token ID50256
Feature activation+2.28e+00

Pos logit contributions
Sad+0.003
 sincere+0.003
 faint+0.003
 widen+0.003
 rapidly+0.003
Neg logit contributions
 days-0.009
 weeks-0.008
ops-0.008
 times-0.008
 months-0.008
TokenOnce
Token ID7454
Feature activation+6.42e+00

Pos logit contributions
 days+0.127
 weeks+0.110
ops+0.103
 months+0.098
 day+0.097
Neg logit contributions
 sincere-0.093
 rapidly-0.091
 widen-0.089
 faint-0.089
fly-0.089
Token and
Token ID290
Feature activation+1.77e+00

Pos logit contributions
Sad+0.301
 sincere+0.293
itating+0.288
Jud+0.288
fly+0.286
Neg logit contributions
 days-0.171
 weeks-0.137
 times-0.111
 later-0.110
 months-0.109
Token nodded
Token ID14464
Feature activation-6.73e+00

Pos logit contributions
 days+0.099
 weeks+0.088
ops+0.084
 times+0.079
 months+0.078
Neg logit contributions
 rapidly-0.068
 sincere-0.068
 faint-0.067
 startled-0.065
 widen-0.065
Token.
Token ID13
Feature activation+3.25e-02

Pos logit contributions
itating+0.345
 sincere+0.343
Sad+0.342
 widen+0.338
 rapidly+0.337
Neg logit contributions
 days-0.293
 weeks-0.246
ops-0.210
 times-0.209
 months-0.207
Token He
Token ID679
Feature activation-1.71e+00

Pos logit contributions
 days+0.002
 weeks+0.002
ops+0.002
 months+0.002
 times+0.002
Neg logit contributions
 sincere-0.001
 rapidly-0.001
 widen-0.001
 faint-0.001
fly-0.001
Token loved
Token ID6151
Feature activation-6.04e-01

Pos logit contributions
 rapidly+0.068
 faint+0.066
 sincere+0.065
 widen+0.064
 startled+0.064
Neg logit contributions
 days-0.092
 weeks-0.080
ops-0.076
 times-0.074
 months-0.072
Token pic
Token ID8301
Feature activation+1.05e+01

Pos logit contributions
 faint+0.022
 rapidly+0.021
 fright+0.020
 sincere+0.020
 source+0.020
Neg logit contributions
ops-0.034
 days-0.032
 weeks-0.029
 months-0.027
 times-0.026
Tokenn
Token ID77
Feature activation+5.26e+00

Pos logit contributions
 days+0.322
 weeks+0.251
ops+0.223
 times+0.193
 months+0.191
Neg logit contributions
 sincere-0.678
 rapidly-0.670
 faint-0.667
 widen-0.664
fly-0.660
Tokenics
Token ID873
Feature activation+2.68e+00

Pos logit contributions
 days+0.289
 weeks+0.256
ops+0.233
 months+0.229
 times+0.224
Neg logit contributions
 sincere-0.208
 rapidly-0.207
itating-0.205
 faint-0.204
 widen-0.204
Token and
Token ID290
Feature activation+1.83e+00

Pos logit contributions
 days+0.136
 weeks+0.122
ops+0.119
 months+0.108
 times+0.106
Neg logit contributions
 rapidly-0.112
 source-0.107
 faint-0.105
 sincere-0.105
fly-0.104
Token couldn
Token ID3521
Feature activation+3.31e+00

Pos logit contributions
 days+0.095
ops+0.092
 weeks+0.087
 times+0.078
 months+0.076
Neg logit contributions
 faint-0.067
 rapidly-0.066
 startled-0.065
 aw-0.064
 sincere-0.063
Token't
Token ID470
Feature activation-3.50e+00

Pos logit contributions
 days+0.222
 weeks+0.201
ops+0.193
 months+0.183
 times+0.182
Neg logit contributions
 sincere-0.091
 rapidly-0.088
 faint-0.087
 widen-0.086
Sad-0.085
Token squ
Token ID2809
Feature activation-2.75e+00

Pos logit contributions
Sad+0.064
itating+0.064
Maria+0.063
Jud+0.063
anne+0.063
Neg logit contributions
 days-0.088
 weeks-0.079
 months-0.069
 times-0.068
 later-0.067
Tokenaw
Token ID707
Feature activation-2.75e+00

Pos logit contributions
 sincere+0.106
 rapidly+0.104
 widen+0.103
 faint+0.103
itating+0.101
Neg logit contributions
 days-0.156
 weeks-0.137
ops-0.128
 months-0.122
 times-0.122
Tokenking
Token ID3364
Feature activation-5.87e+00

Pos logit contributions
 sincere+0.090
 rapidly+0.089
 widen+0.088
 faint+0.088
fly+0.086
Neg logit contributions
 days-0.172
 weeks-0.154
ops-0.142
 months-0.139
 times-0.139
Token and
Token ID290
Feature activation+1.65e+00

Pos logit contributions
 sincere+0.269
 faint+0.262
 rapidly+0.262
Sad+0.262
 widen+0.262
Neg logit contributions
 days-0.286
 weeks-0.247
ops-0.227
 times-0.216
 months-0.215
Token his
Token ID465
Feature activation+1.64e+00

Pos logit contributions
 days+0.088
 weeks+0.077
ops+0.072
 months+0.068
 times+0.068
Neg logit contributions
 sincere-0.068
 rapidly-0.067
 faint-0.066
 widen-0.066
fly-0.065
Tokensing
Token ID12215
Feature activation-1.14e+01

Pos logit contributions
 days+0.098
 weeks+0.088
ops+0.082
 months+0.079
 times+0.078
Neg logit contributions
 sincere-0.057
 rapidly-0.055
 faint-0.055
 widen-0.055
Sad-0.054
Token.
Token ID13
Feature activation-2.29e-01

Pos logit contributions
 rapidly+0.446
 sincere+0.443
 faint+0.443
fly+0.431
 widen+0.430
Neg logit contributions
 days-0.619
 weeks-0.555
ops-0.524
 months-0.496
 times-0.471
Token He
Token ID679
Feature activation-2.05e+00

Pos logit contributions
fly+0.009
 sincere+0.008
 rapidly+0.008
itating+0.008
 faint+0.008
Neg logit contributions
 days-0.013
 weeks-0.012
 months-0.011
ops-0.011
 times-0.010
Token had
Token ID550
Feature activation+1.52e+00

Pos logit contributions
 sincere+0.095
 widen+0.095
itating+0.094
Sad+0.094
 faint+0.093
Neg logit contributions
 days-0.097
 weeks-0.085
ops-0.078
 months-0.073
 times-0.073
Token forgotten
Token ID11564
Feature activation-9.67e-01

Pos logit contributions
 days+0.084
 weeks+0.074
ops+0.068
 months+0.066
 times+0.066
Neg logit contributions
 sincere-0.059
 rapidly-0.058
 widen-0.058
itating-0.058
fly-0.058
Token to
Token ID284
Feature activation-2.15e+00

Pos logit contributions
 sincere+0.039
 rapidly+0.038
 faint+0.038
 widen+0.037
Sad+0.037
Neg logit contributions
 days-0.053
 weeks-0.047
ops-0.044
 months-0.041
 times-0.041
Token iron
Token ID6953
Feature activation-1.36e+00

Pos logit contributions
fly+0.047
 sincere+0.047
 rapidly+0.047
itating+0.046
Sad+0.046
Neg logit contributions
 days-0.074
 weeks-0.065
ops-0.061
 times-0.059
 months-0.058
Token made
Token ID925
Feature activation+6.19e-01

Pos logit contributions
 rapidly+0.053
 sincere+0.053
 faint+0.052
 widen+0.052
fly+0.051
Neg logit contributions
 days-0.075
 weeks-0.066
ops-0.060
 months-0.059
 times-0.058
Token a
Token ID257
Feature activation+4.55e-01

Pos logit contributions
 days+0.034
 weeks+0.030
ops+0.027
 times+0.026
 months+0.026
Neg logit contributions
 sincere-0.025
itating-0.025
fly-0.025
 rapidly-0.025
 widen-0.024
Token loud
Token ID7812
Feature activation-4.91e+00

Pos logit contributions
 days+0.025
 weeks+0.021
 times+0.021
 things+0.020
 day+0.020
Neg logit contributions
anne-0.017
Jud-0.017
ff-0.016
Sad-0.016
itating-0.016
Token his
Token ID465
Feature activation+1.54e+00

Pos logit contributions
 sincere+0.159
itating+0.151
 rapidly+0.150
Sad+0.148
 widen+0.147
Neg logit contributions
 days-0.307
 weeks-0.273
ops-0.259
 times-0.253
 months-0.247
Tokensing
Token ID12215
Feature activation-1.14e+01

Pos logit contributions
 days+0.094
 weeks+0.081
ops+0.078
 times+0.077
 day+0.073
Neg logit contributions
itating-0.053
 sincere-0.053
Jud-0.053
Sad-0.053
 rapidly-0.052
Token sound
Token ID2128
Feature activation-5.41e+00

Pos logit contributions
 faint+0.361
 rapidly+0.359
 widen+0.347
 sincere+0.340
fly+0.335
Neg logit contributions
 days-0.705
 weeks-0.642
ops-0.614
 months-0.583
 nights-0.556
Token and
Token ID290
Feature activation+1.49e+00

Pos logit contributions
 sincere+0.280
 rapidly+0.271
Sad+0.271
 faint+0.270
itating+0.269
Neg logit contributions
 days-0.235
 weeks-0.199
ops-0.181
 times-0.171
 months-0.169
Token steam
Token ID13324
Feature activation-3.64e-01

Pos logit contributions
 days+0.082
 weeks+0.072
ops+0.064
 months+0.064
 times+0.064
Neg logit contributions
itating-0.060
Sad-0.059
 sincere-0.059
 rapidly-0.058
 widen-0.057
Token came
Token ID1625
Feature activation-2.48e+00

Pos logit contributions
 rapidly+0.013
 sincere+0.013
 widen+0.013
 faint+0.013
fly+0.013
Neg logit contributions
 days-0.021
 weeks-0.019
ops-0.017
 months-0.017
 times-0.016
Token out
Token ID503
Feature activation-8.04e+00

Pos logit contributions
 sincere+0.102
 perplex+0.092
Sad+0.088
anne+0.087
itating+0.086
Neg logit contributions
 days-0.139
 weeks-0.121
 later-0.114
 times-0.111
 things-0.110
Token the
Token ID262
Feature activation+1.75e+00

Pos logit contributions
 sincere+0.011
 faint+0.011
 rapidly+0.011
 widen+0.011
 source+0.010
Neg logit contributions
 days-0.011
 weeks-0.010
ops-0.009
 times-0.009
 months-0.008
Token iron
Token ID6953
Feature activation-1.43e+00

Pos logit contributions
 days+0.109
 weeks+0.099
ops+0.094
 months+0.089
 times+0.088
Neg logit contributions
 sincere-0.056
 faint-0.055
 rapidly-0.054
 widen-0.054
 source-0.054
Token made
Token ID925
Feature activation+6.13e-01

Pos logit contributions
 sincere+0.058
 rapidly+0.057
 faint+0.057
 widen+0.057
fly+0.055
Neg logit contributions
 days-0.077
 weeks-0.068
ops-0.062
 months-0.060
 times-0.060
Token a
Token ID257
Feature activation+4.68e-01

Pos logit contributions
 days+0.034
 weeks+0.030
ops+0.028
 times+0.027
 months+0.027
Neg logit contributions
 sincere-0.024
 rapidly-0.024
itating-0.023
fly-0.023
 widen-0.023
Token his
Token ID465
Feature activation+1.64e+00

Pos logit contributions
 days+0.026
 weeks+0.023
 times+0.022
 things+0.021
 day+0.021
Neg logit contributions
ull-0.016
anne-0.016
Jud-0.016
ff-0.016
 sincere-0.016
Tokensing
Token ID12215
Feature activation-1.13e+01

Pos logit contributions
 days+0.096
 weeks+0.084
ops+0.079
 times+0.077
 months+0.075
Neg logit contributions
 sincere-0.060
 rapidly-0.059
Sad-0.058
 widen-0.058
itating-0.058
Token sound
Token ID2128
Feature activation-5.49e+00

Pos logit contributions
 faint+0.339
 rapidly+0.338
 widen+0.330
 sincere+0.323
 source+0.316
Neg logit contributions
 days-0.727
 weeks-0.662
ops-0.631
 months-0.601
 times-0.577
Token and
Token ID290
Feature activation+1.67e+00

Pos logit contributions
 sincere+0.284
Sad+0.273
itating+0.271
 rapidly+0.270
fly+0.269
Neg logit contributions
 days-0.241
 weeks-0.204
ops-0.187
 times-0.177
 months-0.174
Token steam
Token ID13324
Feature activation-4.10e-01

Pos logit contributions
 days+0.087
 weeks+0.076
ops+0.067
 months+0.067
 times+0.066
Neg logit contributions
itating-0.073
 sincere-0.072
Sad-0.071
 widen-0.070
 rapidly-0.070
Token came
Token ID1625
Feature activation-2.46e+00

Pos logit contributions
 sincere+0.016
 rapidly+0.015
 faint+0.015
 widen+0.015
Sad+0.015
Neg logit contributions
 days-0.023
 weeks-0.020
ops-0.019
 months-0.018
 times-0.018
Token out
Token ID503
Feature activation-8.08e+00

Pos logit contributions
 sincere+0.098
 perplex+0.087
Sad+0.084
anne+0.083
itating+0.082
Neg logit contributions
 days-0.140
 weeks-0.122
 later-0.113
 times-0.112
ops-0.109
Token lava
Token ID28856
Feature activation-4.10e+00

Pos logit contributions
 days+0.095
 weeks+0.082
 times+0.075
 months+0.075
 day+0.074
Neg logit contributions
Sad-0.060
itating-0.057
 sincere-0.057
Jud-0.056
 rapidly-0.055
Token bub
Token ID10015
Feature activation+1.23e+00

Pos logit contributions
 rapidly+0.179
 widen+0.178
 sincere+0.177
 faint+0.177
fly+0.175
Neg logit contributions
 days-0.208
 weeks-0.182
ops-0.168
 months-0.159
 times-0.157
Tokenbling
Token ID11108
Feature activation-2.60e+00

Pos logit contributions
 days+0.076
 weeks+0.068
ops+0.064
 months+0.061
 times+0.060
Neg logit contributions
 sincere-0.041
 faint-0.039
Sad-0.039
 rapidly-0.038
 widen-0.038
Token and
Token ID290
Feature activation+1.47e+00

Pos logit contributions
 rapidly+0.111
 widen+0.107
 faint+0.106
 source+0.105
fly+0.105
Neg logit contributions
 days-0.136
 weeks-0.120
ops-0.116
 months-0.106
 times-0.103
Token his
Token ID465
Feature activation+1.56e+00

Pos logit contributions
 days+0.076
 weeks+0.066
ops+0.059
 months+0.058
 times+0.058
Neg logit contributions
 sincere-0.064
itating-0.063
 widen-0.063
Sad-0.063
 rapidly-0.062
Tokensing
Token ID12215
Feature activation-1.13e+01

Pos logit contributions
 days+0.091
 weeks+0.080
ops+0.075
 times+0.072
 months+0.071
Neg logit contributions
Sad-0.057
itating-0.057
 sincere-0.057
 widen-0.056
 rapidly-0.056
Token.
Token ID13
Feature activation-4.83e-01

Pos logit contributions
 rapidly+0.437
 sincere+0.436
 faint+0.434
 widen+0.427
fly+0.419
Neg logit contributions
 days-0.628
 weeks-0.560
ops-0.530
 months-0.498
 times-0.488
Token It
Token ID632
Feature activation-6.43e+00

Pos logit contributions
fly+0.018
Sad+0.018
 faint+0.018
 widen+0.018
itating+0.018
Neg logit contributions
 days-0.028
 weeks-0.025
 months-0.022
ops-0.022
 times-0.021
Token was
Token ID373
Feature activation-1.69e+00

Pos logit contributions
 sincere+0.398
itating+0.394
icker+0.380
amus+0.377
Sad+0.376
Neg logit contributions
 days-0.226
 weeks-0.183
 months-0.150
ops-0.150
 day-0.142
Token so
Token ID523
Feature activation+1.73e+00

Pos logit contributions
itating+0.087
Sad+0.084
anne+0.083
 sincere+0.082
icker+0.079
Neg logit contributions
 days-0.081
 weeks-0.071
 months-0.060
 day-0.059
 times-0.057
Token hot
Token ID3024
Feature activation-2.86e+00

