TOP ACTIVATIONS
MAX = 0.588

Ev angel ical adults , like believers
hope that a com er cial version of the Rift would
hope that a com er cial version of the Rift would
next strongest candidates - Z alm ai R ass ul and
." Lu ol Deng was traded to the Cavs
's published scouting report on Deng , who was the redacted
types of block syntax . Towards the end of that post
at ribe on Lu ol Deng as belonging to someone else
was given an ult im atum and a day to think
re - stud ying the Deng intelligence report a player
tactical advantage over the ch asm below . War th ogs
to describe the shortcomings of Deng in a way that never
4 ms G 2 G Sharp M VA + 120 Hz
Similarly , compare the ch asm in rational analysis separating the
doubt be having a sp asm or two trying to make
was tweeted by Diana Al ze er .
citizens the right to gra ze sheep on any golf course
executive director David Re it ze says that this practice will
the death of the Dru ze police officer .
Jewish , Arab and Dru ze who came together for

MIN ACTIVATIONS
MIN = -0.628

( AP ) Story continues There were
continues below advertisement Story continues below advertisement
of dollars . Story continues below advertisement
She pell . Story continues below advertisement
PC s Back Story : ( Example : Th
' keeper . Story continues below advertisement
the club . Story continues below advertisement
continues below advertisement Story continues below advertisement
to vote accordingly . <|endoftext|> Story highlights Police chief vows wanted
big stage . Story continues below advertisement
disclosure statement . Story continues below advertisement
- t weet / <|endoftext|> Story highlights Secretary of Defense Chuck
On stad . Story continues below advertisement
season one ! Story Editor and Producer ,
Coach [ Doug ] Mar rone has instructed him to do
about its drug defer ip rone , which is used to
, specifically concerning " mis represent ations " made to the
thoroughly . Add more jun iper infusion if necessary . Leave
It would be dis pir iting if the book came
dip these in boiling jun iper infusion first .) Transfer the

INTERVAL 0.284 - 0.588
CONTAINS 0.561%

chief forest official of the Sund arb ans in Bangladesh ,
poor health or suffering from burn out retire early while those
up more or less mirror ing the Rab id Pupp ies
may not be that young evangelicals are abandoning their faith ,
and we went to his home . We went to a

INTERVAL -0.020 - 0.284
CONTAINS 71.374%

oil company Petro br as . The arms dealer
1982 V itus road bike . Gl enn ,
beings possess reason in equal measure , Hume 's endorsement of
we had reached the final part of the process . She
if I 'm making news here ," National Review 's Jonah

INTERVAL -0.324 - -0.020
CONTAINS 27.852%

run the sl s deploy command , the following things happen
from processes in the planet 's mantle beneath the crust ,
future husbands . Then we were blind fold ed .
he thinks interest will rapidly grow in the mainstream world .
utions does not reflect a belief that he never

INTERVAL -0.628 - -0.324
CONTAINS 0.213%

- 150 Eco Boost Tort ure Test truck in the 2010
rankings . R ANK 1 Josh Norman , Redskins
Advertisement Continue reading the main story In the capital
, he is an instinct ive leader and a perfectly efficient
Chin ook and Cit ra hops in the kettle and dry
Token
Token ID447
Feature activation-1.28e-03

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.002
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token
Token ID251
Feature activation-4.81e-03

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token
Token ID198
Feature activation+6.99e-03

Pos logit contributions
Story+0.004
ylan+0.004
 Brist+0.004
kok+0.003
 Kyr+0.003
Neg logit contributions
Pope-0.004
angel-0.004
 Towards-0.003
 Deng-0.003
 Chu-0.003
Token
Token ID198
Feature activation+1.02e-03

Pos logit contributions
Pope+0.006
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.005
 Kyr-0.005
TokenEv
Token ID15200
Feature activation+2.40e-01

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Tokenangel
Token ID8368
Feature activation+5.88e-01

Pos logit contributions
Pope+0.160
angel+0.145
 Towards+0.119
 Deng+0.117
 Chu+0.114
Neg logit contributions
Story-0.212
ylan-0.210
 Brist-0.207
kok-0.201
 Kyr-0.193
Tokenical
Token ID605
Feature activation-3.79e-02

Pos logit contributions
Pope+0.469
angel+0.434
 Towards+0.368
 Deng+0.364
 Chu+0.357
Neg logit contributions
Story-0.443
ylan-0.439
 Brist-0.432
kok-0.416
 Kyr-0.399
Token adults
Token ID6490
Feature activation+1.15e-01

Pos logit contributions
Story+0.030
ylan+0.030
 Brist+0.029
kok+0.028
 Kyr+0.027
Neg logit contributions
Pope-0.029
angel-0.026
 Towards-0.022
 Deng-0.022
atum-0.022
Token,
Token ID11
Feature activation+1.58e-03

Pos logit contributions
Pope+0.093
angel+0.086
 Towards+0.073
 Deng+0.072
 Chu+0.071
Neg logit contributions
Story-0.085
ylan-0.084
 Brist-0.083
kok-0.080
 Kyr-0.077
Token like
Token ID588
Feature activation+6.61e-02

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token believers
Token ID23142
Feature activation+3.39e-01

Pos logit contributions
Pope+0.053
angel+0.049
 Towards+0.042
 Deng+0.041
atum+0.041
Neg logit contributions
Story-0.049
ylan-0.049
 Brist-0.048
kok-0.046
 Kyr-0.044
Token hope
Token ID2911
Feature activation-1.13e-01

Pos logit contributions
Pope+0.009
angel+0.009
 Towards+0.007
 Deng+0.007
 Chu+0.007
Neg logit contributions
Story-0.008
ylan-0.008
 Brist-0.008
kok-0.008
 Kyr-0.007
Token that
Token ID326
Feature activation-1.65e-02

Pos logit contributions
Story+0.085
ylan+0.084
 Brist+0.083
kok+0.080
 Kyr+0.076
Neg logit contributions
Pope-0.090
angel-0.084
 Towards-0.071
 Deng-0.070
 Chu-0.069
Token a
Token ID257
Feature activation+6.69e-03

Pos logit contributions
Story+0.013
ylan+0.012
 Brist+0.012
kok+0.012
 Kyr+0.011
Neg logit contributions
Pope-0.013
angel-0.012
 Towards-0.010
 Deng-0.010
 Chu-0.010
Token com
Token ID401
Feature activation+1.40e-01

Pos logit contributions
Pope+0.006
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.005
 Kyr-0.004
Tokener
Token ID263
Feature activation-2.02e-01

Pos logit contributions
Pope+0.120
angel+0.111
 Towards+0.096
 Deng+0.095
 Chu+0.093
Neg logit contributions
Story-0.098
ylan-0.097
 Brist-0.095
kok-0.091
 Kyr-0.087
Tokencial
Token ID2413
Feature activation+5.12e-01

Pos logit contributions
Story+0.157
ylan+0.156
 Brist+0.154
kok+0.148
 Kyr+0.142
Neg logit contributions
Pope-0.156
angel-0.144
 Towards-0.122
 Deng-0.120
 Chu-0.118
Token version
Token ID2196
Feature activation-1.69e-01

Pos logit contributions
Pope+0.420
angel+0.390
 Towards+0.333
 Deng+0.329
 Chu+0.322
Neg logit contributions
Story-0.373
ylan-0.369
 Brist-0.363
kok-0.349
 Kyr-0.334
Token of
Token ID286
Feature activation+3.09e-03

Pos logit contributions
Story+0.126
ylan+0.125
 Brist+0.123
kok+0.118
 Kyr+0.113
Neg logit contributions
Pope-0.136
angel-0.126
 Towards-0.107
 Deng-0.106
 Chu-0.104
Token the
Token ID262
Feature activation+3.53e-03

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.002
Token Rift
Token ID21222
Feature activation+1.74e-01

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.002
 Kyr-0.002
Token would
Token ID561
Feature activation-1.65e-02

Pos logit contributions
Pope+0.142
angel+0.131
 Towards+0.112
 Deng+0.110
 Chu+0.108
Neg logit contributions
Story-0.128
ylan-0.126
 Brist-0.124
kok-0.119
 Kyr-0.114
Token hope
Token ID2911
Feature activation-1.24e-01

Pos logit contributions
Pope+0.010
angel+0.010
 Towards+0.008
 Deng+0.008
 Chu+0.008
Neg logit contributions
Story-0.006
ylan-0.006
 Brist-0.006
kok-0.006
 Kyr-0.005
Token that
Token ID326
Feature activation-2.02e-02

Pos logit contributions
Story+0.088
ylan+0.087
 Brist+0.086
kok+0.083
 Kyr+0.079
Neg logit contributions
Pope-0.104
angel-0.096
 Towards-0.083
 Deng-0.082
 Chu-0.080
Token a
Token ID257
Feature activation+2.20e-03

Pos logit contributions
Story+0.015
ylan+0.015
 Brist+0.015
kok+0.014
 Kyr+0.014
Neg logit contributions
Pope-0.016
angel-0.015
 Towards-0.013
 Deng-0.013
 Chu-0.012
Token com
Token ID401
Feature activation+1.36e-01

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.002
Tokener
Token ID263
Feature activation-2.05e-01

Pos logit contributions
Pope+0.143
angel+0.135
 Towards+0.120
 Deng+0.119
 Chu+0.117
Neg logit contributions
Story-0.068
ylan-0.067
 Brist-0.065
kok-0.062
 Kyr-0.058
Tokencial
Token ID2413
Feature activation+5.02e-01

Pos logit contributions
Story+0.277
ylan+0.275
 Brist+0.273
kok+0.267
 Kyr+0.261
Neg logit contributions
Pope-0.041
angel-0.029
 Towards-0.006
 Deng-0.004
 Chu-0.002
Token version
Token ID2196
Feature activation-1.78e-01

Pos logit contributions
Pope+0.501
angel+0.471
 Towards+0.415
 Deng+0.411
 Chu+0.405
Neg logit contributions
Story-0.278
ylan-0.275
 Brist-0.269
kok-0.255
 Kyr-0.240
Token of
Token ID286
Feature activation+8.44e-04

Pos logit contributions
Story+0.134
ylan+0.132
 Brist+0.130
kok+0.125
 Kyr+0.120
Neg logit contributions
Pope-0.142
angel-0.132
 Towards-0.112
 Deng-0.110
atum-0.108
Token the
Token ID262
Feature activation-5.48e-03

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token Rift
Token ID21222
Feature activation+1.65e-01

Pos logit contributions
Story+0.005
ylan+0.005
 Brist+0.005
kok+0.005
 Kyr+0.005
Neg logit contributions
Pope-0.003
angel-0.003
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token would
Token ID561
Feature activation-2.31e-02

Pos logit contributions
Pope+0.139
angel+0.130
 Towards+0.111
 Deng+0.110
 Chu+0.108
Neg logit contributions
Story-0.116
ylan-0.115
 Brist-0.113
kok-0.108
 Kyr-0.103
Token next
Token ID1306
Feature activation-2.58e-02

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token strongest
Token ID12841
Feature activation+1.54e-01

Pos logit contributions
Story+0.019
ylan+0.019
 Brist+0.019
kok+0.018
 Kyr+0.017
Neg logit contributions
Pope-0.021
angel-0.019
 Towards-0.016
 Deng-0.016
 Chu-0.016
Token candidates
Token ID5871
Feature activation-1.02e-01

Pos logit contributions
Pope+0.130
angel+0.121
 Towards+0.104
 Deng+0.103
 Chu+0.101
Neg logit contributions
Story-0.109
ylan-0.108
 Brist-0.106
kok-0.102
 Kyr-0.097
Token -
Token ID532
Feature activation-2.62e-02

Pos logit contributions
Story+0.077
ylan+0.076
 Brist+0.075
kok+0.072
 Kyr+0.069
Neg logit contributions
Pope-0.082
angel-0.076
 Towards-0.064
 Deng-0.064
 Chu-0.062
Token Z
Token ID1168
Feature activation+8.72e-02

Pos logit contributions
Story+0.019
ylan+0.019
 Brist+0.019
kok+0.018
 Kyr+0.017
Neg logit contributions
Pope-0.021
angel-0.020
 Towards-0.017
 Deng-0.016
atum-0.016
Tokenalm
Token ID38182
Feature activation+5.02e-01

Pos logit contributions
Pope+0.071
angel+0.066
 Towards+0.056
 Deng+0.056
 Chu+0.055
Neg logit contributions
Story-0.064
ylan-0.063
 Brist-0.062
kok-0.060
 Kyr-0.057
Tokenai
Token ID1872
Feature activation-6.06e-02

Pos logit contributions
Pope+0.406
angel+0.379
 Towards+0.322
 Deng+0.320
 Chu+0.314
Neg logit contributions
Story-0.371
ylan-0.366
 Brist-0.361
kok-0.347
 saddle-0.332
Token R
Token ID371
Feature activation-4.67e-02

Pos logit contributions
Story+0.044
ylan+0.044
 Brist+0.043
kok+0.041
 Kyr+0.039
Neg logit contributions
Pope-0.050
angel-0.046
 Towards-0.040
 Deng-0.039
 Chu-0.038
Tokenass
Token ID562
Feature activation+4.56e-02

Pos logit contributions
Story+0.037
ylan+0.037
 Brist+0.036
kok+0.035
 Kyr+0.033
Neg logit contributions
Pope-0.035
angel-0.033
 Towards-0.028
 Deng-0.027
 Chu-0.027
Tokenul
Token ID377
Feature activation-5.83e-02

Pos logit contributions
Pope+0.036
angel+0.033
 Towards+0.028
 Deng+0.028
 Chu+0.027
Neg logit contributions
Story-0.035
ylan-0.034
 Brist-0.034
kok-0.033
 Kyr-0.031
Token and
Token ID290
Feature activation+1.04e-02

Pos logit contributions
Story+0.043
ylan+0.043
 Brist+0.042
kok+0.040
 Kyr+0.038
Neg logit contributions
Pope-0.047
angel-0.044
 Towards-0.038
 Deng-0.037
 Chu-0.036
Token."
Token ID526
Feature activation+2.54e-02

Pos logit contributions
Pope+0.007
angel+0.007
 Towards+0.006
 Deng+0.006
 Chu+0.005
Neg logit contributions
Story-0.007
ylan-0.007
 Brist-0.007
kok-0.006
 Kyr-0.006
Token
Token ID198
Feature activation+1.31e-03