Pos logit contributions
 days+0.089
 weeks+0.075
 day+0.069
 times+0.067
 months+0.067
Neg logit contributions
fly-0.083
itating-0.082
Sad-0.081
 sincere-0.080
bird-0.079
Token faster
Token ID5443
Feature activation-1.39e+00

Pos logit contributions
 days+0.092
ops+0.088
 weeks+0.083
 cand+0.078
 times+0.075
Neg logit contributions
 rapidly-0.041
Sad-0.039
 faint-0.038
itating-0.038
 widen-0.037
Token it
Token ID340
Feature activation-1.86e+00

Pos logit contributions
 rapidly+0.055
 startled+0.051
 faint+0.049
anne+0.047
 flashes+0.047
Neg logit contributions
 days-0.062
ops-0.060
 weeks-0.056
atmeal-0.055
 cand-0.054
Token went
Token ID1816
Feature activation+6.17e+00

Pos logit contributions
 rapidly+0.069
 startled+0.068
 faint+0.062
 widen+0.062
 fright+0.062
Neg logit contributions
 days-0.104
 weeks-0.093
ops-0.088
 months-0.084
 times-0.082
Token.
Token ID13
Feature activation-5.36e-01

Pos logit contributions
 days+0.336
 weeks+0.301
ops+0.286
 months+0.263
 times+0.263
Neg logit contributions
 rapidly-0.256
 source-0.243
itating-0.241
 widen-0.240
 startled-0.239
Token Jo
Token ID5302
Feature activation-2.36e+00

Pos logit contributions
 sincere+0.017
 rapidly+0.016
 widen+0.016
fly+0.016
 faint+0.015
Neg logit contributions
 days-0.035
 weeks-0.031
ops-0.029
 months-0.028
 times-0.028
Tokenanne
Token ID21952
Feature activation-1.13e+01

Pos logit contributions
 sincere+0.056
 widen+0.052
 faint+0.050
 rapidly+0.050
 source+0.048
Neg logit contributions
 days-0.173
 weeks-0.156
ops-0.149
 times-0.144
 months-0.143
Token began
Token ID2540
Feature activation-2.21e+00

Pos logit contributions
 rapidly+0.452
fly+0.431
 startled+0.431
 sincere+0.422
 faint+0.420
Neg logit contributions
 days-0.612
 weeks-0.541
ops-0.493
 months-0.481
 times-0.478
Token to
Token ID284
Feature activation-2.17e+00

Pos logit contributions
 rapidly+0.069
 faint+0.068
 source+0.068
 startled+0.065
 fright+0.065
Neg logit contributions
 days-0.140
 weeks-0.127
ops-0.126
 months-0.115
 times-0.113
Token g
Token ID308
Feature activation-2.86e+00

Pos logit contributions
 widen+0.075
 rapidly+0.074
 faint+0.074
 sincere+0.074
 source+0.073
Neg logit contributions
 days-0.134
 weeks-0.119
ops-0.113
 months-0.107
 times-0.104
Tokeniggle
Token ID24082
Feature activation-5.65e+00

Pos logit contributions
fly+0.110
Sad+0.106
 source+0.105
 faint+0.100
 widen+0.100
Neg logit contributions
 days-0.168
 weeks-0.148
ops-0.144
 times-0.138
 months-0.130
Token with
Token ID351
Feature activation+4.18e-02

Pos logit contributions
 rapidly+0.254
 faint+0.241
 widen+0.240
 sincere+0.239
 source+0.235
Neg logit contributions
 days-0.288
 weeks-0.253
ops-0.245
 months-0.222
 nights-0.215
Token head
Token ID1182
Feature activation-4.33e+00

Pos logit contributions
 sincere+0.089
Sad+0.088
itating+0.086
 widen+0.084
 rapidly+0.084
Neg logit contributions
 days-0.110
 weeks-0.094
 times-0.087
ops-0.085
 months-0.082
Token and
Token ID290
Feature activation+1.71e+00

Pos logit contributions
 sincere+0.201
 rapidly+0.197
 faint+0.197
 widen+0.196
Sad+0.194
Neg logit contributions
 days-0.208
 weeks-0.180
ops-0.166
 months-0.156
 times-0.156
Token made
Token ID925
Feature activation+5.98e-01

Pos logit contributions
 days+0.093
 weeks+0.082
ops+0.075
 months+0.072
 times+0.072
Neg logit contributions
 sincere-0.070
 rapidly-0.068
 widen-0.068
 faint-0.068
Sad-0.067
Token a
Token ID257
Feature activation+5.75e-01

Pos logit contributions
 days+0.034
 weeks+0.031
ops+0.029
 months+0.027
 times+0.027
Neg logit contributions
 sincere-0.022
 rapidly-0.022
 faint-0.022
 widen-0.021
Sad-0.021
Token his
Token ID465
Feature activation+1.55e+00

Pos logit contributions
 days+0.033
 weeks+0.029
 times+0.028
 things+0.027
ops+0.027
Neg logit contributions
Sad-0.020
itating-0.020
 sincere-0.020
idget-0.019
ull-0.019
Tokensing
Token ID12215
Feature activation-1.13e+01

Pos logit contributions
 days+0.100
 weeks+0.089
ops+0.084
 times+0.082
 months+0.081
Neg logit contributions
 sincere-0.047
Sad-0.047
itating-0.046
 rapidly-0.046
 widen-0.046
Token sound
Token ID2128
Feature activation-5.38e+00

Pos logit contributions
 faint+0.326
 rapidly+0.321
 widen+0.307
 sincere+0.306
fly+0.301
Neg logit contributions
 days-0.736
 weeks-0.679
ops-0.654
 months-0.618
 nights-0.588
Token.
Token ID13
Feature activation-1.22e-01

Pos logit contributions
 sincere+0.273
Sad+0.266
 rapidly+0.265
 faint+0.264
itating+0.264
Neg logit contributions
 days-0.237
 weeks-0.201
ops-0.183
 times-0.173
 months-0.171
Token Tom
Token ID4186
Feature activation+1.43e+00

Pos logit contributions
 sincere+0.005
fly+0.005
 rapidly+0.005
 faint+0.005
Sad+0.005
Neg logit contributions
 days-0.007
 weeks-0.006
ops-0.006
 months-0.005
 times-0.005
Token and
Token ID290
Feature activation+1.73e+00

Pos logit contributions
 days+0.066
 weeks+0.057
ops+0.052
 months+0.049
 times+0.049
Neg logit contributions
 rapidly-0.069
 sincere-0.069
 faint-0.068
 widen-0.068
fly-0.067
Token Sam
Token ID3409
Feature activation+1.30e+00

Pos logit contributions
 days+0.109
 weeks+0.097
ops+0.092
 months+0.088
 times+0.088
Neg logit contributions
 sincere-0.056
 rapidly-0.055
 faint-0.054
 widen-0.054
Sad-0.053
Token!
Token ID0
Feature activation-1.12e+00

Pos logit contributions
 faint+0.067
 sincere+0.067
 rapidly+0.067
fly+0.066
 source+0.066
Neg logit contributions
 days-0.075
 weeks-0.066
ops-0.059
 months-0.057
 times-0.056
Token The
Token ID383
Feature activation-1.11e+00

Pos logit contributions
 sincere+0.048
 widen+0.047
itating+0.047
 rapidly+0.047
fly+0.047
Neg logit contributions
 days-0.056
 weeks-0.048
ops-0.046
 day-0.044
 months-0.043
Token cat
Token ID3797
Feature activation-1.18e+00

Pos logit contributions
 rapidly+0.056
itating+0.055
 sincere+0.055
 widen+0.055
fly+0.054
Neg logit contributions
 days-0.052
 weeks-0.043
ops-0.038
 times-0.037
 months-0.037
Token was
Token ID373
Feature activation-1.45e+00

Pos logit contributions
 widen+0.064
itating+0.063
 source+0.063
icker+0.063
 sincere+0.062
Neg logit contributions
 days-0.045
 weeks-0.038
ops-0.036
 months-0.031
 times-0.030
Token his
Token ID465
Feature activation+1.70e+00

Pos logit contributions
icker+0.075
anne+0.074
isel+0.072
ff+0.071
 fuse+0.070
Neg logit contributions
 days-0.055
 day-0.044
 weeks-0.044
 next-0.042
 things-0.039
Tokensing
Token ID12215
Feature activation-1.13e+01

Pos logit contributions
 days+0.084
 weeks+0.070
ops+0.067
 times+0.064
 day+0.064
Neg logit contributions
 rapidly-0.076
Sad-0.076
 sincere-0.075
 widen-0.075
ull-0.073
Token and
Token ID290
Feature activation+1.69e+00

Pos logit contributions
 rapidly+0.557
 faint+0.556
 sincere+0.552
 widen+0.541
fly+0.539
Neg logit contributions
 days-0.502
 weeks-0.436
ops-0.414
 months-0.379
 times-0.363
Token grow
Token ID1663
Feature activation-1.72e+00

Pos logit contributions
 days+0.082
 weeks+0.071
ops+0.064
 times+0.062
 months+0.061
Neg logit contributions
 widen-0.076
Sad-0.075
itating-0.075
 source-0.074
 sincere-0.074
Tokenling
Token ID1359
Feature activation-7.15e+00

Pos logit contributions
Sad+0.097
 sincere+0.097
 source+0.095
 faint+0.095
 widen+0.094
Neg logit contributions
 days-0.064
 weeks-0.052
ops-0.049
 times-0.044
 months-0.043
Token.
Token ID13
Feature activation-3.17e-01

Pos logit contributions
 sincere+0.348
Sad+0.341
 widen+0.339
itating+0.339
 faint+0.338
Neg logit contributions
 days-0.329
 weeks-0.280
ops-0.253
 times-0.244
 months-0.242
Token The
Token ID383
Feature activation-1.10e+00

Pos logit contributions
 sincere+0.012
fly+0.012
 widen+0.012
 rapidly+0.012
 faint+0.012
Neg logit contributions
 days-0.018
 weeks-0.016
ops-0.015
 months-0.014
 day-0.013
Token in
Token ID287
Feature activation-5.29e+00

Pos logit contributions
 rapidly+0.092
 source+0.090
 faint+0.090
 widen+0.088
 sincere+0.088
Neg logit contributions
 days-0.116
 weeks-0.102
ops-0.099
 times-0.093
 months-0.091
Token the
Token ID262
Feature activation+1.40e+00

Pos logit contributions
 sincere+0.237
itating+0.231
 rapidly+0.230
 widen+0.229
fly+0.227
Neg logit contributions
 days-0.270
 weeks-0.236
 times-0.208
 months-0.208
ops-0.206
Token sky
Token ID6766
Feature activation-5.63e+00

Pos logit contributions
 days+0.074
 weeks+0.063
 months+0.056
 day+0.055
 nights+0.054
Neg logit contributions
itating-0.062
 sincere-0.062
fly-0.061
 widen-0.060
Sad-0.060
Token.
Token ID13
Feature activation-4.77e-01

Pos logit contributions
 rapidly+0.256
 faint+0.255
 widen+0.252
 sincere+0.252
 source+0.251
Neg logit contributions
 days-0.275
 weeks-0.239
ops-0.221
 months-0.208
 times-0.206
Token Jo
Token ID5302
Feature activation-2.37e+00

Pos logit contributions
 sincere+0.017
fly+0.016
itating+0.015
 rapidly+0.015
ull+0.015
Neg logit contributions
 days-0.030
 weeks-0.026
 months-0.024
ops-0.023
 nights-0.023
Tokenanne
Token ID21952
Feature activation-1.13e+01

Pos logit contributions
 sincere+0.047
 widen+0.041
 fuse+0.037
 source+0.036
 faint+0.035
Neg logit contributions
 days-0.187
 weeks-0.169
 times-0.158
ops-0.157
 months-0.154
Token remembered
Token ID12086
Feature activation-1.97e+00

Pos logit contributions
 sincere+0.506
 rapidly+0.498
 faint+0.497
 widen+0.496
Sad+0.489
Neg logit contributions
 days-0.558
 weeks-0.484
ops-0.449
 months-0.423
 times-0.423
Token the
Token ID262
Feature activation+1.44e+00

Pos logit contributions
 sincere+0.081
 faint+0.080
 rapidly+0.078
 source+0.077
 widen+0.076
Neg logit contributions
 days-0.105
ops-0.092
 weeks-0.092
 months-0.082
 times-0.081
Token day
Token ID1110
Feature activation+8.79e+00

Pos logit contributions
 days+0.085
 weeks+0.073
 times+0.068
 day+0.066
 months+0.065
Neg logit contributions
itating-0.054
Sad-0.053
 sincere-0.053
 widen-0.053
 rapidly-0.052
Token she
Token ID673
Feature activation+3.01e+00

Pos logit contributions
 days+0.406
ops+0.386
 weeks+0.357
 times+0.322
 cand+0.319
Neg logit contributions
 faint-0.392
 rapidly-0.366
 startled-0.361
 source-0.360
 aw-0.353
Token first
Token ID717
Feature activation+1.89e+00

Pos logit contributions
 days+0.156
 weeks+0.135
ops+0.130
 times+0.121
 months+0.119
Neg logit contributions
 sincere-0.129
 rapidly-0.127
 faint-0.127
 widen-0.125
fly-0.124
Token felt
Token ID2936
Feature activation-2.46e+00

Pos logit contributions
 days+0.129
 weeks+0.113
ops+0.106
 times+0.101
 months+0.101
Neg logit contributions
 sincere-0.094
 rapidly-0.093
 faint-0.092
 widen-0.091
fly-0.091
Token the
Token ID262
Feature activation+1.58e+00

Pos logit contributions
fly+0.106
Sad+0.105
itating+0.103
 sincere+0.101
 rapidly+0.101
Neg logit contributions
 days-0.130
 weeks-0.113
 months-0.099
 times-0.098
ops-0.096
Token healing
Token ID11516
Feature activation+2.18e-01

Pos logit contributions
 days+0.096
 weeks+0.084
ops+0.076
 times+0.076
 months+0.075
Neg logit contributions
 sincere-0.055
Sad-0.055
 rapidly-0.054
itating-0.054
 widen-0.053
Token power
Token ID1176
Feature activation-1.49e+00

Pos logit contributions
 days+0.012
 weeks+0.011
ops+0.010
 months+0.010
 times+0.009
Neg logit contributions
fly-0.008
 faint-0.008
 rapidly-0.008
 source-0.008
 widen-0.008
Token cour
Token ID1093
Feature activation-3.15e+00

Pos logit contributions
 rapidly+0.063
 faint+0.063
fly+0.062
 widen+0.062
 source+0.061
Neg logit contributions
 days-0.075
 weeks-0.067
ops-0.063
 months-0.059
 times-0.057
Tokensing
Token ID12215
Feature activation-1.13e+01

Pos logit contributions
 sincere+0.109
 faint+0.104
 rapidly+0.104
 widen+0.103
Sad+0.102
Neg logit contributions
 days-0.190
 weeks-0.169
ops-0.161
 months-0.151
 times-0.150
Token through
Token ID832
Feature activation-5.02e+00

Pos logit contributions
 rapidly+0.475
 faint+0.464
fly+0.447
ull+0.435
 fright+0.434
Neg logit contributions
 days-0.559
ops-0.522
 weeks-0.510
 months-0.459
ip-0.439
Token his
Token ID465
Feature activation+1.50e+00

Pos logit contributions
 rapidly+0.194
 faint+0.193
 sincere+0.187
 widen+0.181
 source+0.180
Neg logit contributions
 days-0.269
ops-0.249
 weeks-0.239
 months-0.213
 times-0.208
Token body
Token ID1767
Feature activation-1.40e+00

Pos logit contributions
 days+0.086
 weeks+0.076
ops+0.071
 times+0.068
 months+0.068
Neg logit contributions
 sincere-0.056
 rapidly-0.056
 widen-0.055
 faint-0.055
Sad-0.055
Token.
Token ID13
Feature activation-4.65e-01

Pos logit contributions
 rapidly+0.061
 faint+0.060
fly+0.059
 widen+0.059
 source+0.059
Neg logit contributions
 days-0.071
 weeks-0.063
ops-0.057
 months-0.055
 times-0.054
Token
Token ID198
Feature activation-1.81e+00

Pos logit contributions
 sincere+0.013
 rapidly+0.013
 faint+0.013
 widen+0.013
Sad+0.013
Neg logit contributions
 days-0.030
 weeks-0.027
ops-0.026
 times-0.025
 months-0.025
Token there
Token ID612
Feature activation-4.05e-01

Pos logit contributions
 faint+0.008
 rapidly+0.008
 sincere+0.008
 source+0.008
 widen+0.008
Neg logit contributions
 days-0.010
 weeks-0.008
ops-0.008
 times-0.007
 months-0.007
Token was
Token ID373
Feature activation-1.63e+00

Pos logit contributions
 sincere+0.026
itating+0.025
Sad+0.025
fly+0.024
amus+0.024
Neg logit contributions
 days-0.014
 weeks-0.011
ops-0.010
 later-0.009
 months-0.009
Token a
Token ID257
Feature activation+5.38e-01

Pos logit contributions
itating+0.085
 sincere+0.079
anne+0.078
 widen+0.078
fly+0.076
Neg logit contributions
 days-0.079
 weeks-0.068
 months-0.059
 things-0.055
 nights-0.054
Token loud
Token ID7812
Feature activation-4.85e+00

Pos logit contributions
 days+0.028
 weeks+0.025
 day+0.023
 times+0.022
 months+0.022
Neg logit contributions
itating-0.022
Sad-0.022
idget-0.021
 rapidly-0.021
ff-0.021
Token his
Token ID465
Feature activation+1.58e+00

Pos logit contributions
itating+0.174
 sincere+0.171
Sad+0.168
 rapidly+0.165
 widen+0.162
Neg logit contributions
 days-0.290
 weeks-0.254
ops-0.236
 times-0.236
 months-0.229
Tokensing
Token ID12215
Feature activation-1.13e+01

Pos logit contributions
 days+0.102
 weeks+0.089
ops+0.085
 times+0.082
 day+0.080
Neg logit contributions
Sad-0.051
itating-0.050
 sincere-0.049
 rapidly-0.048
 widen-0.048
Token noise
Token ID7838
Feature activation-5.02e+00

Pos logit contributions
 rapidly+0.348
 faint+0.348
 sincere+0.348
 widen+0.340
fly+0.335
Neg logit contributions
 days-0.710
 weeks-0.641
ops-0.609
 months-0.580
 times-0.572
Token.
Token ID13
Feature activation-2.91e-01

Pos logit contributions
 sincere+0.261
Sad+0.252
itating+0.248
 rapidly+0.247
 widen+0.247
Neg logit contributions
 days-0.222
 weeks-0.187
ops-0.172
 times-0.162
 months-0.160
Token The
Token ID383
Feature activation-1.15e+00

Pos logit contributions
itating+0.011
 sincere+0.011
Sad+0.010
fly+0.010
 widen+0.010
Neg logit contributions
 days-0.017
 weeks-0.015
 months-0.014
ops-0.014
 times-0.013
Token mouse
Token ID10211
Feature activation-1.35e+00

Pos logit contributions
 rapidly+0.050
itating+0.050
 widen+0.049
 sincere+0.048
Jud+0.048
Neg logit contributions
 days-0.063
 weeks-0.053
 times-0.047
 months-0.047
 day-0.046
Token looked
Token ID3114
Feature activation-4.66e+00

Pos logit contributions
 sincere+0.064
 widen+0.063
Sad+0.062
itating+0.062
 faint+0.062
Neg logit contributions
 days-0.065
 weeks-0.056
ops-0.051
 times-0.049
 months-0.048
Token!"
Token ID2474
Feature activation-1.22e+00

Pos logit contributions
 days+0.087
ops+0.080
 weeks+0.077
 months+0.066
 nights+0.064
Neg logit contributions
 widen-0.081
 faint-0.079
 rapidly-0.079
 source-0.078
 fright-0.076
Token
Token ID220
Feature activation-2.54e+00

Pos logit contributions
 sincere+0.036
 rapidly+0.036
 faint+0.036
 widen+0.035
Sad+0.035
Neg logit contributions
 days-0.079
 weeks-0.071
ops-0.067
 months-0.064
 times-0.064
Token
Token ID198
Feature activation-1.76e+00

Pos logit contributions
 sincere+0.096
 rapidly+0.092
 widen+0.091
fly+0.091
 faint+0.090
Neg logit contributions
 days-0.144
 weeks-0.127
ops-0.123
 months-0.114
 times-0.113
Token
Token ID198
Feature activation-1.77e+00

Pos logit contributions
 sincere+0.069
 widen+0.066
fly+0.066
 rapidly+0.065
 source+0.064
Neg logit contributions
 days-0.101
 weeks-0.088
ops-0.080
 months-0.079
 times-0.078
TokenJo
Token ID9908
Feature activation-1.10e+00

Pos logit contributions
 sincere+0.048
 rapidly+0.048
 faint+0.048
Sad+0.047
 widen+0.047
Neg logit contributions
 days-0.119
 weeks-0.107
ops-0.102
 times-0.097
 months-0.097
Tokenanne
Token ID21952
Feature activation-1.13e+01

Pos logit contributions
 sincere+0.025
 rapidly+0.024
 faint+0.024
 widen+0.024
Sad+0.023
Neg logit contributions
 days-0.079
 weeks-0.072
ops-0.068
 months-0.066
 times-0.066
Token smiled
Token ID13541
Feature activation-5.32e+00

Pos logit contributions
 rapidly+0.446
 sincere+0.444
fly+0.434
 widen+0.431
 faint+0.431
Neg logit contributions
 days-0.615
 weeks-0.541
ops-0.504
 months-0.483
 times-0.479
Token and
Token ID290
Feature activation+1.50e+00

Pos logit contributions
Sad+0.297
 sincere+0.296
 faint+0.291
fly+0.291
itating+0.290
Neg logit contributions
 days-0.202
 weeks-0.165
 times-0.138
ops-0.138
 months-0.135
Token thanked
Token ID26280
Feature activation+1.16e+00

Pos logit contributions
 days+0.085
 weeks+0.076
ops+0.074
 months+0.069
 times+0.068
Neg logit contributions
 rapidly-0.056
 sincere-0.055
 faint-0.055
 startled-0.054
 widen-0.054
Token the
Token ID262
Feature activation+1.52e+00

Pos logit contributions
 days+0.055
 weeks+0.047
 times+0.041
 months+0.041
ops+0.041
Neg logit contributions
 sincere-0.057
itating-0.056
 rapidly-0.056
 widen-0.055
 faint-0.055
Token old
Token ID1468
Feature activation-3.52e+00

Pos logit contributions
 days+0.092
 weeks+0.082
ops+0.080
 months+0.074
 times+0.073
Neg logit contributions
 sincere-0.052
 faint-0.051
 rapidly-0.051
 widen-0.051
 source-0.050
Token
Token ID198
Feature activation-1.69e+00

Pos logit contributions
 sincere+0.072
fly+0.069
 widen+0.067
 rapidly+0.065
 fuse+0.064
Neg logit contributions
 days-0.094
 weeks-0.081
ops-0.073
 months-0.072
 later-0.071
TokenYears
Token ID40630
Feature activation+4.75e+00

Pos logit contributions
 sincere+0.056
 rapidly+0.054
 widen+0.054
 faint+0.053
fly+0.053
Neg logit contributions
 days-0.105
 weeks-0.094
ops-0.088
 months-0.085
 times-0.085
Token passed
Token ID3804
Feature activation+1.96e+00

Pos logit contributions
ops+0.205
 days+0.204
 pads+0.199
 choices+0.189
 cents+0.183
Neg logit contributions
bell-0.188
ff-0.179
anne-0.174
 rapidly-0.170
 darkened-0.166
Token and
Token ID290
Feature activation+1.54e+00

Pos logit contributions
 days+0.093
 weeks+0.080
ops+0.073
 months+0.069
 times+0.069
Neg logit contributions
 sincere-0.093
 rapidly-0.091
 widen-0.091
 faint-0.091
Sad-0.089
Token Jo
Token ID5302
Feature activation-2.31e+00

Pos logit contributions
 days+0.103
ops+0.099
 weeks+0.093
 times+0.087
 cand+0.085
Neg logit contributions
 faint-0.039
Sad-0.038
 source-0.037
 rapidly-0.037
Maria-0.036
Tokenanne
Token ID21952
Feature activation-1.13e+01

Pos logit contributions
 sincere+0.034
 widen+0.031
 faint+0.027
 source+0.026
 rapidly+0.026
Neg logit contributions
 days-0.192
 weeks-0.175
ops-0.166
 times-0.162
 months-0.161
Token grew
Token ID6348
Feature activation-3.22e-01

Pos logit contributions
 rapidly+0.464
fly+0.463
 sincere+0.452
anne+0.442
 faint+0.442
Neg logit contributions
 days-0.589
 weeks-0.513
ops-0.478
 times-0.461
 months-0.454
Token up
Token ID510
Feature activation-5.85e+00

Pos logit contributions
 sincere+0.013
Sad+0.012
 rapidly+0.012
 widen+0.012
fly+0.012
Neg logit contributions
 days-0.018
 weeks-0.016
ops-0.014
 months-0.014
 times-0.014
Token.
Token ID13
Feature activation-4.49e-01

Pos logit contributions
 rapidly+0.259
 faint+0.258
 sincere+0.258
 source+0.255
 widen+0.254
Neg logit contributions
 days-0.293
 weeks-0.253
ops-0.248
 times-0.222
 months-0.220
Token Now
Token ID2735
Feature activation+4.52e+00

Pos logit contributions
 sincere+0.014
 rapidly+0.013
 widen+0.013
 faint+0.013
fly+0.013
Neg logit contributions
 days-0.029
 weeks-0.026
ops-0.024
 months-0.024
 times-0.023
Token she
Token ID673
Feature activation+3.07e+00

Pos logit contributions
 days+0.217
ops+0.204
 weeks+0.187
 cand+0.169
 times+0.167
Neg logit contributions
 faint-0.199
 rapidly-0.193
 widen-0.185
 investigate-0.185
 source-0.183
Token to
Token ID284
Feature activation-2.30e+00

Pos logit contributions
 days+0.283
ops+0.267
 weeks+0.253
 times+0.240
 months+0.220
Neg logit contributions
 rapidly-0.197
 source-0.193
 faint-0.192
 sincere-0.190
 widen-0.189
Token other
Token ID584
Feature activation+2.89e-01

Pos logit contributions
 faint+0.089
 sincere+0.088
 source+0.086
 widen+0.085
 rapidly+0.084
Neg logit contributions
 days-0.127
ops-0.114
 weeks-0.113
 times-0.100
 months-0.099
Token customers
Token ID4297
Feature activation+3.41e+00

Pos logit contributions
ops+0.014
ip+0.012
 days+0.011
 weeks+0.010
mm+0.010
Neg logit contributions
 faint-0.013
 source-0.012
 sincere-0.012
 investigate-0.012
 fright-0.012
Token.
Token ID13
Feature activation-5.99e-01

Pos logit contributions
 days+0.205
 weeks+0.185
ops+0.173
 times+0.169
 months+0.164
Neg logit contributions
 source-0.105
itating-0.105
 sincere-0.104
 rapidly-0.099
 clearly-0.099
Token Jo
Token ID5302
Feature activation-2.35e+00

Pos logit contributions
 sincere+0.016
 rapidly+0.016
 faint+0.016
 widen+0.016
Sad+0.015
Neg logit contributions
 days-0.040
 weeks-0.036
ops-0.035
 times-0.033
 months-0.033
Tokenanne
Token ID21952
Feature activation-1.13e+01

Pos logit contributions
 rapidly+0.097
 faint+0.095
 sincere+0.095
Sad+0.094
 widen+0.093
Neg logit contributions
 days-0.125
 weeks-0.109
ops-0.101
 times-0.098
 months-0.096
Token and
Token ID290
Feature activation+1.39e+00

Pos logit contributions
 sincere+0.457
 rapidly+0.452
fly+0.440
 faint+0.439
 widen+0.436
Neg logit contributions
 days-0.603
 weeks-0.526
ops-0.489
 times-0.472
 months-0.464
Token Joey
Token ID26154
Feature activation-2.52e+00

Pos logit contributions
 days+0.085
ops+0.079
 weeks+0.077
 months+0.070
 times+0.068
Neg logit contributions
 faint-0.044
 sincere-0.042
 rapidly-0.042
 source-0.042
Maria-0.042
Token said
Token ID531
Feature activation+8.81e-01

Pos logit contributions
 sincere+0.103
 rapidly+0.102
 widen+0.100
 faint+0.098
itating+0.097
Neg logit contributions
 days-0.137
 weeks-0.119
ops-0.110
 times-0.107
 months-0.104
Token goodbye
Token ID24829
Feature activation+1.88e+00

Pos logit contributions
 days+0.043
 weeks+0.038
ops+0.037
 times+0.034
 months+0.034
Neg logit contributions
 sincere-0.041
 rapidly-0.039
 faint-0.038
 widen-0.038
 startled-0.037
Token as
Token ID355
Feature activation+4.37e+00

Pos logit contributions
 days+0.099
 weeks+0.087
ops+0.082
 times+0.077
 months+0.077
Neg logit contributions
 rapidly-0.078
 faint-0.077
 sincere-0.077
 widen-0.076
 source-0.076
Token.
Token ID13
Feature activation-3.05e-01

Pos logit contributions
 sincere+0.076
 rapidly+0.075
 faint+0.075
 widen+0.074
fly+0.074
Neg logit contributions
 days-0.085
 weeks-0.074
ops-0.069
 months-0.065
 times-0.064
Token The
Token ID383
Feature activation-1.06e+00

Pos logit contributions
 sincere+0.012
itating+0.012
Sad+0.012
 widen+0.011
 faint+0.011
Neg logit contributions
 days-0.017
 weeks-0.015
 months-0.014
ops-0.013
 times-0.013
Token cats
Token ID11875
Feature activation+8.03e-01

Pos logit contributions
 sincere+0.052
 source+0.051
 faint+0.051
 widen+0.050
 rapidly+0.050
Neg logit contributions
 days-0.048
 weeks-0.041
ops-0.038
 months-0.035
 times-0.035
Token were
Token ID547
Feature activation-6.94e-02

Pos logit contributions
 days+0.038
 weeks+0.033
ops+0.030
 times+0.028
 months+0.028
Neg logit contributions
 sincere-0.038
 rapidly-0.037
 faint-0.037
 widen-0.037
Sad-0.037
Token his
Token ID465
Feature activation+1.66e+00

Pos logit contributions
Sad+0.003
ff+0.003
ull+0.003
fly+0.003
anne+0.003
Neg logit contributions
 days-0.003
 weeks-0.003
 times-0.003
 months-0.003
 things-0.003
Tokensing
Token ID12215
Feature activation-1.13e+01

Pos logit contributions
 days+0.079
 weeks+0.069
ops+0.063
 months+0.060
 times+0.059
Neg logit contributions
 sincere-0.078
 rapidly-0.077
 faint-0.077
 widen-0.076
 source-0.076
Token,
Token ID11
Feature activation-9.84e-02

Pos logit contributions
 rapidly+0.499
 faint+0.489
 sincere+0.484
 startled+0.484
fly+0.477
Neg logit contributions
 days-0.551
 weeks-0.495
ops-0.475
 months-0.434
 nights-0.409
Token sw
Token ID1509
Feature activation+6.84e-01

Pos logit contributions
 sincere+0.004
Sad+0.004
 rapidly+0.004
 widen+0.004
itating+0.004
Neg logit contributions
 days-0.005
 weeks-0.004
ops-0.004
 times-0.004
 months-0.004
Tokeniping
Token ID34690
Feature activation-2.34e+00

Pos logit contributions
 days+0.029
ops+0.027
 weeks+0.025
 times+0.022
 things+0.021
Neg logit contributions
Sad-0.033
 widen-0.033
 faint-0.033
 source-0.032
 sincere-0.032
Token and
Token ID290
Feature activation+1.70e+00

Pos logit contributions
 sincere+0.097
 rapidly+0.095
 faint+0.095
 widen+0.094
Sad+0.093
Neg logit contributions
 days-0.124
 weeks-0.109
ops-0.101
 times-0.096
 months-0.096
Token me
Token ID502
Feature activation-3.28e+00

Pos logit contributions
 days+0.096
 weeks+0.084
ops+0.077
 times+0.075
 months+0.075
Neg logit contributions
 sincere-0.066
 widen-0.065
 rapidly-0.064
itating-0.064
Sad-0.064
TokenAnd
Token ID1870
Feature activation+4.33e+00

Pos logit contributions
 sincere+0.063
 widen+0.062
 rapidly+0.062
 faint+0.061
fly+0.060
Neg logit contributions
 days-0.101
 weeks-0.090
ops-0.083
 months-0.080
 times-0.080
Token so
Token ID523
Feature activation+1.73e+00

Pos logit contributions
 days+0.240
ops+0.237
 weeks+0.216
 months+0.193
 cand+0.192
Neg logit contributions
 faint-0.157
Sad-0.151
Maria-0.146
 source-0.146
 rapidly-0.144
Token,
Token ID11
Feature activation-1.73e-01