Pos logit contributions
Pope+0.020
angel+0.019
 Towards+0.016
 Deng+0.016
 Chu+0.015
Neg logit contributions
Story-0.019
ylan-0.019
 Brist-0.019
kok-0.018
 Kyr-0.017
Token
Token ID198
Feature activation+5.83e-03

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
TokenLu
Token ID25596
Feature activation+2.22e-01

Pos logit contributions
Pope+0.005
angel+0.004
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
Tokenol
Token ID349
Feature activation-3.90e-01

Pos logit contributions
Pope+0.289
angel+0.275
 Towards+0.251
 Deng+0.249
 Chu+0.246
Neg logit contributions
Story-0.056
ylan-0.055
 Brist-0.051
kok-0.046
 Kyr-0.039
Token Deng
Token ID41985
Feature activation+4.96e-01

Pos logit contributions
Story+0.525
ylan+0.522
 Brist+0.519
kok+0.507
 Kyr+0.496
Neg logit contributions
Pope-0.079
angel-0.055
 Towards-0.012
 Chu-0.002
atum-0.002
Token was
Token ID373
Feature activation+1.05e-02

Pos logit contributions
Pope+0.407
angel+0.378
 Towards+0.322
 Deng+0.317
 Chu+0.312
Neg logit contributions
Story-0.363
ylan-0.359
 Brist-0.353
kok-0.339
 Kyr-0.325
Token traded
Token ID14018
Feature activation+1.60e-02

Pos logit contributions
Pope+0.008
angel+0.008
 Towards+0.007
 Deng+0.006
 Chu+0.006
Neg logit contributions
Story-0.008
ylan-0.008
 Brist-0.008
kok-0.007
 Kyr-0.007
Token to
Token ID284
Feature activation-9.62e-04

Pos logit contributions
Pope+0.013
angel+0.012
 Towards+0.010
 Deng+0.010
 Chu+0.010
Neg logit contributions
Story-0.012
ylan-0.012
 Brist-0.012
kok-0.011
 Kyr-0.011
Token the
Token ID262
Feature activation-3.17e-03

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token Cavs
Token ID38943
Feature activation+1.85e-01

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.003
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token's
Token ID338
Feature activation-3.53e-02

Pos logit contributions
Story+0.112
ylan+0.111
 Brist+0.109
kok+0.105
 Kyr+0.101
Neg logit contributions
Pope-0.122
angel-0.113
 Towards-0.096
 Deng-0.095
 Chu-0.093
Token published
Token ID3199
Feature activation+2.25e-01

Pos logit contributions
Story+0.025
ylan+0.025
 Brist+0.025
kok+0.024
 Kyr+0.023
Neg logit contributions
Pope-0.029
angel-0.027
 Towards-0.023
 Deng-0.023
 Chu-0.022
Token scouting
Token ID27088
Feature activation+6.92e-02

Pos logit contributions
Pope+0.191
angel+0.178
 Towards+0.152
 Deng+0.151
 Chu+0.148
Neg logit contributions
Story-0.158
ylan-0.156
 Brist-0.154
kok-0.148
 Kyr-0.141
Token report
Token ID989
Feature activation+2.69e-01

Pos logit contributions
Pope+0.037
angel+0.032
 Towards+0.025
 Deng+0.024
 Chu+0.023
Neg logit contributions
Story-0.071
ylan-0.070
 Brist-0.069
kok-0.067
 saddle-0.066
Token on
Token ID319
Feature activation-2.12e-02

Pos logit contributions
Pope+0.217
angel+0.201
 Towards+0.170
 Deng+0.168
 Chu+0.165
Neg logit contributions
Story-0.200
ylan-0.198
 Brist-0.195
kok-0.187
 Kyr-0.180
Token Deng
Token ID41985
Feature activation+4.93e-01

Pos logit contributions
Story+0.021
ylan+0.021
 Brist+0.020
kok+0.020
 Kyr+0.019
Neg logit contributions
Pope-0.012
angel-0.011
 Towards-0.008
atum-0.008
 Deng-0.008
Token,
Token ID11
Feature activation+5.60e-03

Pos logit contributions
Pope+0.404
angel+0.374
 Towards+0.320
 Deng+0.314
 Chu+0.309
Neg logit contributions
Story-0.361
ylan-0.357
 Brist-0.352
kok-0.338
 Kyr-0.324
Token who
Token ID508
Feature activation+2.75e-03

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.004
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
Token was
Token ID373
Feature activation+2.10e-02

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.002
 Deng+0.002
atum+0.002
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.002
Token the
Token ID262
Feature activation+2.12e-03

Pos logit contributions
Pope+0.017
angel+0.016
 Towards+0.013
 Deng+0.013
 Chu+0.013
Neg logit contributions
Story-0.015
ylan-0.015
 Brist-0.015
kok-0.015
 Kyr-0.014
Token redacted
Token ID44740
Feature activation-7.15e-02

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.001
 Deng+0.001
atum+0.001
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.001
Token types
Token ID3858
Feature activation+8.00e-02

Pos logit contributions
Story+0.105
ylan+0.104
 Brist+0.103
kok+0.099
 Kyr+0.096
Neg logit contributions
Pope-0.089
angel-0.082
 Towards-0.067
 Deng-0.067
 Chu-0.065
Token of
Token ID286
Feature activation+9.86e-04

Pos logit contributions
Pope+0.063
angel+0.058
 Towards+0.049
 Deng+0.048
 Chu+0.047
Neg logit contributions
Story-0.061
ylan-0.061
 Brist-0.060
kok-0.058
 Kyr-0.055
Token block
Token ID2512
Feature activation+1.29e-01

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token syntax
Token ID15582
Feature activation-1.76e-02

Pos logit contributions
Pope+0.103
angel+0.096
 Towards+0.081
 Deng+0.080
 Chu+0.079
Neg logit contributions
Story-0.097
ylan-0.096
 Brist-0.095
kok-0.091
 Kyr-0.087
Token.
Token ID13
Feature activation-6.88e-03

Pos logit contributions
Story+0.013
ylan+0.013
 Brist+0.013
kok+0.012
 Kyr+0.012
Neg logit contributions
Pope-0.014
angel-0.013
 Towards-0.011
 Deng-0.011
 Chu-0.011
Token Towards
Token ID49953
Feature activation+4.92e-01

Pos logit contributions
Story+0.005
ylan+0.005
 Brist+0.005
kok+0.005
 Kyr+0.005
Neg logit contributions
Pope-0.005
angel-0.005
 Towards-0.004
 Deng-0.004
atum-0.004
Token the
Token ID262
Feature activation+1.56e-03

Pos logit contributions
Pope+0.397
angel+0.367
 Towards+0.311
 Deng+0.309
 Chu+0.302
Neg logit contributions
Story-0.367
ylan-0.363
 Brist-0.357
kok-0.344
 Kyr-0.330
Token end
Token ID886
Feature activation-2.35e-02

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
atum+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token of
Token ID286
Feature activation+3.52e-03

Pos logit contributions
Story+0.018
ylan+0.018
 Brist+0.017
kok+0.017
 Kyr+0.016
Neg logit contributions
Pope-0.018
angel-0.017
 Towards-0.014
 Deng-0.014
 Chu-0.014
Token that
Token ID326
Feature activation-1.80e-02

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.002
Token post
Token ID1281
Feature activation+2.26e-01

Pos logit contributions
Story+0.018
ylan+0.018
 Brist+0.018
kok+0.017
 Kyr+0.017
Neg logit contributions
Pope-0.010
angel-0.009
 Towards-0.007
 Deng-0.006
 Chu-0.006
Tokenat
Token ID265
Feature activation+2.77e-02

Pos logit contributions
Pope+0.086
angel+0.080
 Towards+0.068
 Deng+0.068
 Chu+0.066
Neg logit contributions
Story-0.076
ylan-0.075
 Brist-0.073
kok-0.071
 Kyr-0.068
Tokenribe
Token ID4892
Feature activation-2.35e-02

Pos logit contributions
Pope+0.024
angel+0.023
 Towards+0.020
 Deng+0.019
 Chu+0.019
Neg logit contributions
Story-0.018
ylan-0.018
 Brist-0.018
kok-0.017
 Kyr-0.016
Token on
Token ID319
Feature activation-1.97e-02

Pos logit contributions
Story+0.017
ylan+0.017
 Brist+0.017
kok+0.016
 Kyr+0.016
Neg logit contributions
Pope-0.019
angel-0.018
 Towards-0.015
 Deng-0.015
atum-0.014
Token Lu
Token ID6026
Feature activation+8.09e-02

Pos logit contributions
Story+0.015
ylan+0.015
 Brist+0.015
kok+0.014
 Kyr+0.014
Neg logit contributions
Pope-0.015
angel-0.014
 Towards-0.012
 Deng-0.012
atum-0.012
Tokenol
Token ID349
Feature activation-3.83e-01

Pos logit contributions
Pope+0.064
angel+0.059
 Towards+0.050
 Deng+0.050
 Chu+0.049
Neg logit contributions
Story-0.061
ylan-0.061
 Brist-0.060
kok-0.058
 Kyr-0.055
Token Deng
Token ID41985
Feature activation+4.92e-01

Pos logit contributions
Story+0.477
ylan+0.475
 Brist+0.471
kok+0.461
 Kyr+0.448
Neg logit contributions
Pope-0.116
angel-0.089
 Towards-0.049
atum-0.041
cial-0.040
Token as
Token ID355
Feature activation+8.70e-03

Pos logit contributions
Pope+0.402
angel+0.373
 Towards+0.318
 Deng+0.312
 Chu+0.308
Neg logit contributions
Story-0.361
ylan-0.358
 Brist-0.352
kok-0.338
 Kyr-0.324
Token belonging
Token ID16686
Feature activation+4.92e-02

Pos logit contributions
Pope+0.007
angel+0.006
 Towards+0.005
 Deng+0.005
atum+0.005
Neg logit contributions
Story-0.007
ylan-0.007
 Brist-0.007
kok-0.006
 Kyr-0.006
Token to
Token ID284
Feature activation-2.07e-03

Pos logit contributions
Pope+0.039
angel+0.037
 Towards+0.031
 Deng+0.031
 Chu+0.030
Neg logit contributions
Story-0.037
ylan-0.036
 Brist-0.036
kok-0.035
 Kyr-0.033
Token someone
Token ID2130
Feature activation+2.45e-02

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.002
angel-0.001
 Towards-0.001
 Deng-0.001
atum-0.001
Token else
Token ID2073
Feature activation+8.36e-02

Pos logit contributions
Pope+0.019
angel+0.018
 Towards+0.015
 Deng+0.015
atum+0.015
Neg logit contributions
Story-0.019
ylan-0.019
 Brist-0.018
kok-0.018
 Kyr-0.017
Token was
Token ID373
Feature activation+1.99e-02

Pos logit contributions
Story+0.018
ylan+0.018
 Brist+0.018
kok+0.017
 Kyr+0.016
Neg logit contributions
Pope-0.020
angel-0.018
 Towards-0.016
 Deng-0.015
 Chu-0.015
Token given
Token ID1813
Feature activation-2.27e-01

Pos logit contributions
Pope+0.017
angel+0.016
 Towards+0.013
 Deng+0.013
 Chu+0.013
Neg logit contributions
Story-0.014
ylan-0.014
 Brist-0.014
kok-0.013
 Kyr-0.013
Token an
Token ID281
Feature activation+6.66e-03

Pos logit contributions
Story+0.168
ylan+0.166
 Brist+0.164
kok+0.157
 Kyr+0.151
Neg logit contributions
Pope-0.184
angel-0.171
 Towards-0.146
 Deng-0.143
 Chu-0.141
Token ult
Token ID3789
Feature activation+3.28e-01

Pos logit contributions
Pope+0.005
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.005
 Kyr-0.004
Tokenim
Token ID320
Feature activation+1.61e-01

Pos logit contributions
Pope+0.212
angel+0.192
 Towards+0.155
 Deng+0.154
 Chu+0.150
Neg logit contributions
Story-0.297
ylan-0.293
 Brist-0.290
kok-0.284
 Kyr-0.272
Tokenatum
Token ID21307
Feature activation+4.91e-01

Pos logit contributions
Pope+0.039
angel+0.030
 Towards+0.012
 Deng+0.011
 Chu+0.009
Neg logit contributions
Story-0.210
ylan-0.210
 Brist-0.206
kok-0.203
 Kyr-0.198
Token and
Token ID290
Feature activation+1.52e-02

Pos logit contributions
Pope+0.391
angel+0.361
 Towards+0.307
 Deng+0.303
 Chu+0.297
Neg logit contributions
Story-0.371
ylan-0.367
 Brist-0.362
kok-0.349
 Kyr-0.334
Token a
Token ID257
Feature activation+4.59e-03

Pos logit contributions
Pope+0.012
angel+0.011
 Towards+0.010
 Deng+0.010
 Chu+0.010
Neg logit contributions
Story-0.011
ylan-0.011
 Brist-0.011
kok-0.010
 Kyr-0.010
Token day
Token ID1110
Feature activation-4.79e-02

Pos logit contributions
Pope+0.004
angel+0.003
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
Token to
Token ID284
Feature activation-1.47e-03

Pos logit contributions
Story+0.038
ylan+0.038
 Brist+0.037
kok+0.036
 Kyr+0.034
Neg logit contributions
Pope-0.036
angel-0.033
 Towards-0.028
 Deng-0.028
 Chu-0.027
Token think
Token ID892
Feature activation-1.31e-01

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token re
Token ID302
Feature activation+7.72e-04

Pos logit contributions
Pope+0.010
angel+0.009
 Towards+0.008
 Deng+0.008
 Chu+0.008
Neg logit contributions
Story-0.009
ylan-0.009
 Brist-0.009
kok-0.009
 Kyr-0.008
Token-
Token ID12
Feature activation-1.79e-02

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Tokenstud
Token ID19149
Feature activation-2.25e-01

Pos logit contributions
Story+0.013
ylan+0.013
 Brist+0.013
kok+0.013
 Kyr+0.012
Neg logit contributions
Pope-0.014
angel-0.013
 Towards-0.011
 Deng-0.011
 Chu-0.011
Tokenying
Token ID1112
Feature activation+1.47e-01

Pos logit contributions
Story+0.190
ylan+0.189
 Brist+0.186
kok+0.181
 Kyr+0.173
Neg logit contributions
Pope-0.158
angel-0.143
 Towards-0.119
 Deng-0.117
 Chu-0.114
Token the
Token ID262
Feature activation-2.26e-03