Pos logit contributions
 days+0.097
ops+0.090
 weeks+0.088
 cand+0.082
 months+0.078
Neg logit contributions
 faint-0.061
Sad-0.060
Maria-0.057
 rapidly-0.057
 startled-0.056
Token when
Token ID618
Feature activation+5.00e+00

Pos logit contributions
 faint+0.004
Sad+0.004
Maria+0.004
 source+0.004
 rapidly+0.004
Neg logit contributions
 days-0.011
ops-0.011
 weeks-0.010
 cand-0.010
 cents-0.010
Token Jo
Token ID5302
Feature activation-2.42e+00

Pos logit contributions
 days+0.307
ops+0.304
 weeks+0.279
 cand+0.271
 cents+0.265
Neg logit contributions
 faint-0.152
Sad-0.136
 source-0.134
 rapidly-0.132
Maria-0.129
Tokenanne
Token ID21952
Feature activation-1.12e+01

Pos logit contributions
 sincere+0.031
 widen+0.026
 rapidly+0.024
 faint+0.024
 source+0.023
Neg logit contributions
 days-0.204
 weeks-0.187
ops-0.177
 times-0.174
 months-0.173
Token graduated
Token ID18303
Feature activation+4.90e+00

Pos logit contributions
anne+0.398
 startled+0.398
 rapidly+0.397
bird+0.396
fly+0.390
Neg logit contributions
 days-0.627
 weeks-0.540
ops-0.515
 things-0.498
 times-0.496
Token from
Token ID422
Feature activation+1.84e-01

Pos logit contributions
 days+0.220
 weeks+0.188
 times+0.166
ops+0.165
 months+0.163
Neg logit contributions
 sincere-0.244
 rapidly-0.238
 widen-0.237
Sad-0.236
 faint-0.234
Token high
Token ID1029
Feature activation-4.12e+00

Pos logit contributions
 days+0.010
 weeks+0.008
ops+0.008
 months+0.007
 times+0.007
Neg logit contributions
 sincere-0.008
 rapidly-0.007
 faint-0.007
 source-0.007
 widen-0.007
Token school
Token ID1524
Feature activation+4.47e+00

Pos logit contributions
 rapidly+0.169
 source+0.165
 widen+0.163
 faint+0.161
fly+0.160
Neg logit contributions
 days-0.214
ops-0.190
 weeks-0.188
 months-0.162
 nights-0.161
Token,
Token ID11
Feature activation-3.19e-01

Pos logit contributions
 days+0.209
ops+0.183
 weeks+0.183
ip+0.168
 cents+0.167
Neg logit contributions
bell-0.183
 startled-0.178
 faint-0.175
 rapidly-0.172
 source-0.168
Token into
Token ID656
Feature activation-5.04e+00

Pos logit contributions
fly+0.080
 rapidly+0.080
 faint+0.076
 source+0.076
 widen+0.075
Neg logit contributions
 days-0.103
 weeks-0.093
ops-0.084
 months-0.084
 nights-0.080
Token the
Token ID262
Feature activation+1.43e+00

Pos logit contributions
 sincere+0.193
 faint+0.193
 rapidly+0.192
 widen+0.188
 source+0.186
Neg logit contributions
 days-0.282
 weeks-0.249
ops-0.238
 months-0.221
 times-0.220
Token hole
Token ID7604
Feature activation-3.21e+00

Pos logit contributions
 days+0.087
 weeks+0.076
ops+0.070
 months+0.069
 times+0.069
Neg logit contributions
 sincere-0.050
 rapidly-0.049
itating-0.049
Sad-0.049
 widen-0.049
Token.
Token ID13
Feature activation-4.72e-01

Pos logit contributions
 rapidly+0.151
 sincere+0.150
 faint+0.149
fly+0.147
 widen+0.147
Neg logit contributions
 days-0.152
 weeks-0.132
ops-0.122
 months-0.115
 times-0.113
Token Jo
Token ID5302
Feature activation-2.40e+00

Pos logit contributions
 sincere+0.013
fly+0.012
 widen+0.012
 rapidly+0.012
itating+0.011
Neg logit contributions
 days-0.033
 weeks-0.030
ops-0.027
 months-0.027
 times-0.027
Tokenanne
Token ID21952
Feature activation-1.12e+01

Pos logit contributions
 sincere+0.054
 widen+0.047
 fuse+0.042
 source+0.041
 faint+0.039
Neg logit contributions
 days-0.186
 weeks-0.166
 times-0.156
ops-0.155
 day-0.153
Token saw
Token ID2497
Feature activation-4.10e+00

Pos logit contributions
 sincere+0.488
 rapidly+0.479
 faint+0.478
 widen+0.477
itating+0.470
Neg logit contributions
 days-0.573
 weeks-0.500
ops-0.464
 months-0.438
 times-0.437
Token the
Token ID262
Feature activation+1.40e+00

Pos logit contributions
 sincere+0.174
 faint+0.173
 rapidly+0.173
 widen+0.169
 source+0.169
Neg logit contributions
 days-0.213
 weeks-0.187
ops-0.177
 months-0.165
 times-0.164
Token nut
Token ID6701
Feature activation-1.94e+00

Pos logit contributions
 days+0.081
 weeks+0.071
ops+0.066
 times+0.064
 months+0.063
Neg logit contributions
 sincere-0.052
 rapidly-0.051
Sad-0.051
itating-0.051
 widen-0.051
Token disappear
Token ID10921
Feature activation-2.92e+00

Pos logit contributions
 rapidly+0.085
 faint+0.084
fly+0.083
 sincere+0.083
 widen+0.082
Neg logit contributions
 days-0.099
 weeks-0.088
ops-0.081
 months-0.078
 nights-0.075
Token into
Token ID656
Feature activation-5.06e+00

Pos logit contributions
 rapidly+0.135
 sincere+0.134
 faint+0.133
 widen+0.133
fly+0.131
Neg logit contributions
 days-0.143
 weeks-0.124
ops-0.116
 months-0.108
 times-0.106
Token The
Token ID383
Feature activation-1.42e+00

Pos logit contributions
fly+0.030
 rapidly+0.029
itating+0.029
 source+0.029
 sincere+0.028
Neg logit contributions
 days-0.035
 weeks-0.030
 later-0.028
 months-0.027
ops-0.027
Token ball
Token ID2613
Feature activation+1.73e+00

Pos logit contributions
 sincere+0.053
 faint+0.053
 source+0.052
 rapidly+0.051
fly+0.051
Neg logit contributions
 days-0.080
 weeks-0.072
ops-0.068
 months-0.065
 times-0.063
Token makes
Token ID1838
Feature activation+4.45e-01

Pos logit contributions
 days+0.082
 weeks+0.070
ops+0.064
 months+0.061
 nights+0.059
Neg logit contributions
 sincere-0.084
 rapidly-0.082
 widen-0.082
 faint-0.081
fly-0.080
Token a
Token ID257
Feature activation+5.79e-01

Pos logit contributions
 days+0.024
 weeks+0.021
ops+0.019
 times+0.019
 months+0.018
Neg logit contributions
 sincere-0.018
itating-0.018
Sad-0.018
 rapidly-0.018
fly-0.018
Token his
Token ID465
Feature activation+1.41e+00

Pos logit contributions
 days+0.031
 times+0.028
 weeks+0.027
 things+0.026
 day+0.025
Neg logit contributions
anne-0.021
idget-0.021
Sad-0.021
Maria-0.020
itating-0.020
Tokensing
Token ID12215
Feature activation-1.12e+01

Pos logit contributions
 days+0.102
 weeks+0.090
ops+0.088
 times+0.087
 day+0.085
Neg logit contributions
Sad-0.033
itating-0.031
 sincere-0.031
 rapidly-0.031
Jud-0.031
Token sound
Token ID2128
Feature activation-5.36e+00

Pos logit contributions
 faint+0.358
 rapidly+0.356
 sincere+0.349
 widen+0.346
fly+0.341
Neg logit contributions
 days-0.697
 weeks-0.633
ops-0.603
 months-0.575
 nights-0.549
Token and
Token ID290
Feature activation+1.22e+00

Pos logit contributions
 sincere+0.280
Sad+0.274
 rapidly+0.272
 faint+0.270
itating+0.269
Neg logit contributions
 days-0.228
 weeks-0.191
ops-0.174
 times-0.167
 months-0.162
Token goes
Token ID2925
Feature activation+5.91e+00

Pos logit contributions
 days+0.060
 weeks+0.052
ops+0.047
 times+0.046
 months+0.045
Neg logit contributions
Sad-0.054
 sincere-0.054
 rapidly-0.054
itating-0.054
 faint-0.052
Token flat
Token ID6228
Feature activation-2.84e+00

Pos logit contributions
 days+0.344
 weeks+0.305
ops+0.284
 times+0.273
 months+0.273
Neg logit contributions
 sincere-0.214
 faint-0.209
 widen-0.208
 rapidly-0.208
Sad-0.208
Token.
Token ID13
Feature activation-6.99e-01

Pos logit contributions
 rapidly+0.119
 widen+0.110
fly+0.110
 source+0.107
 startled+0.105
Neg logit contributions
 days-0.149
 weeks-0.134
ops-0.129
 months-0.117
 nights-0.116
Token wanted
Token ID2227
Feature activation+2.98e+00

Pos logit contributions
 sincere+0.027
 faint+0.027
 widen+0.026
 fright+0.025
 source+0.025
Neg logit contributions
 days-0.049
ops-0.046
 weeks-0.044
 months-0.040
 times-0.040
Token to
Token ID284
Feature activation-2.23e+00

Pos logit contributions
 days+0.163
 weeks+0.145
ops+0.144
 times+0.130
 months+0.129
Neg logit contributions
 faint-0.112
 rapidly-0.111
 sincere-0.110
 source-0.110
 widen-0.108
Token go
Token ID467
Feature activation+4.94e+00

Pos logit contributions
 sincere+0.087
 rapidly+0.086
itating+0.085
Sad+0.085
fly+0.084
Neg logit contributions
 days-0.123
 weeks-0.108
ops-0.099
 times-0.098
 months-0.096
Token,"
Token ID553
Feature activation-8.12e-01

Pos logit contributions
 days+0.271
 weeks+0.239
ops+0.227
 times+0.212
 months+0.211
Neg logit contributions
 sincere-0.195
 rapidly-0.194
 faint-0.193
 widen-0.192
 source-0.190
Token Jo
Token ID5302
Feature activation-2.38e+00

Pos logit contributions
 faint+0.028
 rapidly+0.028
 sincere+0.028
Sad+0.027
 widen+0.027
Neg logit contributions
 days-0.049
 weeks-0.043
ops-0.041
 months-0.039
 times-0.039
Tokenanne
Token ID21952
Feature activation-1.12e+01

Pos logit contributions
 sincere+0.054
 widen+0.048
 fuse+0.046
 source+0.045
 faint+0.041
Neg logit contributions
 days-0.180
 weeks-0.162
 times-0.153
ops-0.150
 day-0.148
Token said
Token ID531
Feature activation+8.64e-01

Pos logit contributions
 sincere+0.469
 rapidly+0.462
 faint+0.459
 widen+0.458
Sad+0.451
Neg logit contributions
 days-0.588
 weeks-0.515
ops-0.479
 months-0.454
 times-0.453
Token.
Token ID13
Feature activation-2.55e-01

Pos logit contributions
 days+0.037
 weeks+0.031
ops+0.028
 months+0.026
 times+0.026
Neg logit contributions
 sincere-0.045
 rapidly-0.044
 faint-0.044
 widen-0.044
Sad-0.043
Token
Token ID220
Feature activation-2.49e+00

Pos logit contributions
 sincere+0.010
 widen+0.010
 rapidly+0.010
fly+0.010
ull+0.009
Neg logit contributions
 days-0.014
 weeks-0.012
 months-0.011
ops-0.011
 times-0.011
Token
Token ID198
Feature activation-1.71e+00

Pos logit contributions
 sincere+0.100
fly+0.097
 rapidly+0.096
 widen+0.094
 faint+0.092
Neg logit contributions
 days-0.135
 weeks-0.119
ops-0.114
 later-0.107
 months-0.106
Token
Token ID198
Feature activation-1.73e+00

Pos logit contributions
 sincere+0.073
 widen+0.072
fly+0.072
 source+0.069
 rapidly+0.069
Neg logit contributions
 days-0.093
 weeks-0.080
 months-0.071
ops-0.071
 later-0.070
Token sc
Token ID629
Feature activation+7.90e-01

Pos logit contributions
anne+0.062
ff+0.061
icker+0.061
ull+0.060
Jud+0.059
Neg logit contributions
 days-0.065
 weeks-0.054
 day-0.052
 things-0.047
 times-0.047
Tokenow
Token ID322
Feature activation-8.53e+00

Pos logit contributions
 days+0.036
ops+0.033
 weeks+0.030
ip+0.028
 times+0.027
Neg logit contributions
 rapidly-0.035
 widen-0.035
 sincere-0.035
ull-0.035
 faint-0.035
Tokenling
Token ID1359
Feature activation-7.04e+00

Pos logit contributions
 rapidly+0.357
 faint+0.346
 sincere+0.345
 widen+0.340
itating+0.339
Neg logit contributions
 days-0.446
 weeks-0.396
ops-0.373
 months-0.354
 nights-0.339
Token and
Token ID290
Feature activation+1.73e+00

Pos logit contributions
 sincere+0.398
Sad+0.394
 faint+0.385
 widen+0.385
itating+0.383
Neg logit contributions
 days-0.270
 weeks-0.222
ops-0.188
 months-0.183
 times-0.182
Token his
Token ID465
Feature activation+1.85e+00

Pos logit contributions
 days+0.087
 weeks+0.076
ops+0.070
 months+0.067
 times+0.067
Neg logit contributions
 sincere-0.076
 rapidly-0.075
 widen-0.075
 faint-0.074
Sad-0.074
Tokensing
Token ID12215
Feature activation-1.12e+01

Pos logit contributions
 days+0.115
 weeks+0.101
ops+0.096
 times+0.092
 months+0.091
Neg logit contributions
 sincere-0.062
 widen-0.061
 rapidly-0.061
itating-0.061
Sad-0.060
Token.
Token ID13
Feature activation-1.43e-01

Pos logit contributions
 rapidly+0.456
 faint+0.452
 sincere+0.438
 startled+0.433
fly+0.426
Neg logit contributions
 days-0.581
 weeks-0.529
ops-0.526
 months-0.474
 cand-0.439
Token She
Token ID1375
Feature activation-1.56e+00

Pos logit contributions
 sincere+0.006
 widen+0.005
fly+0.005
 rapidly+0.005
 faint+0.005
Neg logit contributions
 days-0.008
 weeks-0.007
ops-0.007
 months-0.006
 day-0.006
Token was
Token ID373
Feature activation-1.32e+00

Pos logit contributions
 widen+0.081
 sincere+0.080
itating+0.080
 source+0.079
 faint+0.078
Neg logit contributions
 days-0.069
 weeks-0.059
ops-0.051
 months-0.049
 times-0.049
Token scared
Token ID12008
Feature activation-4.89e+00

Pos logit contributions
ff+0.059
icker+0.058
anne+0.058
fly+0.058
ull+0.058
Neg logit contributions
 days-0.065
 weeks-0.055
 day-0.049
 months-0.046
 things-0.046
Token,
Token ID11
Feature activation-9.96e-02

Pos logit contributions
 sincere+0.278
 widen+0.274
fly+0.271
 rapidly+0.271
 faint+0.268
Neg logit contributions
 days-0.194
 weeks-0.159
 times-0.134
ops-0.134
 months-0.130
Token The
Token ID383
Feature activation-1.14e+00

Pos logit contributions
 days+0.001
 weeks+0.001
ops+0.001
 months+0.001
 times+0.001
Neg logit contributions
fly-0.001
 sincere-0.001
Sad-0.001
 faint-0.001
 rapidly-0.001
Token bed
Token ID3996
Feature activation+2.86e+00

Pos logit contributions
itating+0.042
 rapidly+0.042
 sincere+0.041
 widen+0.040
Jud+0.040
Neg logit contributions
 days-0.068
 weeks-0.059
ops-0.054
 times-0.054
 months-0.053
Token made
Token ID925
Feature activation+6.88e-01

Pos logit contributions
 days+0.135
 weeks+0.116
ops+0.109
 months+0.101
 times+0.098
Neg logit contributions
 sincere-0.137
 rapidly-0.135
Sad-0.133
 widen-0.133
itating-0.133
Token a
Token ID257
Feature activation+6.96e-01

Pos logit contributions
 days+0.037
 weeks+0.032
 times+0.029
 months+0.028
ops+0.028
Neg logit contributions
 sincere-0.030
itating-0.029
fly-0.029
 rapidly-0.029
 widen-0.028
Token his
Token ID465
Feature activation+1.61e+00

Pos logit contributions
 days+0.036
 times+0.031
 weeks+0.031
 things+0.030
 day+0.030
Neg logit contributions
idget-0.026
 sincere-0.026
itating-0.026
ff-0.026
ull-0.026
Tokensing
Token ID12215
Feature activation-1.12e+01

Pos logit contributions
 days+0.101
 weeks+0.089
ops+0.085
 times+0.082
 months+0.081
Neg logit contributions
 sincere-0.052
 rapidly-0.051
itating-0.050
 widen-0.050
Sad-0.050
Token sound
Token ID2128
Feature activation-5.31e+00

Pos logit contributions
 faint+0.326
 rapidly+0.323
 widen+0.312
 sincere+0.308
fly+0.302
Neg logit contributions
 days-0.723
 weeks-0.661
ops-0.634
 months-0.602
 times-0.578
Token and
Token ID290
Feature activation+1.80e+00

Pos logit contributions
 sincere+0.285
Sad+0.273
itating+0.271
 rapidly+0.266
fly+0.266
Neg logit contributions
 days-0.228
 weeks-0.191
ops-0.173
 times-0.166
 months-0.161
Token started
Token ID2067
Feature activation-1.81e+00

Pos logit contributions
 days+0.096
 weeks+0.083
 months+0.074
ops+0.074
 times+0.073
Neg logit contributions
itating-0.076
Sad-0.074
 sincere-0.073
 widen-0.072
 rapidly-0.072
Token to
Token ID284
Feature activation-2.13e+00

Pos logit contributions
 sincere+0.084
 widen+0.081
itating+0.080
Sad+0.080
 rapidly+0.078
Neg logit contributions
 days-0.089
 weeks-0.076
ops-0.069
 times-0.068
 months-0.066
Token go
Token ID467
Feature activation+4.91e+00

Pos logit contributions
 sincere+0.090
itating+0.089
anne+0.088
itance+0.086
 perplex+0.086
Neg logit contributions
 days-0.099
 times-0.090
 weeks-0.088
 later-0.086
 day-0.082
Token tower
Token ID10580
Feature activation-7.22e-01

Pos logit contributions
 faint+0.148
 rapidly+0.142
 widen+0.142
 sincere+0.141
 source+0.141
Neg logit contributions
 days-0.189
ops-0.178
 weeks-0.170
ip-0.148
 months-0.148
Token this
Token ID428
Feature activation+3.94e+00

Pos logit contributions
 rapidly+0.029
 faint+0.028
fly+0.028
 widen+0.028
 startled+0.027
Neg logit contributions
 days-0.039
 weeks-0.034
ops-0.032
 months-0.030
 nights-0.029
Token time
Token ID640
Feature activation+4.66e+00

Pos logit contributions
 days+0.192
 weeks+0.168
ops+0.164
 months+0.146
 times+0.143
Neg logit contributions
 rapidly-0.173
 faint-0.173
 source-0.172
 sincere-0.169
 widen-0.169
Token.
Token ID13
Feature activation-5.60e-01

Pos logit contributions
 days+0.247
 weeks+0.220
ops+0.211
 times+0.196
 cand+0.196
Neg logit contributions
 rapidly-0.181
 faint-0.177
 sincere-0.170
 widen-0.169
 source-0.168
Token<|endoftext|>
Token ID50256
Feature activation+2.26e+00

Pos logit contributions
 sincere+0.018
 rapidly+0.018
 faint+0.017
 widen+0.017
fly+0.017
Neg logit contributions
 days-0.035
 weeks-0.031
ops-0.030
 months-0.028
 times-0.028
TokenOnce
Token ID7454
Feature activation+6.34e+00

Pos logit contributions
 days+0.127
 weeks+0.112
ops+0.105
 times+0.101
 months+0.100
Neg logit contributions
 sincere-0.086
 rapidly-0.085
 faint-0.084
 widen-0.084
Sad-0.083
Token upon
Token ID2402
Feature activation+3.02e-02

Pos logit contributions
 days+0.329
 weeks+0.286
ops+0.265
 times+0.252
 months+0.249
Neg logit contributions
 widen-0.273
 sincere-0.269
 rapidly-0.268
 faint-0.265
Sad-0.263
Token a
Token ID257
Feature activation+7.62e-01

Pos logit contributions
 days+0.002
 weeks+0.002
ops+0.001
 months+0.001
 times+0.001
Neg logit contributions
 sincere-0.001
 rapidly-0.001
 widen-0.001
 faint-0.001
itating-0.001
Token time
Token ID640
Feature activation+4.70e+00

Pos logit contributions
 days+0.033
 weeks+0.028
ops+0.026
 months+0.024
 times+0.024
Neg logit contributions
 sincere-0.038
 rapidly-0.038
 faint-0.038
 widen-0.037
Sad-0.037
Token,
Token ID11
Feature activation-2.79e-01

Pos logit contributions
 days+0.201
 weeks+0.176
ops+0.157
 months+0.154
 times+0.149
Neg logit contributions
 faint-0.236
 sincere-0.236
fly-0.232
 rapidly-0.231
itating-0.229
Token there
Token ID612
Feature activation-1.50e-01

Pos logit contributions
 widen+0.015
 sincere+0.015
 faint+0.015
 rapidly+0.015
 source+0.015
Neg logit contributions
 days-0.011
 weeks-0.009
ops-0.008
 later-0.008
 day-0.008
Token in
Token ID287
Feature activation-5.09e+00

Pos logit contributions
 sincere+0.253
 faint+0.248
fly+0.248
Sad+0.246
 widen+0.244
Neg logit contributions
 days-0.300
 weeks-0.263
 times-0.231
 later-0.230
 day-0.230
Token pretty
Token ID2495
Feature activation-3.66e+00

Pos logit contributions
 sincere+0.203
 faint+0.202
 widen+0.198
Sad+0.198
 rapidly+0.196
Neg logit contributions
 days-0.274
 weeks-0.242
ops-0.239
 months-0.215
 times-0.212
Token clothes
Token ID8242
Feature activation+2.36e+00

Pos logit contributions
 rapidly+0.179
 sincere+0.179
 widen+0.175
 faint+0.174
 source+0.174
Neg logit contributions
 days-0.152
 weeks-0.133
ops-0.130
 months-0.115
 times-0.108
Token.
Token ID13
Feature activation+1.40e-01

Pos logit contributions
 days+0.128
 weeks+0.115
ops+0.104
 months+0.102
 times+0.102
Neg logit contributions
 source-0.093
itating-0.091
 sincere-0.090
 rapidly-0.089
 widen-0.088
Token One
Token ID1881
Feature activation+9.27e-01

Pos logit contributions
 days+0.008
 weeks+0.007
ops+0.006
 day+0.006
 months+0.006
Neg logit contributions
fly-0.006
 rapidly-0.006
 sincere-0.006
 faint-0.006
 widen-0.006
Token day
Token ID1110
Feature activation+8.87e+00

Pos logit contributions
 days+0.021
ops+0.019
 weeks+0.018
 months+0.015
 cand+0.013
Neg logit contributions
 faint-0.061
Sad-0.060
 source-0.059
ull-0.058
 rapidly-0.058
Token,
Token ID11
Feature activation+1.68e-01

Pos logit contributions
 days+0.388
 weeks+0.348
ops+0.310
 months+0.308
 times+0.308
Neg logit contributions
 sincere-0.406
 faint-0.400
 startled-0.397
 rapidly-0.397
Sad-0.394
Token Lily
Token ID20037
Feature activation+1.97e+00

Pos logit contributions
 days+0.008
 weeks+0.007
ops+0.007
 months+0.007
 times+0.007
Neg logit contributions
 sincere-0.007
 faint-0.007
 rapidly-0.007
 source-0.007
Sad-0.007
Token's
Token ID338
Feature activation-5.68e-01

Pos logit contributions
 days+0.106
 weeks+0.094
ops+0.090
 times+0.087
 months+0.085
Neg logit contributions
 sincere-0.073
 faint-0.072
 startled-0.072
 rapidly-0.072
 source-0.071
Token friend
Token ID1545
Feature activation-1.86e+00

Pos logit contributions
 sincere+0.020
 faint+0.020
 source+0.019
 rapidly+0.019
Sad+0.019
Neg logit contributions
 days-0.033
 weeks-0.030
ops-0.029
 months-0.027
 times-0.027
Token Emma
Token ID18966
Feature activation-2.00e+00

Pos logit contributions
 sincere+0.083
 rapidly+0.083
 widen+0.083
 faint+0.082
itating+0.082
Neg logit contributions
 days-0.093
 weeks-0.081
ops-0.074
 months-0.070
 times-0.070
Token But
Token ID887
Feature activation-7.00e-01

Pos logit contributions
fly+0.006
Sad+0.006
 faint+0.006
 widen+0.006
 rapidly+0.006
Neg logit contributions
 days-0.009
 weeks-0.008
ops-0.007
 day-0.007
 months-0.007
Token her
Token ID607
Feature activation+1.83e+00

Pos logit contributions
 sincere+0.030
 rapidly+0.029
 source+0.028
 faint+0.028
itating+0.028
Neg logit contributions
 days-0.036
ops-0.031
 weeks-0.031
 times-0.028
 months-0.028
Token mom
Token ID1995
Feature activation-1.80e+00

Pos logit contributions
 days+0.112
 weeks+0.101
ops+0.097
 months+0.092
 times+0.090
Neg logit contributions
 sincere-0.061
 faint-0.058
 rapidly-0.057
 source-0.056
 widen-0.055
Token said
Token ID531
Feature activation+9.59e-01

Pos logit contributions
 sincere+0.080
 rapidly+0.079
 faint+0.078
 widen+0.078
Sad+0.077
Neg logit contributions
 days-0.090
 weeks-0.079
ops-0.074
 months-0.069
 times-0.069
Token,
Token ID11
Feature activation-1.48e-01

Pos logit contributions
 days+0.054
 weeks+0.048
ops+0.047
 times+0.044
 months+0.044
Neg logit contributions
 sincere-0.037
 faint-0.034
 rapidly-0.033
 startled-0.032
 widen-0.031
Token �
Token ID6184
Feature activation+5.94e+00

Pos logit contributions
 sincere+0.005
 faint+0.005
 rapidly+0.005
Sad+0.005
 widen+0.004
Neg logit contributions
 days-0.009
 weeks-0.008
ops-0.008
 times-0.007
 months-0.007
Token�
Token ID95
Feature activation+4.04e+00

Pos logit contributions
 days+0.327
 weeks+0.287
ops+0.268
 months+0.255
 times+0.255
Neg logit contributions
 sincere-0.238
 rapidly-0.234
 faint-0.232
 widen-0.231
Sad-0.227
Token€
Token ID26391
Feature activation-1.40e+00

Pos logit contributions
 days+0.237
 weeks+0.210
ops+0.197
 times+0.191
 months+0.188
Neg logit contributions
 sincere-0.145
 rapidly-0.143
 widen-0.142
 faint-0.141
Sad-0.140
Token�
Token ID129
Feature activation-3.26e-01

Pos logit contributions
 sincere+0.055
Jud+0.055
anne+0.054
 faint+0.053
Sad+0.053
Neg logit contributions
 days-0.076
 weeks-0.067
 times-0.063
 months-0.060
 nights-0.059
Token�
Token ID241
Feature activation-3.31e+00

Pos logit contributions
 sincere+0.011
fly+0.011
 faint+0.011
 rapidly+0.011
Sad+0.011
Neg logit contributions
 days-0.020
 weeks-0.018
ops-0.017
 times-0.016
 months-0.016
TokenNo
Token ID2949
Feature activation+3.68e+00

Pos logit contributions
 sincere+0.119
 rapidly+0.118
 faint+0.118
 widen+0.116
Sad+0.115
Neg logit contributions
 days-0.193
 weeks-0.171
ops-0.162
 months-0.154
 times-0.153
Token<|endoftext|>
Token ID50256
Feature activation+2.29e+00

Pos logit contributions
 sincere+0.015
 rapidly+0.014
 widen+0.014
 faint+0.014
 source+0.014
Neg logit contributions
 days-0.026
 weeks-0.023
ops-0.022
 months-0.021
 times-0.021
TokenAlice
Token ID44484
Feature activation-2.71e+00

Pos logit contributions
 days+0.137
 weeks+0.121
ops+0.114
 months+0.109
 times+0.108
Neg logit contributions
 sincere-0.080
 rapidly-0.079
 faint-0.078
 widen-0.078
Sad-0.076
Token and
Token ID290
Feature activation+1.69e+00

Pos logit contributions
fly+0.105
 sincere+0.105
 rapidly+0.104
ff+0.103
 widen+0.101
Neg logit contributions
 days-0.145
 weeks-0.128
 times-0.118
ops-0.118
 months-0.113
Token her
Token ID607
Feature activation+2.13e+00

Pos logit contributions
 days+0.095
 weeks+0.084
ops+0.080
 months+0.075
 times+0.075
Neg logit contributions
 sincere-0.066
 faint-0.064
 rapidly-0.064
 widen-0.063
Sad-0.062
Token mom
Token ID1995
Feature activation-1.95e+00

Pos logit contributions
 days+0.125
 weeks+0.112
ops+0.106
 times+0.101
 months+0.101
Neg logit contributions
 sincere-0.077
 faint-0.075
 rapidly-0.074
 widen-0.073
 source-0.072
Token went
Token ID1816
Feature activation+6.54e+00

Pos logit contributions
 sincere+0.062
ff+0.057
fly+0.057
 widen+0.057
 rapidly+0.056
Neg logit contributions
 days-0.120
 weeks-0.107
ops-0.102
 times-0.099
 months-0.095
Token to
Token ID284
Feature activation-1.96e+00

Pos logit contributions
 days+0.380
 weeks+0.341
ops+0.325
 times+0.308
 months+0.304
Neg logit contributions
 sincere-0.233
 rapidly-0.232
 source-0.231
 faint-0.229
itating-0.226
Token the
Token ID262
Feature activation+2.02e+00

Pos logit contributions
 sincere+0.101
 rapidly+0.100
itating+0.099
fly+0.099
 widen+0.098
Neg logit contributions
 days-0.086
 weeks-0.072
 months-0.062
 later-0.062
 times-0.062
Token grocery
Token ID16918
Feature activation+7.67e+00

Pos logit contributions
 days+0.088
 weeks+0.074
ops+0.066
 months+0.064
 times+0.062
Neg logit contributions
 sincere-0.103
 rapidly-0.102
 widen-0.102
Sad-0.101
 faint-0.100
Token store
Token ID3650
Feature activation+6.15e+00

Pos logit contributions
 days+0.416
ops+0.370
 weeks+0.367
 times+0.340
 nights+0.325
Neg logit contributions
 source-0.299
itating-0.268
 rapidly-0.259
 perplex-0.253
itance-0.250
Token.
Token ID13
Feature activation-2.00e-01

Pos logit contributions
 days+0.354
 weeks+0.320
ops+0.311
 times+0.292
 nights+0.288
Neg logit contributions
 source-0.221
itating-0.199
 rapidly-0.196
 faint-0.191
 perplex-0.191
Token.
Token ID13
Feature activation-3.64e-01

Pos logit contributions
fly+0.081
 faint+0.081
 sincere+0.081
 rapidly+0.080
 source+0.080
Neg logit contributions
 days-0.094
 weeks-0.082
ops-0.078
 months-0.072
 times-0.070
Token
Token ID198
Feature activation-1.40e+00

Pos logit contributions
 sincere+0.012
 rapidly+0.011
 widen+0.011
 faint+0.011
 source+0.011
Neg logit contributions
 days-0.023
 weeks-0.020
ops-0.019
 months-0.018
 times-0.018
Token
Token ID198
Feature activation-1.45e+00

Pos logit contributions
 sincere+0.063
 widen+0.062
fly+0.062
 source+0.060
sing+0.060
Neg logit contributions
 days-0.072
 weeks-0.062
ops-0.057
 months-0.055
 later-0.055
TokenFrom
Token ID4863
Feature activation+5.34e+00

Pos logit contributions
 sincere+0.046
 rapidly+0.045
 faint+0.044
 widen+0.044
Sad+0.044
Neg logit contributions
 days-0.092
 weeks-0.082
ops-0.078
 months-0.074
 times-0.074
Token that
Token ID326
Feature activation+2.57e-01

Pos logit contributions
 days+0.234
 weeks+0.198
ops+0.180
 months+0.169
 times+0.169
Neg logit contributions
 sincere-0.273
 rapidly-0.270
 widen-0.269
 faint-0.268
Sad-0.265
Token day
Token ID1110
Feature activation+9.15e+00