Pos logit contributions
Pope+0.119
angel+0.110
 Towards+0.093
 Deng+0.091
atum+0.090
Neg logit contributions
Story-0.109
ylan-0.108
 Brist-0.107
kok-0.102
 Kyr-0.098
Token Deng
Token ID41985
Feature activation+4.90e-01

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token intelligence
Token ID4430
Feature activation-1.03e-02

Pos logit contributions
Pope+0.405
angel+0.376
 Towards+0.322
 Deng+0.314
 Chu+0.311
Neg logit contributions
Story-0.356
ylan-0.351
 Brist-0.345
kok-0.332
 Kyr-0.317
Token report
Token ID989
Feature activation+2.61e-01

Pos logit contributions
Story+0.007
ylan+0.007
 Brist+0.007
kok+0.007
 Kyr+0.007
Neg logit contributions
Pope-0.009
angel-0.008
 Towards-0.007
 Deng-0.007
 Chu-0.007
Token
Token ID784
Feature activation+2.36e-02

Pos logit contributions
Pope+0.214
angel+0.198
 Towards+0.169
 Deng+0.168
 Chu+0.165
Neg logit contributions
Story-0.191
ylan-0.189
 Brist-0.186
kok-0.179
 Kyr-0.171
Token a
Token ID257
Feature activation+6.41e-03

Pos logit contributions
Pope+0.019
angel+0.018
 Towards+0.015
 Deng+0.015
 Chu+0.015
Neg logit contributions
Story-0.017
ylan-0.017
 Brist-0.017
kok-0.016
 Kyr-0.016
Token player
Token ID2137
Feature activation-9.56e-02

Pos logit contributions
Pope+0.005
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.005
 Kyr-0.004
Token tactical
Token ID16106
Feature activation-1.60e-02

Pos logit contributions
Pope+0.158
angel+0.147
 Towards+0.128
 Deng+0.127
 Chu+0.124
Neg logit contributions
Story-0.122
ylan-0.121
 Brist-0.118
kok-0.114
 Kyr-0.108
Token advantage
Token ID4621
Feature activation-1.53e-01

Pos logit contributions
Story+0.010
ylan+0.010
 Brist+0.010
kok+0.009
 Kyr+0.009
Neg logit contributions
Pope-0.015
angel-0.014
 Towards-0.012
 Deng-0.012
 Chu-0.011
Token over
Token ID625
Feature activation-8.78e-02

Pos logit contributions
Story+0.110
ylan+0.109
 Brist+0.107
kok+0.103
 Kyr+0.098
Neg logit contributions
Pope-0.128
angel-0.119
 Towards-0.102
 Deng-0.101
 Chu-0.099
Token the
Token ID262
Feature activation+5.68e-03

Pos logit contributions
Story+0.068
ylan+0.068
 Brist+0.067
kok+0.064
 Kyr+0.061
Neg logit contributions
Pope-0.068
angel-0.063
 Towards-0.053
 Deng-0.052
 Chu-0.051
Token ch
Token ID442
Feature activation+1.93e-02

Pos logit contributions
Pope+0.005
angel+0.004
 Towards+0.004
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
Tokenasm
Token ID8597
Feature activation+4.88e-01

Pos logit contributions
Pope+0.016
angel+0.014
 Towards+0.013
 Deng+0.012
 Chu+0.012
Neg logit contributions
Story-0.014
ylan-0.014
 Brist-0.014
kok-0.013
earch-0.013
Token below
Token ID2174
Feature activation+9.39e-02

Pos logit contributions
Pope+0.386
angel+0.357
 Towards+0.303
 Deng+0.299
 Chu+0.293
Neg logit contributions
Story-0.371
ylan-0.368
 Brist-0.361
kok-0.348
 Kyr-0.334
Token.
Token ID13
Feature activation+3.58e-03

Pos logit contributions
Pope+0.074
angel+0.068
 Towards+0.058
 Deng+0.058
 Chu+0.056
Neg logit contributions
Story-0.071
ylan-0.071
 Brist-0.070
kok-0.067
 Kyr-0.064
Token War
Token ID1810
Feature activation-1.40e-01

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 saddle-0.002
Tokenth
Token ID400
Feature activation-1.49e-01

Pos logit contributions
Story+0.104
ylan+0.103
 Brist+0.101
kok+0.097
 saddle+0.093
Neg logit contributions
Pope-0.113
angel-0.104
 Towards-0.089
 Deng-0.087
 Chu-0.086
Tokenogs
Token ID18463
Feature activation+2.56e-01

Pos logit contributions
Story+0.118
ylan+0.118
 Brist+0.116
kok+0.112
 Kyr+0.107
Neg logit contributions
Pope-0.112
angel-0.103
 Towards-0.086
 Deng-0.085
 Chu-0.083
Token to
Token ID284
Feature activation-9.49e-03

Pos logit contributions
Pope+0.096
angel+0.089
 Towards+0.076
 Deng+0.075
 Chu+0.074
Neg logit contributions
Story-0.088
ylan-0.087
 Brist-0.086
kok-0.083
 Kyr-0.079
Token describe
Token ID6901
Feature activation+2.40e-01

Pos logit contributions
Story+0.007
ylan+0.007
 Brist+0.007
kok+0.006
 saddle+0.006
Neg logit contributions
Pope-0.008
angel-0.007
 Towards-0.006
 Deng-0.006
 Chu-0.006
Token the
Token ID262
Feature activation-4.91e-03

Pos logit contributions
Pope+0.174
angel+0.160
 Towards+0.133
 Deng+0.130
 Chu+0.128
Neg logit contributions
Story-0.197
ylan-0.196
 Brist-0.193
kok-0.186
 Kyr-0.179
Token shortcomings
Token ID31731
Feature activation+5.15e-02

Pos logit contributions
Story+0.004
ylan+0.004
 Brist+0.004
kok+0.004
 Kyr+0.003
Neg logit contributions
Pope-0.004
angel-0.004
 Towards-0.003
 Deng-0.003
atum-0.003
Token of
Token ID286
Feature activation-2.07e-03

Pos logit contributions
Pope+0.041
angel+0.038
 Towards+0.032
 Deng+0.032
atum+0.031
Neg logit contributions
Story-0.039
ylan-0.038
 Brist-0.038
kok-0.036
 Kyr-0.035
Token Deng
Token ID41985
Feature activation+4.87e-01

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.001
 Towards-0.001
 Deng-0.001
atum-0.001
Token in
Token ID287
Feature activation-1.14e-02

Pos logit contributions
Pope+0.399
angel+0.370
 Towards+0.315
 Deng+0.310
 Chu+0.305
Neg logit contributions
Story-0.357
ylan-0.354
 Brist-0.348
kok-0.334
 Kyr-0.320
Token a
Token ID257
Feature activation-9.94e-04

Pos logit contributions
Story+0.008
ylan+0.008
 Brist+0.008
kok+0.008
 Kyr+0.008
Neg logit contributions
Pope-0.009
angel-0.009
 Towards-0.007
 Deng-0.007
atum-0.007
Token way
Token ID835
Feature activation+1.19e-01

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
atum-0.001
Token that
Token ID326
Feature activation-2.04e-02

Pos logit contributions
Pope+0.099
angel+0.092
 Towards+0.079
 Deng+0.077
atum+0.076
Neg logit contributions
Story-0.086
ylan-0.085
 Brist-0.084
kok-0.080
 Kyr-0.077
Token never
Token ID1239
Feature activation-3.46e-02

Pos logit contributions
Story+0.015
ylan+0.015
 Brist+0.014
kok+0.014
 Kyr+0.013
Neg logit contributions
Pope-0.017
angel-0.016
 Towards-0.013
 Deng-0.013
 Chu-0.013
Token 4
Token ID604
Feature activation+6.29e-02

Pos logit contributions
Pope+0.001
angel+0.000
 Towards+0.000
 Deng+0.000
atum+0.000
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.000
 Kyr-0.000
Tokenms
Token ID907
Feature activation-2.02e-01

Pos logit contributions
Pope+0.064
angel+0.061
 Towards+0.054
 Deng+0.053
 Chu+0.052
Neg logit contributions
Story-0.033
ylan-0.033
 Brist-0.032
kok-0.030
 Kyr-0.028
Token G
Token ID402
Feature activation+8.17e-02

Pos logit contributions
Story+0.177
ylan+0.175
 Brist+0.173
kok+0.167
 Kyr+0.162
Neg logit contributions
Pope-0.137
angel-0.125
 Towards-0.102
 Deng-0.100
atum-0.098
Token2
Token ID17
Feature activation+8.08e-02

Pos logit contributions
Pope+0.057
angel+0.052
 Towards+0.043
 Deng+0.042
 Chu+0.041
Neg logit contributions
Story-0.070
ylan-0.069
 Brist-0.068
kok-0.066
 Kyr-0.064
TokenG
Token ID38
Feature activation+1.06e-01

Pos logit contributions
Pope+0.055
angel+0.050
 Towards+0.041
 Deng+0.041
 Chu+0.040
Neg logit contributions
Story-0.071
ylan-0.069
 Brist-0.069
kok-0.066
 Kyr-0.064
Token Sharp
Token ID22835
Feature activation+4.85e-01

Pos logit contributions
Pope+0.066
angel+0.060
 Towards+0.048
 Deng+0.047
 Chu+0.046
Neg logit contributions
Story-0.098
ylan-0.097
 Brist-0.096
kok-0.093
 Kyr-0.090
Token M
Token ID337
Feature activation+1.88e-02

Pos logit contributions
Pope+0.374
angel+0.346
 Towards+0.292
 Deng+0.288
atum+0.282
Neg logit contributions
Story-0.378
ylan-0.372
 Brist-0.368
kok-0.353
 Kyr-0.339
TokenVA
Token ID11731
Feature activation+2.00e-01

Pos logit contributions
Pope+0.015
angel+0.014
 Towards+0.012
 Deng+0.012
 Chu+0.011
Neg logit contributions
Story-0.014
ylan-0.014
 Brist-0.014
kok-0.013
 Kyr-0.013
Token +
Token ID1343
Feature activation+4.23e-02

Pos logit contributions
Pope+0.164
angel+0.152
 Towards+0.130
 Deng+0.128
 Chu+0.126
Neg logit contributions
Story-0.147
ylan-0.145
 Brist-0.143
kok-0.137
 Kyr-0.131
Token 120
Token ID7982
Feature activation+1.53e-01

Pos logit contributions
Pope+0.033
angel+0.030
 Towards+0.025
 Deng+0.025
atum+0.025
Neg logit contributions
Story-0.033
ylan-0.033
 Brist-0.032
kok-0.031
 Kyr-0.030
TokenHz
Token ID7399
Feature activation+1.12e-02

Pos logit contributions
Pope+0.122
angel+0.113
 Towards+0.096
 Deng+0.095
 Chu+0.093
Neg logit contributions
Story-0.115
ylan-0.114
 Brist-0.113
kok-0.108
 Kyr-0.104
TokenSimilarly
Token ID28039
Feature activation-6.94e-02

Pos logit contributions
Pope+0.005
angel+0.004
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
Token,
Token ID11
Feature activation+4.24e-03

Pos logit contributions
Story+0.052
ylan+0.052
 Brist+0.051
kok+0.049
 Kyr+0.047
Neg logit contributions
Pope-0.055
angel-0.051
 Towards-0.044
 Deng-0.043
 Chu-0.042
Token compare
Token ID8996
Feature activation-5.80e-03

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
Token the
Token ID262
Feature activation+1.38e-03

Pos logit contributions
Story+0.004
ylan+0.004
 Brist+0.004
kok+0.004
 Kyr+0.004
Neg logit contributions
Pope-0.005
angel-0.004
 Towards-0.004
 Deng-0.003
 Chu-0.003
Token ch
Token ID442
Feature activation+2.01e-02

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Tokenasm
Token ID8597
Feature activation+4.85e-01

Pos logit contributions
Pope+0.015
angel+0.014
 Towards+0.012
 Deng+0.012
 Chu+0.011
Neg logit contributions
Story-0.016
ylan-0.016
 Brist-0.016
kok-0.015
 Kyr-0.014
Token in
Token ID287
Feature activation-2.24e-03

Pos logit contributions
Pope+0.371
angel+0.342
 Towards+0.288
 Deng+0.284
 Chu+0.278
Neg logit contributions
Story-0.380
ylan-0.377
 Brist-0.371
kok-0.358
 Kyr-0.344
Token rational
Token ID9377
Feature activation+4.64e-02

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.001
 Chu-0.001
Token analysis
Token ID3781
Feature activation-3.68e-02

Pos logit contributions
Pope+0.039
angel+0.037
 Towards+0.031
 Deng+0.031
 Chu+0.030
Neg logit contributions
Story-0.033
ylan-0.032
 Brist-0.032
kok-0.031
 Kyr-0.029
Token separating
Token ID27259
Feature activation+6.07e-02

Pos logit contributions
Story+0.028
ylan+0.028
 Brist+0.028
kok+0.027
 Kyr+0.026
Neg logit contributions
Pope-0.029
angel-0.026
 Towards-0.022
 Deng-0.022
 Chu-0.021
Token the
Token ID262
Feature activation+5.55e-03

Pos logit contributions
Pope+0.050
angel+0.046
 Towards+0.039
 Deng+0.039
atum+0.038
Neg logit contributions
Story-0.044
ylan-0.044
 Brist-0.043
kok-0.042
 Kyr-0.040
Token doubt
Token ID4719
Feature activation+1.06e-01

Pos logit contributions
Story+0.045
ylan+0.044
 Brist+0.044
kok+0.042
 Kyr+0.041
Neg logit contributions
Pope-0.036
angel-0.033
 Towards-0.027
 Deng-0.027
 Chu-0.026
Token be
Token ID307
Feature activation-3.90e-03

Pos logit contributions
Pope+0.087
angel+0.081
 Towards+0.069
 Deng+0.068
 Chu+0.067
Neg logit contributions
Story-0.077
ylan-0.076
 Brist-0.075
kok-0.072
 Kyr-0.069
Token having
Token ID1719
Feature activation+3.56e-02

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.003
 Kyr+0.003
Neg logit contributions
Pope-0.003
angel-0.003
 Towards-0.003
 Deng-0.003
 Chu-0.003
Token a
Token ID257
Feature activation+2.92e-03

Pos logit contributions
Pope+0.029
angel+0.026
 Towards+0.022
 Deng+0.022
atum+0.022
Neg logit contributions
Story-0.027
ylan-0.026
 Brist-0.026
kok-0.025
 Kyr-0.024
Token sp
Token ID599
Feature activation-3.72e-02