Pos logit contributions
 days+0.007
ops+0.007
 weeks+0.006
 cand+0.006
 cents+0.005
Neg logit contributions
fly-0.016
 source-0.015
 faint-0.015
Sad-0.015
 fright-0.015
Token on
Token ID319
Feature activation+9.08e-01

Pos logit contributions
 days+0.442
 cand+0.416
ops+0.405
 weeks+0.398
 times+0.382
Neg logit contributions
 sincere-0.353
 startled-0.345
 rapidly-0.335
itating-0.333
 widen-0.327
Token,
Token ID11
Feature activation-2.18e-02

Pos logit contributions
 days+0.039
ops+0.035
 weeks+0.034
 months+0.030
 nights+0.030
Neg logit contributions
 sincere-0.042
 faint-0.041
fly-0.040
 rapidly-0.040
Sad-0.040
Token the
Token ID262
Feature activation+1.64e+00

Pos logit contributions
 Maria+0.001
Maria+0.001
 Susan+0.000
bird+0.000
 faint+0.000
Neg logit contributions
 days-0.001
ops-0.001
 weeks-0.001
 times-0.001
 cand-0.001
Token bird
Token ID6512
Feature activation-4.74e+00

Pos logit contributions
 days+0.088
ops+0.080
 weeks+0.078
 times+0.072
 months+0.071
Neg logit contributions
 sincere-0.063
 faint-0.063
 source-0.062
 rapidly-0.060
 widen-0.058
Token and
Token ID290
Feature activation+1.73e+00

Pos logit contributions
fly+0.196
ull+0.176
bird+0.176
 rapidly+0.174
 sincere+0.173
Neg logit contributions
 days-0.249
 weeks-0.220
ops-0.214
 months-0.201
 cand-0.198
Token lady
Token ID10846
Feature activation-1.42e+00

Pos logit contributions
 days+0.008
 weeks+0.007
ops+0.007
 months+0.006
 times+0.006
Neg logit contributions
 sincere-0.007
 faint-0.006
 rapidly-0.006
 widen-0.006
 source-0.006
Token nodded
Token ID14464
Feature activation-6.73e+00

Pos logit contributions
 sincere+0.056
 widen+0.055
 faint+0.055
 rapidly+0.055
Sad+0.054
Neg logit contributions
 days-0.078
 weeks-0.069
ops-0.064
 months-0.061
 times-0.061
Token and
Token ID290
Feature activation+1.65e+00

Pos logit contributions
itating+0.352
Sad+0.351
 sincere+0.347
 faint+0.347
 source+0.347
Neg logit contributions
 days-0.280
 weeks-0.235
ops-0.199
 times-0.199
 months-0.195
Token said
Token ID531
Feature activation+9.08e-01

Pos logit contributions
 days+0.094
 weeks+0.082
ops+0.080
 times+0.075
 months+0.074
Neg logit contributions
 rapidly-0.061
 sincere-0.061
 faint-0.059
 startled-0.059
fly-0.059
Token,
Token ID11
Feature activation-6.22e-02

Pos logit contributions
 days+0.036
 weeks+0.031
ops+0.028
 months+0.026
 times+0.026
Neg logit contributions
 sincere-0.050
 rapidly-0.049
 faint-0.048
 widen-0.048
fly-0.048
Token "
Token ID366
Feature activation+1.38e+00

Pos logit contributions
 sincere+0.002
 rapidly+0.002
 faint+0.002
 widen+0.002
itating+0.002
Neg logit contributions
 days-0.004
 weeks-0.003
ops-0.003
 times-0.003
 months-0.003
TokenIt
Token ID1026
Feature activation-5.70e+00

Pos logit contributions
 days+0.080
 weeks+0.071
ops+0.066
 months+0.063
 times+0.063
Neg logit contributions
 sincere-0.051
 rapidly-0.050
 faint-0.049
 widen-0.049
fly-0.048
Token's
Token ID338
Feature activation-6.88e-01

Pos logit contributions
fly+0.260
 sincere+0.258
 rapidly+0.251
 faint+0.250
itating+0.248
Neg logit contributions
 days-0.286
 weeks-0.250
ops-0.228
 months-0.220
 times-0.215
Token not
Token ID407
Feature activation-2.13e+00

Pos logit contributions
 sincere+0.024
 rapidly+0.024
 faint+0.023
 widen+0.023
 source+0.023
Neg logit contributions
 days-0.041
 weeks-0.037
ops-0.036
 times-0.033
 months-0.033
Token easy
Token ID2562
Feature activation+3.04e+00

Pos logit contributions
 sincere+0.083
 faint+0.082
 source+0.081
 widen+0.081
 rapidly+0.081
Neg logit contributions
 days-0.119
 weeks-0.105
ops-0.104
 months-0.094
 times-0.091
Token to
Token ID284
Feature activation-1.99e+00

Pos logit contributions
 days+0.177
ops+0.169
 weeks+0.164
 months+0.150
mm+0.148
Neg logit contributions
 rapidly-0.084
 source-0.084
 faint-0.082
 fright-0.080
 sincere-0.076
Token learned
Token ID4499
Feature activation+2.76e+00

Pos logit contributions
 sincere+0.204
 widen+0.195
 faint+0.195
 rapidly+0.194
fly+0.190
Neg logit contributions
 days-0.224
 weeks-0.194
ops-0.183
 months-0.170
 times-0.169
Token that
Token ID326
Feature activation+1.46e-01

Pos logit contributions
 days+0.112
 weeks+0.091
 things+0.080
 times+0.079
 later+0.077
Neg logit contributions
 widen-0.152
 rapidly-0.150
itating-0.149
fly-0.148
 sincere-0.148
Token climbing
Token ID14281
Feature activation+3.45e+00

Pos logit contributions
 days+0.007
ops+0.006
 weeks+0.006
 months+0.005
ip+0.005
Neg logit contributions
 faint-0.007
 sincere-0.006
 source-0.006
ull-0.006
fly-0.006
Token trees
Token ID7150
Feature activation-3.27e+00

Pos logit contributions
 days+0.165
 weeks+0.147
ops+0.139
 months+0.126
 times+0.125
Neg logit contributions
 rapidly-0.149
fly-0.149
 sincere-0.148
 faint-0.146
 source-0.144
Token can
Token ID460
Feature activation-2.25e-01

Pos logit contributions
fly+0.136
 faint+0.134
 sincere+0.131
 widen+0.131
 rapidly+0.128
Neg logit contributions
 days-0.169
 weeks-0.152
ops-0.136
 months-0.133
 nights-0.131
Token be
Token ID307
Feature activation+4.65e-01

Pos logit contributions
 sincere+0.009
 rapidly+0.009
Sad+0.009
itating+0.009
 widen+0.009
Neg logit contributions
 days-0.012
 weeks-0.011
ops-0.010
 times-0.010
 months-0.009
Token fun
Token ID1257
Feature activation+2.89e+00

Pos logit contributions
 days+0.028
ops+0.025
 weeks+0.025
 months+0.022
 times+0.022
Neg logit contributions
 sincere-0.016
 faint-0.016
 rapidly-0.016
 widen-0.016
 source-0.015
Token but
Token ID475
Feature activation-1.03e+00

Pos logit contributions
ops+0.157
 days+0.154
 weeks+0.146
ip+0.136
mm+0.134
Neg logit contributions
 faint-0.087
 rapidly-0.084
 source-0.082
fly-0.082
 sincere-0.082
Token also
Token ID635
Feature activation-4.52e+00

Pos logit contributions
 sincere+0.043
 rapidly+0.043
 widen+0.042
 faint+0.042
Sad+0.042
Neg logit contributions
 days-0.055
 weeks-0.048
ops-0.044
 times-0.042
 months-0.042
Token dangerous
Token ID4923
Feature activation-1.14e+00

Pos logit contributions
 sincere+0.180
 faint+0.172
fly+0.167
 source+0.166
 widen+0.166
Neg logit contributions
 days-0.253
 weeks-0.227
ops-0.225
 months-0.201
 nights-0.196
Token.
Token ID13
Feature activation-1.17e-01

Pos logit contributions
 sincere+0.036
 faint+0.035
 rapidly+0.034
fly+0.034
 source+0.033
Neg logit contributions
 days-0.061
ops-0.060
 weeks-0.059
ip-0.054
 months-0.052
Token proud
Token ID6613
Feature activation-1.53e+00

Pos logit contributions
 rapidly+0.064
 widen+0.064
Sad+0.063
 faint+0.062
fly+0.062
Neg logit contributions
 days-0.087
 weeks-0.076
 months-0.067
ops-0.066
 later-0.065
Token of
Token ID286
Feature activation-2.30e+00

Pos logit contributions
 faint+0.051
 sincere+0.048
 rapidly+0.047
 startled+0.047
 source+0.046
Neg logit contributions
 days-0.087
ops-0.085
 weeks-0.079
 months-0.072
 nights-0.069
Token him
Token ID683
Feature activation-1.63e+00

Pos logit contributions
 sincere+0.080
 faint+0.072
 rapidly+0.071
Sad+0.068
 fright+0.066
Neg logit contributions
 days-0.137
ops-0.128
 weeks-0.123
 months-0.112
 times-0.111
Token because
Token ID780
Feature activation+1.52e+00

Pos logit contributions
 source+0.056
 faint+0.056
 rapidly+0.055
 sincere+0.055
fly+0.054
Neg logit contributions
 days-0.086
 weeks-0.078
ops-0.077
 nights-0.070
 months-0.069
Token he
Token ID339
Feature activation+2.28e+00

Pos logit contributions
 days+0.065
ops+0.058
 weeks+0.056
 months+0.048
 times+0.048
Neg logit contributions
 sincere-0.075
 faint-0.074
 rapidly-0.072
ull-0.070
Sad-0.070
Token had
Token ID550
Feature activation+1.40e+00

Pos logit contributions
 days+0.116
 weeks+0.100
ops+0.093
 times+0.090
 months+0.088
Neg logit contributions
 sincere-0.100
 rapidly-0.098
 faint-0.097
fly-0.097
 widen-0.095
Token been
Token ID587
Feature activation+5.10e-01

Pos logit contributions
 days+0.076
 weeks+0.067
ops+0.064
 times+0.060
 months+0.060
Neg logit contributions
 sincere-0.055
 faint-0.054
 rapidly-0.054
 source-0.053
 widen-0.053
Token so
Token ID523
Feature activation+1.71e+00

Pos logit contributions
 days+0.027
 weeks+0.023
ops+0.021
 months+0.020
 times+0.020
Neg logit contributions
 sincere-0.022
 rapidly-0.022
 widen-0.021
 faint-0.021
Sad-0.021
Token brave
Token ID14802
Feature activation-1.62e+00

Pos logit contributions
 days+0.092
 weeks+0.081
ops+0.075
 months+0.072
 times+0.072
Neg logit contributions
 sincere-0.069
 rapidly-0.068
 widen-0.068
 faint-0.068
Sad-0.067
Token and
Token ID290
Feature activation+1.59e+00

Pos logit contributions
 rapidly+0.056
 source+0.053
 fright+0.053
 menacing+0.052
 startled+0.052
Neg logit contributions
ops-0.087
 days-0.082
mm-0.075
 weeks-0.074
 cand-0.069
Token listened
Token ID16399
Feature activation-2.46e+00

Pos logit contributions
 days+0.093
ops+0.089
 weeks+0.085
 times+0.078
 months+0.076
Neg logit contributions
 faint-0.055
 sincere-0.055
 startled-0.051
 menacing-0.051
 rapidly-0.050
Token busy
Token ID8179
Feature activation-2.24e+00

Pos logit contributions
Sad+0.044
 rapidly+0.044
 widen+0.044
fly+0.043
itating+0.043
Neg logit contributions
 days-0.073
 weeks-0.064
ops-0.058
 times-0.058
 months-0.057
Token with
Token ID351
Feature activation+8.21e-02

Pos logit contributions
 source+0.070
 rapidly+0.069
 faint+0.069
 sincere+0.066
 startled+0.062
Neg logit contributions
ops-0.127
 days-0.123
 weeks-0.114
mm-0.111
ip-0.111
Token all
Token ID477
Feature activation-3.00e+00

Pos logit contributions
 days+0.005
ops+0.004
 weeks+0.004
 months+0.004
 times+0.004
Neg logit contributions
 faint-0.003
 sincere-0.003
 rapidly-0.003
 source-0.003
 fright-0.003
Token of
Token ID286
Feature activation-2.20e+00

Pos logit contributions
 faint+0.106
 rapidly+0.105
 sincere+0.103
 source+0.103
Sad+0.102
Neg logit contributions
 days-0.168
ops-0.156
 weeks-0.152
 months-0.137
 times-0.130
Token the
Token ID262
Feature activation+1.91e+00

Pos logit contributions
 sincere+0.086
 rapidly+0.085
 faint+0.084
 widen+0.084
Sad+0.083
Neg logit contributions
 days-0.122
 weeks-0.108
ops-0.100
 months-0.096
 times-0.096
Token other
Token ID584
Feature activation+4.44e-01

Pos logit contributions
 days+0.078
 weeks+0.068
ops+0.066
 months+0.057
 times+0.056
Neg logit contributions
 faint-0.098
 source-0.098
 rapidly-0.098
 sincere-0.097
 widen-0.096
Token gears
Token ID28713
Feature activation+1.17e+00

Pos logit contributions
 days+0.016
ops+0.015
 weeks+0.015
 later+0.013
ip+0.013
Neg logit contributions
 source-0.022
 faint-0.022
 rapidly-0.022
 widen-0.021
 hood-0.020
Token.
Token ID13
Feature activation+4.34e-02

Pos logit contributions
 days+0.067
 weeks+0.063
ops+0.057
 months+0.056
 times+0.054
Neg logit contributions
 source-0.039
 rapidly-0.039
fly-0.038
itating-0.037
 sincere-0.036
Token Every
Token ID3887
Feature activation+3.85e+00

Pos logit contributions
 days+0.002
 weeks+0.002
 day+0.002
 months+0.002
ops+0.002
Neg logit contributions
fly-0.002
 sincere-0.002
itating-0.002
 rapidly-0.002
 widen-0.002
Token day
Token ID1110
Feature activation+8.79e+00

Pos logit contributions
 days+0.082
ops+0.072
 weeks+0.063
 cand+0.052
 months+0.045
Neg logit contributions
 faint-0.264
 rapidly-0.262
 source-0.259
ull-0.256
 fright-0.256
Token,
Token ID11
Feature activation-8.36e-02

Pos logit contributions
 days+0.390
ops+0.353
 weeks+0.352
 times+0.318
 months+0.305
Neg logit contributions
 faint-0.384
 rapidly-0.378
 sincere-0.377
 widen-0.374
 startled-0.373
Tokenite
Token ID578
Feature activation-9.90e-01

Pos logit contributions
 days+0.101
 weeks+0.082
ops+0.080
 times+0.069
 months+0.067
Neg logit contributions
 widen-0.158
 faint-0.156
 sincere-0.156
 rapidly-0.155
 source-0.150
Token in
Token ID287
Feature activation-5.15e+00

Pos logit contributions
fly+0.040
 sincere+0.040
 rapidly+0.040
 source+0.039
 faint+0.039
Neg logit contributions
 days-0.054
 weeks-0.049
ops-0.044
 months-0.043
 nights-0.042
Token the
Token ID262
Feature activation+1.78e+00

Pos logit contributions
 sincere+0.269
itating+0.267
 rapidly+0.260
 widen+0.259
fly+0.258
Neg logit contributions
 days-0.229
 weeks-0.197
 times-0.172
 months-0.167
 later-0.159
Token sky
Token ID6766
Feature activation-5.55e+00

Pos logit contributions
 days+0.087
 weeks+0.074
ops+0.065
 months+0.064
 times+0.063
Neg logit contributions
 sincere-0.084
 rapidly-0.084
fly-0.083
Sad-0.082
 faint-0.082
Token with
Token ID351
Feature activation+1.55e-01

Pos logit contributions
 sincere+0.261
 rapidly+0.260
 faint+0.259
 widen+0.257
 source+0.255
Neg logit contributions
 days-0.262
 weeks-0.226
ops-0.209
 months-0.196
 times-0.195
Token a
Token ID257
Feature activation+6.00e-01

Pos logit contributions
 days+0.008
 weeks+0.006
 times+0.006
 things+0.006
 day+0.005
Neg logit contributions
itating-0.008
Sad-0.008
fly-0.007
anne-0.007
 outage-0.007
Token license
Token ID5964
Feature activation+1.98e+00

Pos logit contributions
 days+0.027
 day+0.023
 things+0.022
 times+0.022
 weeks+0.022
Neg logit contributions
idget-0.028
Maria-0.027
rant-0.026
Sad-0.026
anne-0.026
Token attached
Token ID7223
Feature activation-2.51e-01

Pos logit contributions
 days+0.101
 weeks+0.090
ops+0.082
 months+0.079
 times+0.078
Neg logit contributions
 sincere-0.086
 rapidly-0.085
 source-0.085
fly-0.084
 faint-0.084
Token.
Token ID13
Feature activation-2.76e-01

Pos logit contributions
 sincere+0.011
Sad+0.011
 widen+0.011
 faint+0.011
 rapidly+0.010
Neg logit contributions
 days-0.013
 weeks-0.011
ops-0.010
 times-0.010
 months-0.010
Token He
Token ID679
Feature activation-2.08e+00

Pos logit contributions
 widen+0.009
 sincere+0.009
 rapidly+0.009
 faint+0.009
itating+0.009
Neg logit contributions
 days-0.017
 weeks-0.015
ops-0.014
 months-0.014
 times-0.013
Token asked
Token ID1965
Feature activation-1.24e+00

Pos logit contributions
 sincere+0.093
 rapidly+0.091
 widen+0.091
 faint+0.091
Sad+0.090
Neg logit contributions
 days-0.104
 weeks-0.091
ops-0.084
 months-0.079
 times-0.079
Token,
Token ID11
Feature activation-2.98e-01

Pos logit contributions
 sincere+0.007
 rapidly+0.007
 faint+0.007
 widen+0.007
 fright+0.007
Neg logit contributions
 days-0.007
 weeks-0.006
ops-0.005
 months-0.005
 times-0.005
Token it
Token ID340
Feature activation-1.95e+00

Pos logit contributions
 faint+0.011
 sincere+0.011
 fright+0.010
fly+0.010
 widen+0.010
Neg logit contributions
 days-0.017
ops-0.016
 weeks-0.015
 months-0.014
 times-0.014
Token's
Token ID338
Feature activation-8.11e-01

Pos logit contributions
fly+0.085
 widen+0.083
 sincere+0.083
itating+0.081
 startled+0.081
Neg logit contributions
 days-0.105
 weeks-0.092
 months-0.081
 times-0.079
 nights-0.079
Token w
Token ID266
Feature activation+1.28e+00

Pos logit contributions
 sincere+0.028
 rapidly+0.028
 faint+0.027
 widen+0.027
Sad+0.027
Neg logit contributions
 days-0.049
 weeks-0.043
ops-0.041
 months-0.039
 times-0.039
Tokenobb
Token ID21963
Feature activation-1.44e+00

Pos logit contributions
 days+0.081
 weeks+0.073
ops+0.068
 months+0.066
 times+0.066
Neg logit contributions
 sincere-0.040
 rapidly-0.039
 faint-0.038
 widen-0.038
itating-0.037
Tokenly
Token ID306
Feature activation-4.42e+00

Pos logit contributions
 widen+0.048
 rapidly+0.048
ff+0.046
fly+0.046
 source+0.045
Neg logit contributions
 days-0.082
 weeks-0.076
 months-0.068
 nights-0.065
ops-0.065
Token.
Token ID13
Feature activation-2.13e-01

Pos logit contributions
 source+0.156
fly+0.149
 faint+0.149
 widen+0.144
 hood+0.140
Neg logit contributions
 days-0.248
 weeks-0.231
ops-0.219
 months-0.202
 nights-0.198
Token See
Token ID4091
Feature activation+1.18e+00

Pos logit contributions
 sincere+0.008
 rapidly+0.007
 faint+0.007
 widen+0.007
itating+0.007
Neg logit contributions
 days-0.013
 weeks-0.011
ops-0.010
 months-0.010
 times-0.010
Token?"
Token ID1701
Feature activation-3.72e+00

Pos logit contributions
 days+0.061
 weeks+0.055
ops+0.054
 months+0.051
 nights+0.049
Neg logit contributions
 sincere-0.048
 faint-0.043
fly-0.043
 clearly-0.042
 fright-0.042
Token
Token ID198
Feature activation-1.75e+00

Pos logit contributions
 rapidly+0.145
itating+0.143
fly+0.143
 sincere+0.143
 widen+0.142
Neg logit contributions
 days-0.207
 weeks-0.181
ops-0.168
 months-0.163
 times-0.160
Token
Token ID198
Feature activation-1.76e+00

Pos logit contributions
fly+0.095
itating+0.091
 widen+0.090
sing+0.090
 rapidly+0.090
Neg logit contributions
 days-0.075
 weeks-0.062
 later-0.057
ops-0.052
 months-0.052
Token don
Token ID836
Feature activation+3.62e+00

Pos logit contributions
 sincere+0.031
 rapidly+0.031
 faint+0.031
 widen+0.030
Sad+0.030
Neg logit contributions
 days-0.039
 weeks-0.034
ops-0.032
 times-0.030
 months-0.030
Token't
Token ID470
Feature activation-3.58e+00

Pos logit contributions
 days+0.263
 weeks+0.239
ops+0.224
 months+0.219
 times+0.218
Neg logit contributions
 sincere-0.081
 faint-0.079
 widen-0.079
 rapidly-0.079
Sad-0.077
Token want
Token ID765
Feature activation+3.03e+00

Pos logit contributions
 faint+0.109
 fright+0.109
 sincere+0.107
 widen+0.106
 rapidly+0.105
Neg logit contributions
 days-0.227
 weeks-0.205
ops-0.197
 months-0.187
 nights-0.182
Token my
Token ID616
Feature activation+1.86e+00

Pos logit contributions
 days+0.180
 weeks+0.162
ops+0.158
 months+0.146
 nights+0.143
Neg logit contributions
 faint-0.101
 sincere-0.100
 source-0.100
 rapidly-0.099
 fright-0.099
Token brother
Token ID3956
Feature activation+1.16e+00

Pos logit contributions
 days+0.098
 weeks+0.091
ops+0.086
 months+0.081
 nights+0.078
Neg logit contributions
 source-0.075
 sincere-0.074
 faint-0.074
 fright-0.073
fly-0.071
Token to
Token ID284
Feature activation-2.08e+00

Pos logit contributions
 days+0.068
 weeks+0.063
 months+0.058
 nights+0.056
ops+0.054
Neg logit contributions
 fright-0.041
fly-0.040
 startled-0.039
 sincere-0.038
 source-0.037
Token suffer
Token ID8659
Feature activation-3.74e+00

Pos logit contributions
 sincere+0.086
 rapidly+0.085
 faint+0.084
 widen+0.084
Sad+0.084
Neg logit contributions
 days-0.109
 weeks-0.096
ops-0.089
 times-0.085
 months-0.084
Token.
Token ID13
Feature activation-1.43e-01

Pos logit contributions
 rapidly+0.164
 faint+0.162
 sincere+0.161
 widen+0.159
 source+0.156
Neg logit contributions
 days-0.187
 weeks-0.164
ops-0.158
 months-0.143
 times-0.138
Token Can
Token ID1680
Feature activation+1.22e+00

Pos logit contributions
 rapidly+0.005
 sincere+0.005
 source+0.005
 widen+0.005
 faint+0.005
Neg logit contributions
 days-0.008
 weeks-0.007
ops-0.007
 months-0.006
 times-0.006
Token we
Token ID356
Feature activation+3.19e+00

Pos logit contributions
 days+0.044
 weeks+0.036
ops+0.032
 months+0.029
 times+0.029
Neg logit contributions
 sincere-0.072
 rapidly-0.071
 faint-0.071
 widen-0.070
Sad-0.070
Token give
Token ID1577
Feature activation+4.12e+00

Pos logit contributions
 days+0.113
 later+0.097
 weeks+0.092
ops+0.090
 day+0.090
Neg logit contributions
anne-0.176
 rapidly-0.174
 perplex-0.174
Sad-0.173
Maria-0.173
Token picks
Token ID11103
Feature activation+3.01e+00

Pos logit contributions
 sincere+0.103
 rapidly+0.102
 faint+0.101
 widen+0.100
Sad+0.098
Neg logit contributions
 days-0.127
 weeks-0.111
ops-0.103
 times-0.098
 months-0.098
Token it
Token ID340
Feature activation-2.65e+00

Pos logit contributions
 days+0.179
 weeks+0.159
ops+0.150
 times+0.143
 months+0.143
Neg logit contributions
 sincere-0.107
 rapidly-0.104
 faint-0.104
 widen-0.103
Sad-0.102
Token up
Token ID510
Feature activation-5.99e+00

Pos logit contributions
 sincere+0.082
 rapidly+0.080
 faint+0.079
 widen+0.079
Sad+0.077
Neg logit contributions
 days-0.170
 weeks-0.152
ops-0.144
 months-0.138
 times-0.138
Token and
Token ID290
Feature activation+2.64e-01

Pos logit contributions
 rapidly+0.289
 sincere+0.286
 faint+0.282
 widen+0.281
 source+0.277
Neg logit contributions
 days-0.278
 weeks-0.238
ops-0.225
 months-0.206
 times-0.204
Token kicks
Token ID17364
Feature activation+1.15e+00

Pos logit contributions
 days+0.014
 weeks+0.012
ops+0.011
 times+0.010
 months+0.010
Neg logit contributions
 sincere-0.012
 widen-0.011
 rapidly-0.011
 faint-0.011
 source-0.011
Token it
Token ID340
Feature activation-2.45e+00

Pos logit contributions
 days+0.065
 weeks+0.057
ops+0.054
 months+0.051
 times+0.051
Neg logit contributions
 rapidly-0.043
 sincere-0.043
 faint-0.042
 widen-0.042
Sad-0.042
Token hard
Token ID1327
Feature activation-1.09e+00

Pos logit contributions
 rapidly+0.096
 widen+0.091
 sincere+0.091
fly+0.091
 faint+0.091
Neg logit contributions
 days-0.136
 weeks-0.123
ops-0.116
 months-0.110
 nights-0.107
Token.
Token ID13
Feature activation-1.15e+00

Pos logit contributions
 rapidly+0.041
 source+0.038
 widen+0.036
fly+0.035
 fright+0.035
Neg logit contributions
 days-0.058
 weeks-0.053
ops-0.052
 nights-0.047
 months-0.047
Token The
Token ID383
Feature activation-1.56e+00

Pos logit contributions
fly+0.044
 sincere+0.044
 rapidly+0.043
 widen+0.043
 source+0.043
Neg logit contributions
 days-0.064
 weeks-0.056
ops-0.053
 months-0.050
 later-0.049
Token ball
Token ID2613
Feature activation+1.77e+00

Pos logit contributions
 sincere+0.061
 faint+0.059
 source+0.058
 rapidly+0.058
 widen+0.057
Neg logit contributions
 days-0.086
 weeks-0.077
ops-0.073
 months-0.068
 times-0.067
Token flies
Token ID17607
Feature activation+1.79e+00

Pos logit contributions
 days+0.088
 weeks+0.076
ops+0.069
 months+0.067
 nights+0.065
Neg logit contributions
 sincere-0.081
 rapidly-0.081
 widen-0.080
 faint-0.079
fly-0.078
Token listen
Token ID6004
Feature activation-6.67e-01

Pos logit contributions
 sincere+0.093
Sad+0.091
 rapidly+0.090
fly+0.090
 faint+0.090
Neg logit contributions
 days-0.132
 weeks-0.116
ops-0.107
 times-0.107
 months-0.103
Token to
Token ID284
Feature activation-2.25e+00

Pos logit contributions
 sincere+0.027
 rapidly+0.027
 faint+0.026
 widen+0.026
itating+0.026
Neg logit contributions
 days-0.036
 weeks-0.032
ops-0.030
 months-0.028
 times-0.028
Token each
Token ID1123
Feature activation-3.64e+00

Pos logit contributions
itating+0.096
 sincere+0.095
fly+0.094
 rapidly+0.094
 widen+0.093
Neg logit contributions
 days-0.121
 weeks-0.105
 times-0.099
 months-0.092
ops-0.090
Token other
Token ID584
Feature activation+3.09e-01

Pos logit contributions
 source+0.170
 faint+0.169
 rapidly+0.168
Sad+0.167
 fright+0.167
Neg logit contributions
 days-0.164
ops-0.143
 weeks-0.142
 months-0.125
 nights-0.122
Token.
Token ID13
Feature activation-5.85e-01

Pos logit contributions
 days+0.018
 weeks+0.016
ops+0.015
 months+0.014
 nights+0.014
Neg logit contributions
 rapidly-0.011
 widen-0.011
itating-0.011
 sincere-0.011
 faint-0.011
Token They
Token ID1119
Feature activation+7.41e-02

Pos logit contributions
fly+0.028
 rapidly+0.027
 widen+0.027
 sincere+0.027
itating+0.026
Neg logit contributions
 days-0.029
 weeks-0.024
 months-0.022
ops-0.020
 later-0.020
Token do
Token ID466
Feature activation+1.53e+00

Pos logit contributions
 days+0.003
 weeks+0.003
ops+0.003
 times+0.003
 months+0.002
Neg logit contributions
Sad-0.004
ull-0.004
fly-0.004
Maria-0.004
 faint-0.004
Token not
Token ID407
Feature activation-2.31e+00

Pos logit contributions
 days+0.110
 weeks+0.099
ops+0.095
 months+0.091
 nights+0.090
Neg logit contributions
 sincere-0.038
 faint-0.035
 rapidly-0.035
 widen-0.035
itating-0.034
Token realize
Token ID6537
Feature activation-1.55e+00

Pos logit contributions
 sincere+0.097
Sad+0.095
 rapidly+0.095
itating+0.095
 faint+0.095
Neg logit contributions
 days-0.121
 weeks-0.105
ops-0.097
 times-0.096
 months-0.093
Token that
Token ID326
Feature activation+2.45e-01

Pos logit contributions
 sincere+0.071
 faint+0.070
 rapidly+0.069
Sad+0.068
fly+0.066
Neg logit contributions
 days-0.075
 weeks-0.066
ops-0.064
 months-0.057
 nights-0.056
Token the
Token ID262
Feature activation+1.61e+00

Pos logit contributions
 days+0.013
ops+0.012
 weeks+0.012
 months+0.010
 nights+0.010
Neg logit contributions
 sincere-0.009
 faint-0.009
 rapidly-0.009
 fright-0.009
 source-0.009
Token the
Token ID262
Feature activation+1.80e+00

Pos logit contributions
 faint+0.190
 rapidly+0.186
 source+0.184
 sincere+0.183
Sad+0.182
Neg logit contributions
 days-0.287
ops-0.263
 weeks-0.258
 months-0.230
 times-0.227
Token garden
Token ID11376
Feature activation+1.37e+00

Pos logit contributions
 days+0.093
 weeks+0.082
ops+0.077
 months+0.072
 times+0.072
Neg logit contributions
 sincere-0.077
 rapidly-0.076
 faint-0.076
 widen-0.075
Sad-0.074
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
 days+0.063
 weeks+0.056
ops+0.054
 months+0.049
 times+0.049
Neg logit contributions
 source-0.064
 rapidly-0.063
 faint-0.061
 sincere-0.061
itating-0.060
Token He
Token ID679
Feature activation-1.67e+00

Pos logit contributions
 days+0.007
 weeks+0.006
ops+0.006
 months+0.006
 times+0.006
Neg logit contributions
 sincere-0.003
 widen-0.003
fly-0.003
 rapidly-0.003
 faint-0.003
Token was
Token ID373
Feature activation-1.28e+00

Pos logit contributions
 sincere+0.055
 rapidly+0.055
 faint+0.054
 widen+0.053
fly+0.052
Neg logit contributions
 days-0.101
 weeks-0.091
ops-0.086
 times-0.082
 months-0.082
Token very
Token ID845
Feature activation-1.18e+00

Pos logit contributions
 sincere+0.062
fly+0.061
 rapidly+0.061
 widen+0.061
 faint+0.061
Neg logit contributions
 days-0.059
 weeks-0.051
ops-0.044
 months-0.044
 times-0.043
Token careful
Token ID8161
Feature activation+3.18e+00

Pos logit contributions
fly+0.051
 sincere+0.050
Sad+0.050
 widen+0.050
 rapidly+0.049
Neg logit contributions
 days-0.062
 weeks-0.054
ops-0.048
 times-0.047
 months-0.047
Token so
Token ID523
Feature activation+1.98e+00

Pos logit contributions
 days+0.164
 weeks+0.146
ops+0.134
 months+0.130
 times+0.125
Neg logit contributions
 rapidly-0.134
 faint-0.134
 source-0.130
itating-0.130
 sincere-0.129
Token he
Token ID339
Feature activation+2.61e+00

Pos logit contributions
 days+0.102
 weeks+0.090
ops+0.089
 months+0.080
 times+0.078
Neg logit contributions
 faint-0.083
 rapidly-0.083
 sincere-0.080
Sad-0.076
 widen-0.076
Token didn
Token ID1422
Feature activation+3.36e+00