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.002
Tokenasm
Token ID8597
Feature activation+4.83e-01

Pos logit contributions
Story+0.031
ylan+0.030
 Brist+0.030
kok+0.029
earch+0.028
Neg logit contributions
Pope-0.027
angel-0.025
 Towards-0.021
 Deng-0.020
 Chu-0.020
Token or
Token ID393
Feature activation-6.69e-02

Pos logit contributions
Pope+0.385
angel+0.355
 Towards+0.302
 Deng+0.298
 Chu+0.292
Neg logit contributions
Story-0.364
ylan-0.360
 Brist-0.354
kok-0.342
 saddle-0.327
Token two
Token ID734
Feature activation-1.72e-02

Pos logit contributions
Story+0.048
ylan+0.048
 Brist+0.047
kok+0.045
 saddle+0.044
Neg logit contributions
Pope-0.055
angel-0.051
 Towards-0.044
 Deng-0.043
atum-0.042
Token trying
Token ID2111
Feature activation-3.45e-02

Pos logit contributions
Story+0.013
ylan+0.013
 Brist+0.013
kok+0.012
 Kyr+0.012
Neg logit contributions
Pope-0.014
angel-0.013
 Towards-0.011
 Deng-0.011
atum-0.010
Token to
Token ID284
Feature activation-1.89e-03

Pos logit contributions
Story+0.026
ylan+0.026
 Brist+0.025
kok+0.024
 Kyr+0.023
Neg logit contributions
Pope-0.028
angel-0.026
 Towards-0.022
 Deng-0.021
 Chu-0.021
Token make
Token ID787
Feature activation-6.30e-02

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.002
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token was
Token ID373
Feature activation+1.86e-02

Pos logit contributions
Story+0.065
ylan+0.065
 Brist+0.064
kok+0.061
 Kyr+0.058
Neg logit contributions
Pope-0.078
angel-0.072
 Towards-0.062
 Deng-0.061
 Chu-0.060
Token tweeted
Token ID10830
Feature activation+1.72e-01

Pos logit contributions
Pope+0.014
angel+0.013
 Towards+0.011
 Deng+0.010
 Chu+0.010
Neg logit contributions
Story-0.015
ylan-0.015
 Brist-0.015
kok-0.014
 Kyr-0.014
Token by
Token ID416
Feature activation-2.86e-03

Pos logit contributions
Pope+0.139
angel+0.129
 Towards+0.109
 Deng+0.108
 Chu+0.106
Neg logit contributions
Story-0.128
ylan-0.127
 Brist-0.125
kok-0.120
 Kyr-0.115
Token Diana
Token ID25752
Feature activation+6.47e-03

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token Al
Token ID978
Feature activation+8.40e-02

Pos logit contributions
Pope+0.005
angel+0.005
 Towards+0.004
 Deng+0.004
atum+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.005
 Kyr-0.004
Tokenze
Token ID2736
Feature activation+4.71e-01

Pos logit contributions
Pope+0.067
angel+0.062
 Towards+0.052
 Deng+0.052
 Chu+0.051
Neg logit contributions
Story-0.063
ylan-0.063
 Brist-0.062
kok-0.060
 Kyr-0.057
Tokener
Token ID263
Feature activation-2.06e-01

Pos logit contributions
Pope+0.379
angel+0.353
 Towards+0.299
 Deng+0.296
 Chu+0.291
Neg logit contributions
Story-0.351
ylan-0.344
 Brist-0.342
kok-0.327
 saddle-0.314
Token.
Token ID13
Feature activation-3.38e-03

Pos logit contributions
Story+0.165
ylan+0.164
 Brist+0.161
kok+0.156
 Kyr+0.150
Neg logit contributions
Pope-0.154
angel-0.142
 Towards-0.119
 Deng-0.117
 Chu-0.115
Token
Token ID198
Feature activation+6.55e-03

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.003
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token
Token ID198
Feature activation+1.05e-02

Pos logit contributions
Pope+0.005
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.005
 Kyr-0.004
Token
Token ID447
Feature activation+5.97e-04

Pos logit contributions
Pope+0.008
angel+0.008
 Towards+0.007
 Deng+0.007
 Chu+0.006
Neg logit contributions
Story-0.008
ylan-0.008
 Brist-0.008
kok-0.007
 Kyr-0.007
Token citizens
Token ID4290
Feature activation+7.44e-03

Pos logit contributions
Story+0.117
ylan+0.116
 Brist+0.114
kok+0.110
 Kyr+0.106
Neg logit contributions
Pope-0.117
angel-0.108
 Towards-0.091
 Deng-0.090
atum-0.088
Token the
Token ID262
Feature activation-8.97e-03

Pos logit contributions
Pope+0.006
angel+0.006
 Towards+0.005
 Deng+0.005
atum+0.005
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.005
 Kyr-0.005
Token right
Token ID826
Feature activation-8.40e-03

Pos logit contributions
Story+0.007
ylan+0.007
 Brist+0.007
kok+0.006
 Kyr+0.006
Neg logit contributions
Pope-0.007
angel-0.007
 Towards-0.006
 Deng-0.005
 Chu-0.005
Token to
Token ID284
Feature activation-1.31e-02

Pos logit contributions
Story+0.006
ylan+0.006
 Brist+0.006
kok+0.006
 Kyr+0.006
Neg logit contributions
Pope-0.007
angel-0.006
 Towards-0.005
 Deng-0.005
 Chu-0.005
Token gra
Token ID7933
Feature activation+1.19e-03

Pos logit contributions
Story+0.010
ylan+0.010
 Brist+0.010
kok+0.009
 saddle+0.009
Neg logit contributions
Pope-0.010
angel-0.010
 Towards-0.008
 Deng-0.008
 Chu-0.008
Tokenze
Token ID2736
Feature activation+4.70e-01

Pos logit contributions
Pope+0.000
angel+0.000
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.001
 saddle-0.001
Token sheep
Token ID15900
Feature activation-6.85e-02

Pos logit contributions
Pope+0.379
angel+0.350
 Towards+0.297
 Deng+0.294
 Chu+0.288
Neg logit contributions
Story-0.350
ylan-0.348
 Brist-0.343
kok-0.329
 Kyr-0.316
Token on
Token ID319
Feature activation-2.44e-02

Pos logit contributions
Story+0.051
ylan+0.051
 Brist+0.050
kok+0.048
 Kyr+0.046
Neg logit contributions
Pope-0.055
angel-0.051
 Towards-0.043
 Deng-0.043
 Chu-0.042
Token any
Token ID597
Feature activation-6.88e-02

Pos logit contributions
Story+0.018
ylan+0.018
 Brist+0.018
kok+0.017
 Kyr+0.016
Neg logit contributions
Pope-0.020
angel-0.018
 Towards-0.016
 Deng-0.015
 Chu-0.015
Token golf
Token ID13126
Feature activation-8.95e-02

Pos logit contributions
Story+0.053
ylan+0.052
 Brist+0.052
kok+0.050
 saddle+0.048
Neg logit contributions
Pope-0.054
angel-0.050
 Towards-0.042
 Deng-0.041
 Chu-0.040
Token course
Token ID1781
Feature activation-1.76e-01

Pos logit contributions
Story+0.046
ylan+0.046
 Brist+0.045
kok+0.042
 saddle+0.040
Neg logit contributions
Pope-0.093
angel-0.087
 Towards-0.077
 Deng-0.077
 Chu-0.075
Token executive
Token ID4640
Feature activation+1.21e-01

Pos logit contributions
Story+0.027
ylan+0.026
 Brist+0.026
kok+0.025
 Kyr+0.024
Neg logit contributions
Pope-0.028
angel-0.026
 Towards-0.021
 Deng-0.021
atum-0.021
Token director
Token ID3437
Feature activation-2.40e-02

Pos logit contributions
Pope+0.102
angel+0.095
 Towards+0.082
 Deng+0.080
atum+0.079
Neg logit contributions
Story-0.085
ylan-0.084
 Brist-0.083
kok-0.080
 Kyr-0.076
Token David
Token ID3271
Feature activation-4.31e-02

Pos logit contributions
Story+0.018
ylan+0.018
 Brist+0.017
kok+0.017
 Kyr+0.016
Neg logit contributions
Pope-0.019
angel-0.018
 Towards-0.015
 Deng-0.015
atum-0.015
Token Re
Token ID797
Feature activation-1.84e-02

Pos logit contributions
Story+0.033
ylan+0.033
 Brist+0.032
kok+0.031
 Kyr+0.030
Neg logit contributions
Pope-0.034
angel-0.031
 Towards-0.026
 Deng-0.026
atum-0.026
Tokenit
Token ID270
Feature activation+4.64e-02

Pos logit contributions
Story+0.014
ylan+0.014
 Brist+0.013
kok+0.013
 Kyr+0.012
Neg logit contributions
Pope-0.015
angel-0.014
 Towards-0.012
 Deng-0.012
 Chu-0.011
Tokenze
Token ID2736
Feature activation+4.69e-01

Pos logit contributions
Pope+0.040
angel+0.037
 Towards+0.032
 Deng+0.032
 Chu+0.031
Neg logit contributions
Story-0.032
ylan-0.032
 Brist-0.031
kok-0.030
earch-0.028
Token says
Token ID1139
Feature activation+4.45e-02

Pos logit contributions
Pope+0.374
angel+0.345
 Towards+0.294
 Deng+0.289
 Chu+0.283
Neg logit contributions
Story-0.352
ylan-0.350
 Brist-0.345
kok-0.333
 Kyr-0.318
Token that
Token ID326
Feature activation-2.56e-02

Pos logit contributions
Pope+0.036
angel+0.033
 Towards+0.029
 Deng+0.028
 Chu+0.028
Neg logit contributions
Story-0.033
ylan-0.033
 Brist-0.032
kok-0.031
 Kyr-0.030
Token this
Token ID428
Feature activation+1.01e-01

Pos logit contributions
Story+0.019
ylan+0.019
 Brist+0.019
kok+0.018
 Kyr+0.017
Neg logit contributions
Pope-0.021
angel-0.019
 Towards-0.016
 Deng-0.016
atum-0.016
Token practice
Token ID3357
Feature activation+7.04e-02

Pos logit contributions
Pope+0.081
angel+0.076
 Towards+0.064
 Deng+0.063
atum+0.062
Neg logit contributions
Story-0.075
ylan-0.075
 Brist-0.073
kok-0.071
 Kyr-0.068
Token will
Token ID481
Feature activation+7.04e-03

Pos logit contributions
Pope+0.058
angel+0.054
 Towards+0.046
 Deng+0.045
 Chu+0.044
Neg logit contributions
Story-0.051
ylan-0.051
 Brist-0.050
kok-0.048
 Kyr-0.046
Token the
Token ID262
Feature activation-1.74e-04

Pos logit contributions
Pope+0.009
angel+0.008
 Towards+0.007
 Deng+0.007
 Chu+0.007
Neg logit contributions
Story-0.008
ylan-0.008
 Brist-0.007
kok-0.007
 Kyr-0.007
Token death
Token ID1918
Feature activation+7.54e-02

Pos logit contributions
Story+0.000
ylan+0.000
 Brist+0.000
kok+0.000
 Kyr+0.000
Neg logit contributions
Pope-0.000
angel-0.000
 Towards-0.000
 Deng-0.000
 Chu-0.000
Token of
Token ID286
Feature activation+5.16e-03

Pos logit contributions
Pope+0.059
angel+0.055
 Towards+0.046
 Deng+0.046
 Chu+0.045
Neg logit contributions
Story-0.058
ylan-0.057
 Brist-0.056
kok-0.054
 Kyr-0.052
Token the
Token ID262
Feature activation-2.98e-03

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.003
 Deng+0.003
atum+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.003
 Kyr-0.003
Token Dru
Token ID21295
Feature activation-4.63e-02

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
atum-0.002
Tokenze
Token ID2736
Feature activation+4.68e-01

Pos logit contributions
Story+0.059
ylan+0.059
 Brist+0.058
kok+0.057
 saddle+0.056
Neg logit contributions
Pope-0.012
angel-0.009
 Towards-0.005
 Deng-0.004
 Chu-0.004
Token police
Token ID1644
Feature activation-2.92e-02

Pos logit contributions
Pope+0.370
angel+0.343
 Towards+0.291
 Deng+0.288
atum+0.281
Neg logit contributions
Story-0.354
ylan-0.351
 Brist-0.346
kok-0.332
 Kyr-0.319
Token officer
Token ID3818
Feature activation-6.99e-02

Pos logit contributions
Story+0.023
ylan+0.023
 Brist+0.023
kok+0.022
 Kyr+0.021
Neg logit contributions
Pope-0.022
angel-0.020
 Towards-0.017
 Deng-0.017
atum-0.016
Token.
Token ID13
Feature activation-4.02e-03

Pos logit contributions
Story+0.052
ylan+0.052
 Brist+0.051
kok+0.049
 Kyr+0.047
Neg logit contributions
Pope-0.056
angel-0.052
 Towards-0.044
 Deng-0.044
 Chu-0.043
Token
Token ID198
Feature activation+7.70e-03

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.003
 Kyr+0.003
Neg logit contributions
Pope-0.003
angel-0.003
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token
Token ID198
Feature activation+1.58e-03

Pos logit contributions
Pope+0.006
angel+0.006
 Towards+0.005
 Deng+0.005
 Chu+0.005
Neg logit contributions
Story-0.006
ylan-0.006
 Brist-0.006
kok-0.005
 Kyr-0.005
Token Jewish
Token ID5582
Feature activation+3.18e-02

Pos logit contributions
Pope+0.019
angel+0.018
 Towards+0.015
 Deng+0.015
 Chu+0.015
Neg logit contributions
Story-0.018
ylan-0.018
 Brist-0.018
kok-0.017
 Kyr-0.016
Token,
Token ID11
Feature activation-1.73e-03

Pos logit contributions
Pope+0.025
angel+0.023
 Towards+0.019
 Deng+0.019
atum+0.019
Neg logit contributions
Story-0.024
ylan-0.024
 Brist-0.024
kok-0.023
 Kyr-0.022
Token Arab
Token ID4498
Feature activation-1.20e-01

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.002
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token and
Token ID290
Feature activation+5.15e-03

Pos logit contributions
Story+0.092
ylan+0.092
 Brist+0.090
kok+0.087
 Kyr+0.083
Neg logit contributions
Pope-0.094
angel-0.087
 Towards-0.073
 Deng-0.072
 Chu-0.071
Token Dru
Token ID21295
Feature activation-5.27e-02