Pos logit contributions
 days+0.133
 weeks+0.115
ops+0.107
 months+0.101
 times+0.101
Neg logit contributions
 sincere-0.114
 rapidly-0.112
 faint-0.112
 widen-0.111
Sad-0.109
Token't
Token ID470
Feature activation-3.58e+00

Pos logit contributions
 days+0.183
ops+0.168
 weeks+0.163
 later+0.149
 times+0.147
Neg logit contributions
 sincere-0.132
fly-0.126
 rapidly-0.118
ff-0.118
anne-0.115
Token and
Token ID290
Feature activation+1.69e+00

Pos logit contributions
 days+0.112
 weeks+0.099
ops+0.096
 months+0.086
 times+0.086
Neg logit contributions
 rapidly-0.108
 source-0.104
 faint-0.102
fly-0.101
itating-0.101
Token back
Token ID736
Feature activation-6.55e+00

Pos logit contributions
 days+0.099
 weeks+0.088
ops+0.083
 months+0.079
 times+0.078
Neg logit contributions
 sincere-0.061
 rapidly-0.060
 faint-0.060
 widen-0.060
 source-0.058
Token,
Token ID11
Feature activation-1.56e-01

Pos logit contributions
 rapidly+0.223
 source+0.220
 faint+0.216
fly+0.211
itating+0.207
Neg logit contributions
 days-0.389
 weeks-0.356
ops-0.350
 months-0.318
 times-0.312
Token over
Token ID625
Feature activation-7.56e+00

Pos logit contributions
 sincere+0.006
 rapidly+0.006
 source+0.006
 faint+0.006
 widen+0.006
Neg logit contributions
 days-0.009
 weeks-0.008
ops-0.008
 months-0.007
 times-0.007
Token and
Token ID290
Feature activation+1.70e+00

Pos logit contributions
 faint+0.299
 rapidly+0.297
 source+0.289
 sincere+0.281
 fright+0.279
Neg logit contributions
 days-0.390
ops-0.364
 weeks-0.348
 times-0.312
 cand-0.308
Token over
Token ID625
Feature activation-7.55e+00

Pos logit contributions
 days+0.102
 weeks+0.091
ops+0.087
 months+0.081
 times+0.081
Neg logit contributions
 sincere-0.059
 rapidly-0.059
 widen-0.058
 faint-0.058
 source-0.057
Token again
Token ID757
Feature activation-4.21e+00

Pos logit contributions
 faint+0.291
 rapidly+0.290
 source+0.280
 sincere+0.273
 fright+0.272
Neg logit contributions
 days-0.397
ops-0.373
 weeks-0.355
 times-0.318
 months-0.315
Token.
Token ID13
Feature activation-2.34e-01

Pos logit contributions
 faint+0.167
 rapidly+0.165
 source+0.152
 widen+0.151
 sincere+0.149
Neg logit contributions
 days-0.218
ops-0.205
 weeks-0.196
 cand-0.184
 times-0.176
Token He
Token ID679
Feature activation-1.69e+00

Pos logit contributions
fly+0.010
 sincere+0.009
 rapidly+0.009
 faint+0.009
itating+0.009
Neg logit contributions
 days-0.013
 weeks-0.011
ops-0.011
 months-0.010
 day-0.010
Token liked
Token ID8288
Feature activation-1.05e+00

Pos logit contributions
 rapidly+0.073
 sincere+0.072
 faint+0.071
fly+0.070
Sad+0.069
Neg logit contributions
 days-0.085
 weeks-0.074
ops-0.070
 times-0.066
 months-0.065
Token to
Token ID284
Feature activation-2.00e+00

Pos logit contributions
 faint+0.032
 rapidly+0.031
 source+0.030
 fright+0.029
 sincere+0.029
Neg logit contributions
 days-0.064
ops-0.063
 weeks-0.059
 months-0.054
 times-0.053
Token thought
Token ID1807
Feature activation+1.47e+00

Pos logit contributions
 days+0.083
ops+0.075
 weeks+0.072
 times+0.067
 months+0.065
Neg logit contributions
 sincere-0.055
 rapidly-0.052
 faint-0.050
Maria-0.048
 perplex-0.048
Token,
Token ID11
Feature activation-3.45e-01

Pos logit contributions
 days+0.075
 weeks+0.066
ops+0.063
 months+0.059
 times+0.058
Neg logit contributions
 rapidly-0.061
 faint-0.061
 sincere-0.060
 widen-0.059
Sad-0.058
Token and
Token ID290
Feature activation+1.46e+00

Pos logit contributions
 rapidly+0.012
 faint+0.012
 sincere+0.011
Sad+0.011
 source+0.011
Neg logit contributions
 days-0.020
ops-0.018
 weeks-0.017
 times-0.016
 nights-0.016
Token he
Token ID339
Feature activation+2.33e+00

Pos logit contributions
 days+0.074
ops+0.071
 weeks+0.063
 times+0.061
 months+0.056
Neg logit contributions
 sincere-0.060
 rapidly-0.059
 startled-0.057
 faint-0.056
 perplex-0.055
Token came
Token ID1625
Feature activation-2.27e+00

Pos logit contributions
 days+0.106
 weeks+0.093
ops+0.081
 months+0.079
 later+0.075
Neg logit contributions
itating-0.117
 widen-0.116
 faint-0.115
 source-0.114
 sincere-0.113
Token up
Token ID510
Feature activation-5.68e+00

Pos logit contributions
 sincere+0.079
 rapidly+0.077
 widen+0.077
 faint+0.077
Sad+0.076
Neg logit contributions
 days-0.136
 weeks-0.121
ops-0.113
 months-0.109
 times-0.108
Token with
Token ID351
Feature activation+2.21e-01

Pos logit contributions
 sincere+0.273
 rapidly+0.269
Sad+0.269
 widen+0.268
fly+0.268
Neg logit contributions
 days-0.260
 weeks-0.226
 months-0.195
ops-0.195
 times-0.193
Token an
Token ID281
Feature activation-1.99e-02

Pos logit contributions
 days+0.012
 weeks+0.010
 times+0.009
 months+0.009
 things+0.008
Neg logit contributions
itating-0.010
fly-0.010
Sad-0.009
 rapidly-0.009
 widen-0.009
Token idea
Token ID2126
Feature activation+3.92e+00

Pos logit contributions
 sincere+0.001
 rapidly+0.001
 faint+0.001
 widen+0.001
Sad+0.001
Neg logit contributions
 days-0.001
 weeks-0.001
ops-0.001
 months-0.001
 times-0.001
Token.
Token ID13
Feature activation-4.11e-01

Pos logit contributions
 days+0.225
 weeks+0.206
ops+0.201
 months+0.187
 nights+0.185
Neg logit contributions
 rapidly-0.132
 faint-0.130
 source-0.125
 fright-0.125
Sad-0.125
Token He
Token ID679
Feature activation-2.24e+00

Pos logit contributions
 sincere+0.010
 rapidly+0.010
 faint+0.010
 widen+0.010
Sad+0.009
Neg logit contributions
 days-0.029
 weeks-0.026
ops-0.025
 times-0.024
 months-0.024
Token walked
Token ID6807
Feature activation+4.65e+00

Pos logit contributions
 widen+0.089
 sincere+0.089
itating+0.088
 source+0.087
 faint+0.087
Neg logit contributions
 days-0.077
 weeks-0.066
ops-0.059
 months-0.056
 times-0.056
Token closer
Token ID5699
Feature activation-8.05e+00

Pos logit contributions
 days+0.281
 weeks+0.251
 later+0.225
 months+0.223
 times+0.223
Neg logit contributions
 sincere-0.172
 widen-0.154
Sad-0.153
 faint-0.153
fly-0.149
Token and
Token ID290
Feature activation+1.61e+00

Pos logit contributions
 rapidly+0.345
 faint+0.337
 source+0.331
 widen+0.329
 sincere+0.329
Neg logit contributions
 days-0.412
 weeks-0.363
ops-0.344
 months-0.321
 times-0.316
Token stepped
Token ID10764
Feature activation+2.56e+00

Pos logit contributions
 days+0.075
 weeks+0.066
 later+0.063
 months+0.057
ops+0.055
Neg logit contributions
 sincere-0.075
 widen-0.072
ull-0.070
 faint-0.070
amus-0.069
Token right
Token ID826
Feature activation+5.79e-01

Pos logit contributions
 days+0.135
 weeks+0.118
 months+0.102
 later+0.102
ops+0.101
Neg logit contributions
 sincere-0.113
fly-0.110
 faint-0.108
itating-0.107
 widen-0.106
Token up
Token ID510
Feature activation-5.86e+00

Pos logit contributions
 days+0.033
 weeks+0.029
ops+0.027
 months+0.026
 times+0.026
Neg logit contributions
 sincere-0.022
 rapidly-0.022
 faint-0.022
 widen-0.022
Sad-0.021
Token to
Token ID284
Feature activation-2.22e+00

Pos logit contributions
 rapidly+0.270
 sincere+0.268
 faint+0.267
 widen+0.265
 source+0.262
Neg logit contributions
 days-0.284
 weeks-0.245
ops-0.232
 months-0.213
 times-0.213
Token it
Token ID340
Feature activation-1.91e+00

Pos logit contributions
itating+0.130
itance+0.124
Sad+0.123
 outage+0.122
icker+0.120
Neg logit contributions
 days-0.091
 weeks-0.073
 day-0.068
 things-0.068
 later-0.066
Token.
Token ID13
Feature activation-3.88e-01

Pos logit contributions
 rapidly+0.088
 faint+0.087
 widen+0.087
 sincere+0.087
 source+0.086
Neg logit contributions
 days-0.094
 weeks-0.081
ops-0.075
 months-0.071
 times-0.070
Token
Token ID198
Feature activation-1.64e+00

Pos logit contributions
amus+0.019
ull+0.018
 sincere+0.018
 blurry+0.018
fly+0.018
Neg logit contributions
 days-0.018
 weeks-0.015
 day-0.014
 months-0.013
 things-0.013
Token
Token ID198
Feature activation-1.65e+00

Pos logit contributions
fly+0.110
sing+0.110
 sincere+0.109
 blurry+0.104
 widen+0.104
Neg logit contributions
 days-0.053
 day-0.041
 later-0.039
 weeks-0.037
ops-0.028
Token.
Token ID13
Feature activation-4.63e-02

Pos logit contributions
 days+0.033
 weeks+0.028
ops+0.028
 months+0.025
 times+0.025
Neg logit contributions
 sincere-0.029
 rapidly-0.028
 source-0.027
 faint-0.027
 widen-0.027
Token She
Token ID1375
Feature activation-1.82e+00

Pos logit contributions
 sincere+0.001
 rapidly+0.001
 widen+0.001
 faint+0.001
fly+0.001
Neg logit contributions
 days-0.003
 weeks-0.003
ops-0.002
 months-0.002
 times-0.002
Token put
Token ID1234
Feature activation+4.16e+00

Pos logit contributions
 sincere+0.082
 rapidly+0.081
 faint+0.080
 widen+0.080
Sad+0.079
Neg logit contributions
 days-0.091
 weeks-0.079
ops-0.073
 months-0.069
 times-0.069
Token the
Token ID262
Feature activation+1.80e+00

Pos logit contributions
 days+0.215
 weeks+0.188
ops+0.175
 months+0.165
 times+0.165
Neg logit contributions
 sincere-0.178
 rapidly-0.176
 faint-0.175
 widen-0.174
Sad-0.172
Token onions
Token ID24681
Feature activation+3.41e-01

Pos logit contributions
 days+0.101
 weeks+0.088
ops+0.079
 times+0.078
 months+0.077
Neg logit contributions
fly-0.073
 sincere-0.072
 widen-0.072
 faint-0.072
Sad-0.071
Token back
Token ID736
Feature activation-6.57e+00

Pos logit contributions
 days+0.020
 weeks+0.018
ops+0.018
 months+0.017
 times+0.017
Neg logit contributions
 rapidly-0.011
itating-0.011
fly-0.011
 sincere-0.010
 source-0.010
Token into
Token ID656
Feature activation-4.86e+00

Pos logit contributions
 rapidly+0.266
 sincere+0.261
fly+0.258
itating+0.257
 source+0.255
Neg logit contributions
 days-0.334
 weeks-0.297
ops-0.293
 times-0.266
 months-0.264
Token the
Token ID262
Feature activation+1.81e+00

Pos logit contributions
 sincere+0.226
itating+0.224
 rapidly+0.223
 widen+0.223
fly+0.222
Neg logit contributions
 days-0.239
 weeks-0.208
 months-0.181
 times-0.181
ops-0.179
Token ground
Token ID2323
Feature activation-2.32e+00

Pos logit contributions
 days+0.100
 weeks+0.088
ops+0.081
 months+0.078
 times+0.078
Neg logit contributions
 sincere-0.072
 rapidly-0.072
 widen-0.071
 faint-0.071
Sad-0.070
Token and
Token ID290
Feature activation+1.73e+00

Pos logit contributions
 rapidly+0.103
 source+0.101
 sincere+0.100
 faint+0.100
fly+0.098
Neg logit contributions
 days-0.112
 weeks-0.098
ops-0.096
 times-0.086
 months-0.086
Token said
Token ID531
Feature activation+8.82e-01

Pos logit contributions
 days+0.090
ops+0.078
 weeks+0.078
 times+0.071
 months+0.069
Neg logit contributions
 sincere-0.070
 rapidly-0.069
 faint-0.068
 source-0.066
 startled-0.066
Token at
Token ID379
Feature activation-6.93e-01

Pos logit contributions
Sad+0.249
 faint+0.247
 sincere+0.246
fly+0.245
 widen+0.244
Neg logit contributions
 days-0.206
 weeks-0.172
ops-0.152
 months-0.147
 times-0.146
Token each
Token ID1123
Feature activation-3.64e+00

Pos logit contributions
itating+0.034
 widen+0.033
fly+0.032
 sincere+0.032
 rapidly+0.032
Neg logit contributions
 days-0.035
 weeks-0.029
 times-0.028
 things-0.025
 months-0.025
Token other
Token ID584
Feature activation+4.23e-01

Pos logit contributions
 sincere+0.189
 rapidly+0.188
 faint+0.188
 source+0.187
 widen+0.187
Neg logit contributions
 days-0.152
 weeks-0.129
ops-0.120
 months-0.110
 times-0.106
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
 days+0.026
 weeks+0.024
ops+0.022
 nights+0.022
 months+0.021
Neg logit contributions
 widen-0.014
 sincere-0.013
 source-0.012
 gasp-0.012
 rapidly-0.012
Token They
Token ID1119
Feature activation-4.29e-02

Pos logit contributions
itating+0.007
 rapidly+0.007
Sad+0.007
fly+0.007
 sincere+0.007
Neg logit contributions
 days-0.007
 weeks-0.006
 months-0.005
ops-0.005
 times-0.005
Token shrugged
Token ID28271
Feature activation-8.24e+00

Pos logit contributions
itating+0.002
fly+0.002
Sad+0.002
 widen+0.002
amus+0.002
Neg logit contributions
 days-0.002
 weeks-0.001
 later-0.001
ops-0.001
 months-0.001
Token and
Token ID290
Feature activation+1.59e+00

Pos logit contributions
 sincere+0.413
 rapidly+0.408
 faint+0.406
 widen+0.406
Sad+0.403
Neg logit contributions
 days-0.368
 weeks-0.313
ops-0.283
 times-0.269
 months-0.268
Token decided
Token ID3066
Feature activation+5.44e+00

Pos logit contributions
 days+0.077
 weeks+0.066
 times+0.057
 months+0.057
ops+0.056
Neg logit contributions
itating-0.076
fly-0.074
Sad-0.074
 rapidly-0.073
 sincere-0.073
Token to
Token ID284
Feature activation-2.15e+00

Pos logit contributions
 days+0.350
ops+0.319
 weeks+0.319
 months+0.293
 times+0.290
Neg logit contributions
 sincere-0.170
 faint-0.163
 rapidly-0.157
 source-0.149
 widen-0.148
Token go
Token ID467
Feature activation+4.85e+00

Pos logit contributions
itating+0.109
 rapidly+0.107
Sad+0.106
 perplex+0.104
fly+0.104
Neg logit contributions
 days-0.091
 weeks-0.077
 times-0.071
 later-0.071
 day-0.068
Token see
Token ID766
Feature activation-3.46e+00

Pos logit contributions
 days+0.306
 weeks+0.279
ops+0.273
 times+0.255
 months+0.252
Neg logit contributions
 source-0.152
 sincere-0.145
 faint-0.145
 rapidly-0.144
itating-0.142