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.004
 Deng+0.003
atum+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.003
kok-0.003
 Kyr-0.003
Tokenze
Token ID2736
Feature activation+4.68e-01

Pos logit contributions
Story+0.069
ylan+0.068
 Brist+0.067
kok+0.066
 Kyr+0.065
Neg logit contributions
Pope-0.013
angel-0.010
 Towards-0.004
 Deng-0.004
 Chu-0.003
Token
Token ID784
Feature activation+1.76e-02

Pos logit contributions
Pope+0.357
angel+0.330
 Towards+0.278
 Deng+0.275
 Chu+0.269
Neg logit contributions
Story-0.367
ylan-0.364
 Brist-0.358
kok-0.346
 Kyr-0.331
Token who
Token ID508
Feature activation-2.33e-03

Pos logit contributions
Pope+0.014
angel+0.013
 Towards+0.011
 Deng+0.011
 Chu+0.011
Neg logit contributions
Story-0.013
ylan-0.013
 Brist-0.013
kok-0.012
 Kyr-0.012
Token came
Token ID1625
Feature activation+1.68e-01

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token together
Token ID1978
Feature activation-8.47e-02

Pos logit contributions
Pope+0.136
angel+0.126
 Towards+0.108
 Deng+0.106
 Chu+0.104
Neg logit contributions
Story-0.124
ylan-0.123
 Brist-0.121
kok-0.116
 Kyr-0.111
Token for
Token ID329
Feature activation-3.74e-03

Pos logit contributions
Story+0.063
ylan+0.062
 Brist+0.061
kok+0.059
 Kyr+0.057
Neg logit contributions
Pope-0.068
angel-0.063
 Towards-0.054
 Deng-0.053
 Chu-0.052
Token (
Token ID357
Feature activation-7.08e-02

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.001
 Deng-0.001
atum-0.001
TokenAP
Token ID2969
Feature activation-4.88e-02

Pos logit contributions
Story+0.050
ylan+0.049
 Brist+0.048
kok+0.046
 Kyr+0.044
Neg logit contributions
Pope-0.060
angel-0.056
 Towards-0.048
 Deng-0.047
 Chu-0.047
Token)
Token ID8
Feature activation-3.60e-02

Pos logit contributions
Story+0.030
ylan+0.030
 Brist+0.029
kok+0.028
 Kyr+0.027
Neg logit contributions
Pope-0.045
angel-0.042
 Towards-0.037
 Deng-0.037
 Chu-0.036
Token
Token ID198
Feature activation+6.18e-04

Pos logit contributions
Story+0.026
ylan+0.026
 Brist+0.026
kok+0.025
 Kyr+0.024
Neg logit contributions
Pope-0.029
angel-0.027
 Towards-0.023
 Deng-0.023
atum-0.023
Token
Token ID198
Feature activation+3.81e-03

Pos logit contributions
Pope+0.000
angel+0.000
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.000
ylan-0.000
 Brist-0.000
kok-0.000
 Kyr-0.000
TokenStory
Token ID11605
Feature activation-6.28e-01

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
Token continues
Token ID4477
Feature activation-5.59e-02

Pos logit contributions
Story+0.426
ylan+0.420
 Brist+0.412
kok+0.394
 Kyr+0.374
Neg logit contributions
Pope-0.551
angel-0.514
 Towards-0.441
 Deng-0.437
 Chu-0.429
Token
Token ID198
Feature activation+3.81e-03

Pos logit contributions
Story+0.048
ylan+0.048
 Brist+0.047
kok+0.046
 Kyr+0.044
Neg logit contributions
Pope-0.038
angel-0.035
 Towards-0.029
 Deng-0.028
 Chu-0.028
Token
Token ID198
Feature activation+5.31e-03

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
TokenThere
Token ID1858
Feature activation-9.15e-02

Pos logit contributions
Pope+0.007
angel+0.007
 Towards+0.007
 Deng+0.007
 Chu+0.006
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.000
Token were
Token ID547
Feature activation-2.66e-02

Pos logit contributions
Story+0.068
ylan+0.067
 Brist+0.066
kok+0.064
 Kyr+0.061
Neg logit contributions
Pope-0.074
angel-0.069
 Towards-0.058
 Deng-0.058
 Chu-0.057
Token continues
Token ID4477
Feature activation-6.08e-02

Pos logit contributions
Story+0.427
ylan+0.424
 Brist+0.418
kok+0.401
 Kyr+0.383
Neg logit contributions
Pope-0.534
angel-0.497
 Towards-0.428
 Deng-0.423
 Chu-0.416
Token below
Token ID2174
Feature activation+8.70e-02

Pos logit contributions
Story+0.054
ylan+0.054
 Brist+0.053
kok+0.052
 Kyr+0.050
Neg logit contributions
Pope-0.040
angel-0.036
 Towards-0.030
 Deng-0.029
 Chu-0.028
Token advertisement
Token ID15422
Feature activation+2.27e-02

Pos logit contributions
Pope+0.068
angel+0.063
 Towards+0.053
 Deng+0.052
 Chu+0.051
Neg logit contributions
Story-0.067
ylan-0.067
 Brist-0.065
kok-0.063
 Kyr-0.060
Token
Token ID198
Feature activation-1.31e-03

Pos logit contributions
Pope+0.018
angel+0.017
 Towards+0.014
 Deng+0.014
 Chu+0.014
Neg logit contributions
Story-0.017
ylan-0.017
 Brist-0.017
kok-0.016
 Kyr-0.016
Token
Token ID198
Feature activation-3.18e-03

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
TokenStory
Token ID11605
Feature activation-6.24e-01

Pos logit contributions
ylan+0.000
Story+0.000
 Brist+0.000
kok+0.000
 Kyr+0.000
Neg logit contributions
Pope-0.005
angel-0.004
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token continues
Token ID4477
Feature activation-6.01e-02

Pos logit contributions
Story+0.425
ylan+0.422
 Brist+0.415
kok+0.397
 Kyr+0.379
Neg logit contributions
Pope-0.541
angel-0.504
 Towards-0.434
 Deng-0.430
 Chu-0.422
Token below
Token ID2174
Feature activation+8.61e-02

Pos logit contributions
Story+0.053
ylan+0.052
 Brist+0.052
kok+0.050
 Kyr+0.048
Neg logit contributions
Pope-0.040
angel-0.037
 Towards-0.030
 Deng-0.030
 Chu-0.029
Token advertisement
Token ID15422
Feature activation+2.05e-02

Pos logit contributions
Pope+0.065
angel+0.060
 Towards+0.051
 Deng+0.050
 Chu+0.049
Neg logit contributions
Story-0.068
ylan-0.068
 Brist-0.067
kok-0.064
 Kyr-0.062
Token
Token ID198
Feature activation+3.31e-03

Pos logit contributions
Pope+0.016
angel+0.015
 Towards+0.013
 Deng+0.013
 Chu+0.012
Neg logit contributions
Story-0.016
ylan-0.015
 Brist-0.015
kok-0.015
 Kyr-0.014
Token
Token ID198
Feature activation-5.40e-04

Pos logit contributions
Pope+0.003
angel+0.002
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.002
kok-0.002
 Kyr-0.002
Token of
Token ID286
Feature activation+6.58e-04

Pos logit contributions
Pope+0.055
angel+0.051
 Towards+0.044
 Deng+0.043
 Chu+0.042
Neg logit contributions
Story-0.052
ylan-0.052
 Brist-0.051
kok-0.049
 Kyr-0.047
Token dollars
Token ID5054
Feature activation-6.69e-02

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.000
ylan-0.000
 Brist-0.000
kok-0.000
 Kyr-0.000
Token.
Token ID13
Feature activation-6.24e-03

Pos logit contributions
Story+0.050
ylan+0.049
 Brist+0.048
kok+0.047
 Kyr+0.045
Neg logit contributions
Pope-0.054
angel-0.050
 Towards-0.042
 Deng-0.042
 Chu-0.041
Token
Token ID198
Feature activation+1.73e-04

Pos logit contributions
ylan+0.005
Story+0.005
 Brist+0.005
kok+0.005
 saddle+0.004
Neg logit contributions
Pope-0.005
angel-0.004
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token
Token ID198
Feature activation-1.90e-04

Pos logit contributions
Pope+0.000
angel+0.000
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.000
ylan-0.000
 Brist-0.000
kok-0.000
 Kyr-0.000
TokenStory
Token ID11605
Feature activation-6.21e-01

Pos logit contributions
Story+0.000
ylan+0.000
 Brist+0.000
kok+0.000
 Kyr+0.000
Neg logit contributions
Pope-0.000
angel-0.000
 Towards-0.000
 Deng-0.000
 Chu-0.000
Token continues
Token ID4477
Feature activation-6.08e-02

Pos logit contributions
Story+0.427
ylan+0.424
 Brist+0.418
kok+0.401
 Kyr+0.383
Neg logit contributions
Pope-0.534
angel-0.497
 Towards-0.428
 Deng-0.423
 Chu-0.416
Token below
Token ID2174
Feature activation+8.70e-02

Pos logit contributions
Story+0.054
ylan+0.054
 Brist+0.053
kok+0.052
 Kyr+0.050
Neg logit contributions
Pope-0.040
angel-0.036
 Towards-0.030
 Deng-0.029
 Chu-0.028
Token advertisement
Token ID15422
Feature activation+2.27e-02

Pos logit contributions
Pope+0.068
angel+0.063
 Towards+0.053
 Deng+0.052
 Chu+0.051
Neg logit contributions
Story-0.067
ylan-0.067
 Brist-0.065
kok-0.063
 Kyr-0.060
Token
Token ID198
Feature activation-1.31e-03

Pos logit contributions
Pope+0.018
angel+0.017
 Towards+0.014
 Deng+0.014
 Chu+0.014
Neg logit contributions
Story-0.017
ylan-0.017
 Brist-0.017
kok-0.016
 Kyr-0.016
Token
Token ID198
Feature activation-3.18e-03

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token She
Token ID1375
Feature activation+2.50e-02

Pos logit contributions
Pope+0.109
angel+0.101
 Towards+0.086
 Deng+0.085
 Chu+0.084
Neg logit contributions
Story-0.097
ylan-0.096
 Brist-0.095
kok-0.091
 Kyr-0.087
Tokenpell
Token ID23506
Feature activation+9.70e-02

Pos logit contributions
Pope+0.018
angel+0.016
 Towards+0.013
 Deng+0.013
 Chu+0.013
Neg logit contributions
Story-0.021
ylan-0.021
 Brist-0.020
kok-0.020
 Kyr-0.019
Token.
Token ID13
Feature activation-5.97e-03

Pos logit contributions
Pope+0.077
angel+0.071
 Towards+0.060
 Deng+0.060
 Chu+0.058
Neg logit contributions
Story-0.074
ylan-0.073
 Brist-0.072
kok-0.069
 Kyr-0.066
Token
Token ID198
Feature activation+6.93e-03

Pos logit contributions
Story+0.005
ylan+0.005
 Brist+0.004
kok+0.004
 saddle+0.004
Neg logit contributions
Pope-0.005
angel-0.004
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token
Token ID198
Feature activation-9.58e-04

Pos logit contributions
Pope+0.005
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.005
 Kyr-0.005
TokenStory
Token ID11605
Feature activation-6.21e-01

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token continues
Token ID4477
Feature activation-5.73e-02

Pos logit contributions
Story+0.426
ylan+0.423
 Brist+0.417
kok+0.399
 Kyr+0.381
Neg logit contributions
Pope-0.535
angel-0.499
 Towards-0.429
 Deng-0.424
 Chu-0.417
Token below
Token ID2174
Feature activation+8.98e-02

Pos logit contributions
Story+0.051
ylan+0.051
 Brist+0.050
kok+0.048
 Kyr+0.047
Neg logit contributions
Pope-0.038
angel-0.034
 Towards-0.028
 Deng-0.028
 Chu-0.027
Token advertisement
Token ID15422
Feature activation+2.19e-02

Pos logit contributions
Pope+0.067
angel+0.062
 Towards+0.052
 Deng+0.052
 Chu+0.050
Neg logit contributions
Story-0.071
ylan-0.071
 Brist-0.070
kok-0.068
 Kyr-0.065
Token
Token ID198
Feature activation-4.13e-03

Pos logit contributions
Pope+0.017
angel+0.016
 Towards+0.014
 Deng+0.013
 Chu+0.013
Neg logit contributions
Story-0.017
ylan-0.017
 Brist-0.016
kok-0.016
 Kyr-0.015
Token
Token ID198
Feature activation+7.44e-03

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.003
 Kyr+0.003
Neg logit contributions
Pope-0.003
angel-0.003
 Towards-0.003
 Deng-0.003
 Chu-0.002
Token PC
Token ID4217
Feature activation+2.03e-01

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.001
 Kyr-0.001
Token
Token ID447
Feature activation+2.87e-03

Pos logit contributions
Pope+0.162
angel+0.151
 Towards+0.128
 Deng+0.126
 Chu+0.124
Neg logit contributions
Story-0.152
ylan-0.151
 Brist-0.149
kok-0.144
 Kyr-0.137
Token
Token ID247
Feature activation+2.38e-03

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.002
Tokens
Token ID82
Feature activation-1.59e-03

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.002
Token Back
Token ID5157
Feature activation-1.16e-01

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
TokenStory
Token ID11605
Feature activation-6.21e-01

Pos logit contributions
Story+0.080
ylan+0.080
 Brist+0.078
kok+0.075
 Kyr+0.072
Neg logit contributions
Pope-0.100
angel-0.093
 Towards-0.080
 Deng-0.079
 Chu-0.078
Token:
Token ID25
Feature activation+2.33e-03

Pos logit contributions
Story+0.469
ylan+0.461
 Brist+0.455
kok+0.437
 Kyr+0.420
Neg logit contributions
Pope-0.496
angel-0.459
 Towards-0.388
 Deng-0.385
 Chu-0.377
Token (
Token ID357
Feature activation-7.45e-02

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.001
TokenExample
Token ID16281
Feature activation-2.41e-02

Pos logit contributions
Story+0.053
ylan+0.053
 Brist+0.052
kok+0.050
 Kyr+0.047
Neg logit contributions
Pope-0.062
angel-0.058
 Towards-0.050
 Deng-0.049
 Chu-0.048
Token:
Token ID25
Feature activation+5.41e-03

Pos logit contributions
Story+0.019
ylan+0.018
 Brist+0.018
kok+0.018
 Kyr+0.017
Neg logit contributions
Pope-0.019
angel-0.017
 Towards-0.015
 Deng-0.014
 Chu-0.014
Token Th
Token ID536
Feature activation+1.20e-01

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
Token '
Token ID705
Feature activation+4.71e-03

Pos logit contributions
Pope+0.105
angel+0.097
 Towards+0.082
 Deng+0.081
 Chu+0.079
Neg logit contributions
Story-0.102
ylan-0.101
 Brist-0.099
kok-0.096
 Kyr-0.092
Tokenkeeper
Token ID13884
Feature activation+8.33e-02

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
Token.
Token ID13
Feature activation+2.73e-04

Pos logit contributions
Pope+0.067
angel+0.062
 Towards+0.053
 Deng+0.052
 Chu+0.051
Neg logit contributions
Story-0.062
ylan-0.061
 Brist-0.060
kok-0.058
 Kyr-0.056
Token
Token ID198
Feature activation+6.13e-03

Pos logit contributions
Pope+0.000
angel+0.000
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.000
ylan-0.000
 Brist-0.000
kok-0.000
 Kyr-0.000
Token
Token ID198
Feature activation+5.22e-03

Pos logit contributions
Pope+0.005
angel+0.004
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.004
 Kyr-0.004
TokenStory
Token ID11605
Feature activation-6.20e-01

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.004
 Deng+0.004
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.003
 Kyr-0.003
Token continues
Token ID4477
Feature activation-5.08e-02

Pos logit contributions
Story+0.420
ylan+0.415
 Brist+0.407
kok+0.391
 Kyr+0.372
Neg logit contributions
Pope-0.542
angel-0.505
 Towards-0.436
 Deng-0.432
 Chu-0.424
Token below
Token ID2174
Feature activation+9.20e-02

Pos logit contributions
Story+0.045
ylan+0.044
 Brist+0.044
kok+0.043
 Kyr+0.041
Neg logit contributions
Pope-0.034
angel-0.031
 Towards-0.025
 Deng-0.025
 Chu-0.024
Token advertisement
Token ID15422
Feature activation+2.59e-02

Pos logit contributions
Pope+0.069
angel+0.063
 Towards+0.053
 Deng+0.053
 Chu+0.052
Neg logit contributions
Story-0.073
ylan-0.073
 Brist-0.072
kok-0.069
 Kyr-0.066
Token
Token ID198
Feature activation+4.97e-03

Pos logit contributions
Pope+0.020
angel+0.019
 Towards+0.016
 Deng+0.016
 Chu+0.015
Neg logit contributions
Story-0.020
ylan-0.020
 Brist-0.019
kok-0.019
 Kyr-0.018
Token
Token ID198
Feature activation+6.22e-03

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.003
Token the
Token ID262
Feature activation-9.40e-04

Pos logit contributions
Pope+0.005
angel+0.004
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
Token club
Token ID3430
Feature activation-1.14e-01

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token.
Token ID13
Feature activation-7.22e-03

Pos logit contributions
Story+0.087
ylan+0.086
 Brist+0.084
kok+0.082
earch+0.078
Neg logit contributions
Pope-0.089
angel-0.082
 Towards-0.070
 Deng-0.069
 Chu-0.068
Token
Token ID198
Feature activation+3.66e-03

Pos logit contributions
Story+0.006
ylan+0.006
 Brist+0.005
kok+0.005
 saddle+0.005
Neg logit contributions
Pope-0.006
angel-0.005
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token
Token ID198
Feature activation-7.64e-04

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
TokenStory
Token ID11605
Feature activation-6.19e-01

Pos logit contributions
ylan+0.001
Story+0.001
 Brist+0.000
kok+0.000
 saddle+0.000
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token continues
Token ID4477
Feature activation-5.43e-02

Pos logit contributions
Story+0.419
ylan+0.415
 Brist+0.407
kok+0.391
 Kyr+0.372
Neg logit contributions
Pope-0.540
angel-0.504
 Towards-0.435
 Deng-0.430
 Chu-0.423
Token below
Token ID2174
Feature activation+8.84e-02

Pos logit contributions
Story+0.048
ylan+0.047
 Brist+0.047
kok+0.045
 Kyr+0.044
Neg logit contributions
Pope-0.036
angel-0.033
 Towards-0.027
 Deng-0.027
 Chu-0.026
Token advertisement
Token ID15422
Feature activation+1.70e-02

Pos logit contributions
Pope+0.066
angel+0.061
 Towards+0.051
 Deng+0.051
 Chu+0.050
Neg logit contributions
Story-0.070
ylan-0.070
 Brist-0.069
kok-0.067
 Kyr-0.064
Token
Token ID198
Feature activation+7.75e-03

Pos logit contributions
Pope+0.013
angel+0.012
 Towards+0.010
 Deng+0.010
 Chu+0.010
Neg logit contributions
Story-0.013
ylan-0.013
 Brist-0.013
kok-0.012
 Kyr-0.012
Token
Token ID198
Feature activation+2.21e-04

Pos logit contributions
Pope+0.006
angel+0.006
 Towards+0.005
 Deng+0.005
 Chu+0.005
Neg logit contributions
Story-0.006
ylan-0.006
 Brist-0.006
kok-0.006
 Kyr-0.005
Token continues
Token ID4477
Feature activation-5.08e-02

Pos logit contributions
Story+0.420
ylan+0.415
 Brist+0.407
kok+0.391
 Kyr+0.372
Neg logit contributions
Pope-0.542
angel-0.505
 Towards-0.436
 Deng-0.432
 Chu-0.424
Token below
Token ID2174
Feature activation+9.20e-02

Pos logit contributions
Story+0.045
ylan+0.044
 Brist+0.044
kok+0.043
 Kyr+0.041
Neg logit contributions
Pope-0.034
angel-0.031
 Towards-0.025
 Deng-0.025
 Chu-0.024
Token advertisement
Token ID15422
Feature activation+2.59e-02

Pos logit contributions
Pope+0.069
angel+0.063
 Towards+0.053
 Deng+0.053
 Chu+0.052
Neg logit contributions
Story-0.073
ylan-0.073
 Brist-0.072
kok-0.069
 Kyr-0.066
Token
Token ID198
Feature activation+4.97e-03

Pos logit contributions
Pope+0.020
angel+0.019
 Towards+0.016
 Deng+0.016
 Chu+0.015
Neg logit contributions
Story-0.020
ylan-0.020
 Brist-0.019
kok-0.019
 Kyr-0.018
Token
Token ID198
Feature activation+6.22e-03

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.003
TokenStory
Token ID11605
Feature activation-6.18e-01

Pos logit contributions
Pope+0.009
angel+0.009
 Towards+0.008
 Deng+0.008
 Chu+0.008
Neg logit contributions
Story-0.000
ylan-0.000
 Brist-0.000
kok+0.000
 Kyr+0.000
Token continues
Token ID4477
Feature activation-5.45e-02

Pos logit contributions
Story+0.419
ylan+0.415
 Brist+0.407
kok+0.391
 Kyr+0.372
Neg logit contributions
Pope-0.539
angel-0.503
 Towards-0.434
 Deng-0.429
 Chu-0.421
Token below
Token ID2174
Feature activation+9.73e-02

Pos logit contributions
Story+0.048
ylan+0.047
 Brist+0.047
kok+0.045
 Kyr+0.044
Neg logit contributions
Pope-0.037
angel-0.033
 Towards-0.027
 Deng-0.027
 Chu-0.026
Token advertisement
Token ID15422
Feature activation+2.14e-02

Pos logit contributions
Pope+0.073
angel+0.068
 Towards+0.057
 Deng+0.057
 Chu+0.055
Neg logit contributions
Story-0.077
ylan-0.076
 Brist-0.075
kok-0.073
 Kyr-0.070
Token
Token ID198
Feature activation+9.12e-03

Pos logit contributions
Pope+0.017
angel+0.016
 Towards+0.013
 Deng+0.013
 Chu+0.013
Neg logit contributions
Story-0.016
ylan-0.016
 Brist-0.016
kok-0.015
 Kyr-0.015
Token
Token ID198
Feature activation+9.31e-03

Pos logit contributions
Pope+0.007
angel+0.007
 Towards+0.006
 Deng+0.006
 Chu+0.005
Neg logit contributions
Story-0.007
ylan-0.007
 Brist-0.007
kok-0.007
 Kyr-0.006
Token to
Token ID284
Feature activation-3.53e-03

Pos logit contributions
Pope+0.020
angel+0.018
 Towards+0.015
 Deng+0.015
 Chu+0.015
Neg logit contributions
Story-0.018
ylan-0.018
 Brist-0.018
kok-0.017
 Kyr-0.016
Token vote
Token ID3015
Feature activation+1.05e-01

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.003
angel-0.003
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token accordingly
Token ID16062
Feature activation+1.41e-01

Pos logit contributions
Pope+0.084
angel+0.078
 Towards+0.066
 Deng+0.065
atum+0.064
Neg logit contributions
Story-0.079
ylan-0.078
 Brist-0.077
kok-0.074
 Kyr-0.071
Token.
Token ID13
Feature activation-1.49e-03

Pos logit contributions
Pope+0.112
angel+0.104
 Towards+0.088
 Deng+0.087
 Chu+0.085
Neg logit contributions
Story-0.106
ylan-0.105
 Brist-0.104
kok-0.100
 Kyr-0.096
Token<|endoftext|>
Token ID50256
Feature activation-2.01e-01

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
TokenStory
Token ID11605
Feature activation-6.17e-01

Pos logit contributions
Story+0.150
ylan+0.148
 Brist+0.145
kok+0.140
 Kyr+0.134
Neg logit contributions
Pope-0.161
angel-0.149
 Towards-0.128
 Deng-0.126
 Chu-0.124
Token highlights
Token ID11330
Feature activation+1.06e-01

Pos logit contributions
Story+0.509
ylan+0.499
 Brist+0.493
kok+0.474
 Kyr+0.454
Neg logit contributions
Pope-0.452
angel-0.418
 Towards-0.346
 Deng-0.342
atum-0.335
Token Police
Token ID4287
Feature activation-5.59e-02

Pos logit contributions
Pope+0.084
angel+0.078
 Towards+0.066
 Deng+0.065
 Chu+0.064
Neg logit contributions
Story-0.080
ylan-0.079
 Brist-0.078
kok-0.075
 Kyr-0.072
Token chief
Token ID4039
Feature activation+1.42e-01

Pos logit contributions
Story+0.040
ylan+0.040
 Brist+0.039
kok+0.038
 Kyr+0.036
Neg logit contributions
Pope-0.046
angel-0.043
 Towards-0.037
 Deng-0.036
 Chu-0.036
Token vows
Token ID36605
Feature activation+8.90e-02

Pos logit contributions
Pope+0.111
angel+0.103
 Towards+0.087
 Deng+0.085
 Chu+0.084
Neg logit contributions
Story-0.110
ylan-0.109
 Brist-0.107
kok-0.103
 Kyr-0.099
Token wanted
Token ID2227
Feature activation+7.57e-02

Pos logit contributions
Pope+0.072
angel+0.067
 Towards+0.057
 Deng+0.056
 Chu+0.055
Neg logit contributions
Story-0.066
ylan-0.065
 Brist-0.064
kok-0.061
 Kyr-0.059
Token big
Token ID1263
Feature activation+3.06e-01

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.003
 Deng+0.003
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
Token stage
Token ID3800
Feature activation+1.08e-01

Pos logit contributions
Pope+0.201
angel+0.183
 Towards+0.149
 Deng+0.147
 Chu+0.144
Neg logit contributions
Story-0.270
ylan-0.269
 Brist-0.266
kok-0.258
 Kyr-0.248
Token.
Token ID13
Feature activation-1.56e-03

Pos logit contributions
Pope+0.085
angel+0.079
 Towards+0.067
 Deng+0.066
 Chu+0.065
Neg logit contributions
Story-0.081
ylan-0.081
 Brist-0.079
kok-0.076
 Kyr-0.073
Token
Token ID198
Feature activation+4.66e-03

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token
Token ID198
Feature activation+1.13e-03

Pos logit contributions
Pope+0.004
angel+0.003
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
TokenStory
Token ID11605
Feature activation-6.17e-01

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token continues
Token ID4477
Feature activation-5.59e-02

Pos logit contributions
Story+0.408
ylan+0.400
 Brist+0.391
kok+0.373
 saddle+0.355
Neg logit contributions
Pope-0.555
angel-0.518
 Towards-0.445
 Deng-0.443
 Chu-0.436
Token below
Token ID2174
Feature activation+9.38e-02

Pos logit contributions
Story+0.049
ylan+0.049
 Brist+0.048
kok+0.047
 Kyr+0.045
Neg logit contributions
Pope-0.037
angel-0.034
 Towards-0.028
 Deng-0.027
 Chu-0.027
Token advertisement
Token ID15422
Feature activation+2.53e-02

Pos logit contributions
Pope+0.073
angel+0.067
 Towards+0.057
 Deng+0.056
 Chu+0.055
Neg logit contributions
Story-0.072
ylan-0.072
 Brist-0.071
kok-0.068
 Kyr-0.065
Token
Token ID198
Feature activation+4.08e-03

Pos logit contributions
Pope+0.020
angel+0.018
 Towards+0.016
 Deng+0.015
 Chu+0.015
Neg logit contributions
Story-0.019
ylan-0.019
 Brist-0.019
kok-0.018
 Kyr-0.017
Token
Token ID198
Feature activation+3.49e-03

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.003
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
Token disclosure
Token ID13019
Feature activation-6.56e-02

Pos logit contributions
Pope+0.016
angel+0.015
 Towards+0.013
 Deng+0.013
 Chu+0.012
Neg logit contributions
Story-0.014
ylan-0.014
 Brist-0.013
kok-0.013
 Kyr-0.012
Token statement
Token ID2643
Feature activation-6.27e-02

Pos logit contributions
Story+0.049
ylan+0.049
 Brist+0.048
kok+0.046
 Kyr+0.044
Neg logit contributions
Pope-0.053
angel-0.049
 Towards-0.041
 Deng-0.041
 Chu-0.040
Token.
Token ID13
Feature activation-4.53e-03

Pos logit contributions
Story+0.047
ylan+0.047
 Brist+0.046
kok+0.045
 Kyr+0.043
Neg logit contributions
Pope-0.050
angel-0.046
 Towards-0.039
 Deng-0.039
 Chu-0.038
Token
Token ID198
Feature activation-3.43e-04

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.003
 saddle+0.003
Neg logit contributions
Pope-0.004
angel-0.003
 Towards-0.003
 Deng-0.003
 Chu-0.003
Token
Token ID198
Feature activation+1.95e-03

Pos logit contributions
Story+0.000
ylan+0.000
 Brist+0.000
kok+0.000
 Kyr+0.000
Neg logit contributions
Pope-0.000
angel-0.000
 Towards-0.000
 Deng-0.000
 Chu-0.000
TokenStory
Token ID11605
Feature activation-6.16e-01

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token continues
Token ID4477
Feature activation-5.52e-02

Pos logit contributions
Story+0.419
ylan+0.416
 Brist+0.409
kok+0.392
 Kyr+0.373
Neg logit contributions
Pope-0.534
angel-0.498
 Towards-0.429
 Deng-0.425
 Chu-0.417
Token below
Token ID2174
Feature activation+9.17e-02

Pos logit contributions
Story+0.049
ylan+0.048
 Brist+0.048
kok+0.046
 Kyr+0.045
Neg logit contributions
Pope-0.037
angel-0.033
 Towards-0.027
 Deng-0.027
 Chu-0.026
Token advertisement
Token ID15422
Feature activation+2.68e-02

Pos logit contributions
Pope+0.068
angel+0.063
 Towards+0.053
 Deng+0.053
 Chu+0.051
Neg logit contributions
ylan-0.073
Story-0.073
 Brist-0.072
kok-0.069
 Kyr-0.066
Token
Token ID198
Feature activation+1.02e-03

Pos logit contributions
Pope+0.021
angel+0.020
 Towards+0.017
 Deng+0.016
 Chu+0.016
Neg logit contributions
Story-0.021
ylan-0.020
 Brist-0.020
kok-0.019
 Kyr-0.018
Token
Token ID198
Feature activation+1.32e-03

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token-
Token ID12
Feature activation-1.65e-02

Pos logit contributions
Pope+0.111
angel+0.103
 Towards+0.087
 Deng+0.087
 Chu+0.085
Neg logit contributions
Story-0.104
ylan-0.102
 Brist-0.101
kok-0.097
 Kyr-0.093
Tokent
Token ID83
Feature activation+8.24e-03

Pos logit contributions
Story+0.013
ylan+0.012
 Brist+0.012
kok+0.012
 Kyr+0.011
Neg logit contributions
Pope-0.013
angel-0.012
 Towards-0.010
 Deng-0.010
 Chu-0.010
Tokenweet
Token ID7277
Feature activation+1.49e-01

Pos logit contributions
Pope+0.005
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.007
ylan-0.007
 Brist-0.007
kok-0.007
 Kyr-0.007
Token/
Token ID14
Feature activation+1.21e-01

Pos logit contributions
Pope+0.120
angel+0.111
 Towards+0.094
 Deng+0.093
 Chu+0.092
Neg logit contributions
Story-0.112
ylan-0.110
 Brist-0.108
kok-0.105
 Kyr-0.100
Token<|endoftext|>
Token ID50256
Feature activation-2.05e-01

Pos logit contributions
Pope+0.106
angel+0.099
 Towards+0.085
 Deng+0.084
 Chu+0.083
Neg logit contributions
Story-0.082
ylan-0.081
 Brist-0.080
kok-0.076
 Kyr-0.073
TokenStory
Token ID11605
Feature activation-6.16e-01

Pos logit contributions
Story+0.154
ylan+0.151
 Brist+0.148
kok+0.144
 Kyr+0.137
Neg logit contributions
Pope-0.164
angel-0.153
 Towards-0.130
 Deng-0.129
 Chu-0.126
Token highlights
Token ID11330
Feature activation+1.03e-01

Pos logit contributions
Story+0.509
ylan+0.500
 Brist+0.493
kok+0.475
 Kyr+0.455
Neg logit contributions
Pope-0.450
angel-0.415
 Towards-0.344
 Deng-0.340
 Chu-0.333
Token Secretary
Token ID4986
Feature activation+1.69e-01

Pos logit contributions
Pope+0.082
angel+0.076
 Towards+0.064
 Deng+0.063
 Chu+0.062
Neg logit contributions
Story-0.078
ylan-0.077
 Brist-0.076
kok-0.073
 Kyr-0.070
Token of
Token ID286
Feature activation-5.07e-03

Pos logit contributions
Pope+0.132
angel+0.122
 Towards+0.103
 Deng+0.102
 Chu+0.100
Neg logit contributions
Story-0.129
ylan-0.128
 Brist-0.126
kok-0.122
 saddle-0.116
Token Defense
Token ID5947
Feature activation-3.91e-02

Pos logit contributions
Story+0.004
ylan+0.004
 Brist+0.004
kok+0.004
 Kyr+0.004
Neg logit contributions
Pope-0.004
angel-0.003
 Towards-0.003
 Deng-0.003
 Chu-0.003
Token Chuck
Token ID14663
Feature activation-3.80e-01

Pos logit contributions
Story+0.026
ylan+0.026
 Brist+0.025
kok+0.024
 Kyr+0.023
Neg logit contributions
Pope-0.034
angel-0.032
 Towards-0.028
 Deng-0.028
 Chu-0.027
Token On
Token ID1550
Feature activation+4.06e-02

Pos logit contributions
Story+0.050
ylan+0.050
 Brist+0.049
kok+0.048
 Kyr+0.046
Neg logit contributions
Pope-0.046
angel-0.043
 Towards-0.036
 Deng-0.035
 Chu-0.034
Tokenstad
Token ID24107
Feature activation+3.46e-01

Pos logit contributions
Pope+0.016
angel+0.014
 Towards+0.009
 Deng+0.009
 Chu+0.009
Neg logit contributions
Story-0.046
ylan-0.046
 Brist-0.046
kok-0.045
 Kyr-0.043
Token.
Token ID13
Feature activation-3.37e-03

Pos logit contributions
Pope+0.271
angel+0.251
 Towards+0.212
 Deng+0.210
 Chu+0.206
Neg logit contributions
Story-0.264
ylan-0.262
 Brist-0.257
kok-0.249
 Kyr-0.237
Token
Token ID198
Feature activation+1.10e-03

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.003
 Kyr+0.003
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token
Token ID198
Feature activation+3.63e-03

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
TokenStory
Token ID11605
Feature activation-6.14e-01

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.003
 Deng+0.003
 Chu+0.002
Neg logit contributions
ylan-0.002
Story-0.002
 Brist-0.002
kok-0.002
 saddle-0.002
Token continues
Token ID4477
Feature activation-5.64e-02

Pos logit contributions
Story+0.415
ylan+0.410
 Brist+0.402
kok+0.386
 Kyr+0.367
Neg logit contributions
Pope-0.538
angel-0.501
 Towards-0.433
 Deng-0.428
 Chu-0.421
Token below
Token ID2174
Feature activation+9.09e-02

Pos logit contributions
Story+0.049
ylan+0.049
 Brist+0.048
kok+0.047
 Kyr+0.045
Neg logit contributions
Pope-0.038
angel-0.035
 Towards-0.028
 Deng-0.028
 Chu-0.027
Token advertisement
Token ID15422
Feature activation+2.17e-02

Pos logit contributions
Pope+0.068
angel+0.063
 Towards+0.053
 Deng+0.052
 Chu+0.051
Neg logit contributions
Story-0.072
ylan-0.072
 Brist-0.071
kok-0.069
 Kyr-0.066
Token
Token ID198
Feature activation-1.59e-03

Pos logit contributions
Pope+0.017
angel+0.016
 Towards+0.013
 Deng+0.013
 Chu+0.013
Neg logit contributions
Story-0.017
ylan-0.016
 Brist-0.016
kok-0.016
 Kyr-0.015
Token
Token ID198
Feature activation+2.49e-03

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token season
Token ID1622
Feature activation+7.75e-02

Pos logit contributions
Pope+0.102
angel+0.095
 Towards+0.080
 Deng+0.079
 Chu+0.077
Neg logit contributions
Story-0.107
ylan-0.106
 Brist-0.104
kok-0.101
 Kyr-0.097
Token one
Token ID530
Feature activation-1.62e-03

Pos logit contributions
Pope+0.061
angel+0.057
 Towards+0.048
 Deng+0.048
 Chu+0.047
Neg logit contributions
Story-0.058
ylan-0.058
 Brist-0.057
kok-0.055
earch-0.053
Token!
Token ID0
Feature activation+4.95e-02

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token
Token ID198
Feature activation+2.37e-03

Pos logit contributions
Pope+0.040
angel+0.037
 Towards+0.031
 Deng+0.031
atum+0.030
Neg logit contributions
Story-0.037
ylan-0.037
 Brist-0.036
kok-0.035
 Kyr-0.033
Token
Token ID198
Feature activation+8.93e-03

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.002
TokenStory
Token ID11605
Feature activation-6.11e-01

Pos logit contributions
Pope+0.007
angel+0.007
 Towards+0.006
 Deng+0.006
 Chu+0.006
Neg logit contributions
Story-0.007
ylan-0.007
 Brist-0.006
kok-0.006
 Kyr-0.006
Token Editor
Token ID12058
Feature activation-2.11e-02

Pos logit contributions
Story+0.461
ylan+0.452
 Brist+0.447
kok+0.428
 Kyr+0.410
Neg logit contributions
Pope-0.490
angel-0.452
 Towards-0.383
 Deng-0.379
atum-0.372
Token and
Token ID290
Feature activation+1.21e-02

Pos logit contributions
Story+0.016
ylan+0.016
 Brist+0.015
kok+0.015
 Kyr+0.014
Neg logit contributions
Pope-0.017
angel-0.016
 Towards-0.013
 Deng-0.013
 Chu-0.013
Token Producer
Token ID30436
Feature activation-2.07e-01

Pos logit contributions
Pope+0.013
angel+0.012
 Towards+0.011
 Deng+0.010
 Chu+0.010
Neg logit contributions
Story-0.006
ylan-0.006
 Brist-0.006
kok-0.006
 Kyr-0.005
Token,
Token ID11
Feature activation+4.20e-03

Pos logit contributions
Story+0.152
ylan+0.150
 Brist+0.148
kok+0.142
 Kyr+0.136
Neg logit contributions
Pope-0.170
angel-0.157
 Towards-0.134
 Deng-0.132
 Chu-0.130
Token
Token ID198
Feature activation+1.79e-03

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
Token Coach
Token ID16393
Feature activation+1.38e-01

Pos logit contributions
Story+0.037
ylan+0.037
 Brist+0.036
kok+0.034
 Kyr+0.033
Neg logit contributions
Pope-0.042
angel-0.039
 Towards-0.033
 Deng-0.032
atum-0.032
Token [
Token ID685
Feature activation-1.29e-01

Pos logit contributions
Pope+0.111
angel+0.103
 Towards+0.087
 Deng+0.086
atum+0.084
Neg logit contributions
Story-0.103
ylan-0.102
 Brist-0.101
kok-0.097
 Kyr-0.093
TokenDoug
Token ID42297
Feature activation+9.89e-02

Pos logit contributions
Story+0.096
ylan+0.093
 Brist+0.091
kok+0.089
 Kyr+0.084
Neg logit contributions
Pope-0.104
angel-0.097
 Towards-0.084
 Deng-0.082
 Chu-0.081
Token]
Token ID60
Feature activation-7.27e-02

Pos logit contributions
Pope+0.087
angel+0.081
 Towards+0.070
 Deng+0.069
atum+0.068
Neg logit contributions
Story-0.066
ylan-0.066
 Brist-0.065
kok-0.062
 Kyr-0.059
Token Mar
Token ID1526
Feature activation+5.65e-02

Pos logit contributions
Story+0.057
ylan+0.056
 Brist+0.056
kok+0.054
 Kyr+0.052
Neg logit contributions
Pope-0.055
angel-0.051
 Towards-0.043
 Deng-0.042
atum-0.042
Tokenrone
Token ID33171
Feature activation-5.10e-01

Pos logit contributions
Pope+0.080
angel+0.077
 Towards+0.070
 Deng+0.069
atum+0.069
Neg logit contributions
Story-0.008
ylan-0.007
 Brist-0.007
kok-0.005
 Kyr-0.004
Token has
Token ID468
Feature activation-1.92e-02

Pos logit contributions
Story+0.373
ylan+0.368
 Brist+0.363
kok+0.349
 Kyr+0.335
Neg logit contributions
Pope-0.417
angel-0.387
 Towards-0.330
 Deng-0.324
 Chu-0.318
Token instructed
Token ID17767
Feature activation+1.55e-01

Pos logit contributions
Story+0.014
ylan+0.014
 Brist+0.014
kok+0.013
 Kyr+0.013
Neg logit contributions
Pope-0.016
angel-0.014
 Towards-0.012
 Deng-0.012
atum-0.012
Token him
Token ID683
Feature activation-7.64e-02

Pos logit contributions
Pope+0.132
angel+0.123
 Towards+0.105
 Deng+0.104
atum+0.102
Neg logit contributions
Story-0.109
ylan-0.107
 Brist-0.106
kok-0.101
 Kyr-0.098
Token to
Token ID284
Feature activation-5.95e-03

Pos logit contributions
Story+0.056
ylan+0.055
 Brist+0.054
kok+0.052
 Kyr+0.050
Neg logit contributions
Pope-0.063
angel-0.059
 Towards-0.050
 Deng-0.049
 Chu-0.048
Token do
Token ID466
Feature activation+2.02e-02

Pos logit contributions
Story+0.004
ylan+0.004
 Brist+0.004
kok+0.004
 saddle+0.004
Neg logit contributions
Pope-0.005
angel-0.005
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token about
Token ID546
Feature activation-7.97e-02

Pos logit contributions
Pope+0.080
angel+0.074
 Towards+0.063
 Deng+0.062
 Chu+0.061
Neg logit contributions
Story-0.070
ylan-0.069
 Brist-0.068
kok-0.066
 Kyr-0.063
Token its
Token ID663
Feature activation-3.21e-02

Pos logit contributions
Story+0.058
ylan+0.058
 Brist+0.057
kok+0.055
 Kyr+0.052
Neg logit contributions
Pope-0.065
angel-0.060
 Towards-0.051
 Deng-0.051
 Chu-0.050
Token drug
Token ID2563
Feature activation-1.49e-01

Pos logit contributions
Story+0.025
ylan+0.024
 Brist+0.024
kok+0.023
 Kyr+0.022
Neg logit contributions
Pope-0.025
angel-0.023
 Towards-0.020
 Deng-0.019
 Chu-0.019
Token defer
Token ID29135
Feature activation+8.10e-02

Pos logit contributions
Story+0.111
ylan+0.109
 Brist+0.107
kok+0.104
 Kyr+0.099
Neg logit contributions
Pope-0.121
angel-0.112
 Towards-0.096
 Deng-0.095
 Chu-0.093
Tokenip
Token ID541
Feature activation-1.27e-01

Pos logit contributions
Pope+0.059
angel+0.054
 Towards+0.045
 Deng+0.044
 Chu+0.043
Neg logit contributions
Story-0.067
ylan-0.066
 Brist-0.065
kok-0.063
 Kyr-0.061
Tokenrone
Token ID33171
Feature activation-5.08e-01

Pos logit contributions
Story+0.087
ylan+0.085
 Brist+0.084
kok+0.081
 Kyr+0.077
Neg logit contributions
Pope-0.109
angel-0.103
 Towards-0.088
 Deng-0.087
atum-0.086
Token,
Token ID11
Feature activation+4.31e-04

Pos logit contributions
Story+0.388
ylan+0.381
 Brist+0.376
kok+0.363
 Kyr+0.349
Neg logit contributions
Pope-0.400
angel-0.371
 Towards-0.315
 Deng-0.313
atum-0.307
Token which
Token ID543
Feature activation-7.19e-02

Pos logit contributions
Pope+0.000
angel+0.000
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.000
ylan-0.000
 Brist-0.000
kok-0.000
 Kyr-0.000
Token is
Token ID318
Feature activation-1.63e-04

Pos logit contributions
Story+0.052
ylan+0.051
 Brist+0.050
kok+0.048
 Kyr+0.046
Neg logit contributions
Pope-0.060
angel-0.055
 Towards-0.047
 Deng-0.047
 Chu-0.046
Token used
Token ID973
Feature activation+4.63e-02

Pos logit contributions
Story+0.000
ylan+0.000
 Brist+0.000
kok+0.000
 Kyr+0.000
Neg logit contributions
Pope-0.000
angel-0.000
 Towards-0.000
 Deng-0.000
 Chu-0.000
Token to
Token ID284
Feature activation-1.24e-02

Pos logit contributions
Pope+0.036
angel+0.034
 Towards+0.029
 Deng+0.028
 Chu+0.028
Neg logit contributions
Story-0.035
ylan-0.035
 Brist-0.034
kok-0.033
 Kyr-0.032
Token,
Token ID11
Feature activation-2.61e-03

Pos logit contributions
Pope+0.103
angel+0.095
 Towards+0.081
 Deng+0.080
 Chu+0.078
Neg logit contributions
Story-0.095
ylan-0.094
 Brist-0.093
kok-0.089
 Kyr-0.086
Token specifically
Token ID5734
Feature activation+1.05e-01

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token concerning
Token ID9305
Feature activation-2.43e-02

Pos logit contributions
Pope+0.084
angel+0.078
 Towards+0.066
 Deng+0.065
 Chu+0.064
Neg logit contributions
Story-0.079
ylan-0.078
 Brist-0.077
kok-0.074
 Kyr-0.071
Token "
Token ID366
Feature activation+6.18e-02

Pos logit contributions
Story+0.018
ylan+0.018
 Brist+0.018
kok+0.017
 Kyr+0.016
Neg logit contributions
Pope-0.020
angel-0.018
 Towards-0.015
 Deng-0.015
atum-0.015
Tokenmis
Token ID25413
Feature activation-1.36e-01

Pos logit contributions
Pope+0.051
angel+0.047
 Towards+0.040
 Deng+0.040
 Chu+0.039
Neg logit contributions
Story-0.045
ylan-0.044
 Brist-0.044
kok-0.042
 Kyr-0.040
Tokenrepresent
Token ID15603
Feature activation-5.03e-01

Pos logit contributions
Story+0.079
ylan+0.078
 Brist+0.077
kok+0.073
 Kyr+0.069
Neg logit contributions
Pope-0.132
angel-0.124
 Towards-0.108
 Deng-0.108
 Chu-0.106
Tokenations
Token ID602
Feature activation-9.98e-02

Pos logit contributions
Story+0.323
ylan+0.320
 Brist+0.313
kok+0.300
 Kyr+0.285
Neg logit contributions
Pope-0.456
angel-0.426
 Towards-0.370
 Deng-0.367
 Chu-0.361
Token"
Token ID1
Feature activation+3.89e-03

Pos logit contributions
Story+0.075
ylan+0.074
 Brist+0.073
kok+0.070
 Kyr+0.067
Neg logit contributions
Pope-0.080
angel-0.074
 Towards-0.063
 Deng-0.062
 Chu-0.061
Token made
Token ID925
Feature activation-4.91e-02

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.002
 Deng+0.002
atum+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
Token to
Token ID284
Feature activation-4.89e-03

Pos logit contributions
Story+0.036
ylan+0.036
 Brist+0.035
kok+0.034
 Kyr+0.032
Neg logit contributions
Pope-0.040
angel-0.037
 Towards-0.031
 Deng-0.031
 Chu-0.031
Token the
Token ID262
Feature activation+3.16e-03

Pos logit contributions
Story+0.004
ylan+0.004
 Brist+0.004
kok+0.003
 Kyr+0.003
Neg logit contributions
Pope-0.004
angel-0.004
 Towards-0.003
 Deng-0.003
 Chu-0.003
Token thoroughly
Token ID13770
Feature activation-1.15e-01

Pos logit contributions
Pope+0.054
angel+0.050
 Towards+0.043
 Deng+0.043
 Chu+0.042
Neg logit contributions
Story-0.048
ylan-0.047
 Brist-0.046
kok-0.045
 Kyr-0.043
Token.
Token ID13
Feature activation-3.63e-03

Pos logit contributions
Story+0.086
ylan+0.085
 Brist+0.083
kok+0.080
 Kyr+0.077
Neg logit contributions
Pope-0.092
angel-0.085
 Towards-0.073
 Deng-0.072
 Chu-0.070
Token Add
Token ID3060
Feature activation-8.98e-02

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.002
 saddle+0.002
Neg logit contributions
Pope-0.003
angel-0.003
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token more
Token ID517
Feature activation-5.84e-02

Pos logit contributions
Story+0.066
ylan+0.065
 Brist+0.064
kok+0.062
 Kyr+0.059
Neg logit contributions
Pope-0.073
angel-0.068
 Towards-0.058
 Deng-0.058
 Chu-0.057
Token jun
Token ID10891
Feature activation+1.84e-02

Pos logit contributions
Story+0.029
ylan+0.029
 Brist+0.028
kok+0.026
 Kyr+0.024
Neg logit contributions
Pope-0.062
angel-0.058
 Towards-0.052
 Deng-0.051
 Chu-0.051
Tokeniper
Token ID9346
Feature activation-4.92e-01

Pos logit contributions
Pope+0.026
angel+0.025
 Towards+0.023
 Deng+0.022
atum+0.022
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.002
kok-0.002
 Kyr-0.001
Token infusion
Token ID35547
Feature activation-8.28e-02

Pos logit contributions
Story+0.363
ylan+0.360
 Brist+0.354
kok+0.341
 Kyr+0.326
Neg logit contributions
Pope-0.400
angel-0.370
 Towards-0.316
 Deng-0.312
 Chu-0.306
Token if
Token ID611
Feature activation+1.05e-01

Pos logit contributions
Story+0.062
ylan+0.061
 Brist+0.060
kok+0.058
 Kyr+0.056
Neg logit contributions
Pope-0.066
angel-0.062
 Towards-0.052
 Deng-0.052
 Chu-0.051
Token necessary
Token ID3306
Feature activation+6.13e-03

Pos logit contributions
Pope+0.084
angel+0.077
 Towards+0.066
 Deng+0.065
 Chu+0.063
Neg logit contributions
Story-0.079
ylan-0.078
 Brist-0.077
kok-0.074
 Kyr-0.071
Token.
Token ID13
Feature activation-5.39e-03

Pos logit contributions
Pope+0.005
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.004
kok-0.004
 Kyr-0.004
Token Leave
Token ID17446
Feature activation-2.09e-01

Pos logit contributions
Story+0.004
ylan+0.004
 Brist+0.004
kok+0.004
 Kyr+0.004
Neg logit contributions
Pope-0.004
angel-0.004
 Towards-0.004
 Deng-0.003
 Chu-0.003
Token
Token ID198
Feature activation+1.96e-04

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
TokenIt
Token ID1026
Feature activation-9.98e-03

Pos logit contributions
Pope+0.000
angel+0.000
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.000
ylan-0.000
 Brist-0.000
kok-0.000
 Kyr-0.000
Token would
Token ID561
Feature activation-1.49e-02

Pos logit contributions
Story+0.007
ylan+0.007
 Brist+0.007
kok+0.007
 Kyr+0.007
Neg logit contributions
Pope-0.008
angel-0.008
 Towards-0.006
 Deng-0.006
 Chu-0.006
Token be
Token ID307
Feature activation-1.48e-03

Pos logit contributions
Story+0.011
ylan+0.011
 Brist+0.011
kok+0.010
 Kyr+0.010
Neg logit contributions
Pope-0.012
angel-0.011
 Towards-0.009
 Deng-0.009
 Chu-0.009
Token dis
Token ID595
Feature activation+5.71e-02

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Tokenpir
Token ID4063
Feature activation-4.89e-01

Pos logit contributions
Pope+0.062
angel+0.059
 Towards+0.053
 Deng+0.052
 Chu+0.052
Neg logit contributions
Story-0.026
ylan-0.026
 Brist-0.025
kok-0.023
 Kyr-0.022
Tokeniting
Token ID1780
Feature activation+3.03e-02

Pos logit contributions
Story+0.384
ylan+0.381
 Brist+0.375
kok+0.362
 Kyr+0.347
Neg logit contributions
Pope-0.374
angel-0.345
 Towards-0.291
 Deng-0.287
 Chu-0.281
Token if
Token ID611
Feature activation+1.04e-01

Pos logit contributions
Pope+0.023
angel+0.021
 Towards+0.018
 Deng+0.017
 Chu+0.017
Neg logit contributions
Story-0.024
ylan-0.024
 Brist-0.024
kok-0.023
 Kyr-0.022
Token the
Token ID262
Feature activation+6.73e-04

Pos logit contributions
Pope+0.082
angel+0.076
 Towards+0.064
 Deng+0.064
 Chu+0.062
Neg logit contributions
Story-0.080
ylan-0.079
 Brist-0.078
kok-0.075
 Kyr-0.072
Token book
Token ID1492
Feature activation+1.70e-01

Pos logit contributions
Pope+0.001
angel+0.000
 Towards+0.000
 Deng+0.000
atum+0.000
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.000
 Kyr-0.000
Token came
Token ID1625
Feature activation+1.69e-01

Pos logit contributions
Pope+0.138
angel+0.128
 Towards+0.109
 Deng+0.108
 Chu+0.106
Neg logit contributions
Story-0.125
ylan-0.124
 Brist-0.122
kok-0.117
 Kyr-0.112
Token dip
Token ID19550
Feature activation-2.26e-01

Pos logit contributions
Story+0.004
ylan+0.004
 Brist+0.004
kok+0.004
 saddle+0.003
Neg logit contributions
Pope-0.005
angel-0.004
 Towards-0.004
 Deng-0.004
 Chu-0.003
Token these
Token ID777
Feature activation+3.40e-02

Pos logit contributions
Story+0.166
ylan+0.165
 Brist+0.162
kok+0.156
 Kyr+0.149
Neg logit contributions
Pope-0.184
angel-0.170
 Towards-0.145
 Deng-0.144
 Chu-0.141
Token in
Token ID287
Feature activation-5.80e-03

Pos logit contributions
Pope+0.027
angel+0.025
 Towards+0.022
 Deng+0.021
 Chu+0.021
Neg logit contributions
Story-0.025
ylan-0.025
 Brist-0.025
kok-0.024
 Kyr-0.023
Token boiling
Token ID24372
Feature activation+1.62e-02

Pos logit contributions
Story+0.004
ylan+0.004
 Brist+0.004
kok+0.004
 Kyr+0.004
Neg logit contributions
Pope-0.005
angel-0.004
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token jun
Token ID10891
Feature activation+2.05e-02

Pos logit contributions
Pope+0.016
angel+0.015
 Towards+0.013
 Deng+0.013
 Chu+0.013
Neg logit contributions
Story-0.009
ylan-0.009
 Brist-0.009
kok-0.009
earch-0.008
Tokeniper
Token ID9346
Feature activation-4.88e-01

Pos logit contributions
Pope+0.028
angel+0.028
 Towards+0.025
 Deng+0.025
atum+0.025
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.002
 Afgh-0.002
Token infusion
Token ID35547
Feature activation-7.55e-02

Pos logit contributions
Story+0.321
ylan+0.317
 Brist+0.310
kok+0.299
 Kyr+0.284
Neg logit contributions
Pope-0.435
angel-0.408
 Towards-0.353
 Deng-0.349
atum-0.344
Token first
Token ID717
Feature activation+8.26e-02

Pos logit contributions
Story+0.057
ylan+0.056
 Brist+0.055
kok+0.054
 Kyr+0.051
Neg logit contributions
Pope-0.060
angel-0.056
 Towards-0.047
 Deng-0.047
 Chu-0.046
Token.)
Token ID2014
Feature activation+8.37e-02

Pos logit contributions
Pope+0.063
angel+0.058
 Towards+0.049
 Deng+0.048
 Chu+0.047
Neg logit contributions
Story-0.065
ylan-0.064
 Brist-0.063
kok-0.061
 Kyr-0.059
Token Transfer
Token ID20558
Feature activation-5.40e-02

Pos logit contributions
Pope+0.068
angel+0.063
 Towards+0.054
 Deng+0.054
 Chu+0.053
Neg logit contributions
Story-0.061
ylan-0.061
 Brist-0.060
kok-0.057
 Kyr-0.055
Token the
Token ID262
Feature activation+3.80e-04

Pos logit contributions
Story+0.039
ylan+0.039
 Brist+0.038
kok+0.037
 Kyr+0.035
Neg logit contributions
Pope-0.044
angel-0.041
 Towards-0.035
 Deng-0.035
 Chu-0.034
Token chief
Token ID4039
Feature activation+1.44e-01

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
atum-0.001
Token forest
Token ID8222
Feature activation+2.13e-01

Pos logit contributions
Pope+0.109
angel+0.101
 Towards+0.085
 Deng+0.083
atum+0.082
Neg logit contributions
Story-0.114
ylan-0.112
 Brist-0.111
kok-0.107
 Kyr-0.103
Token official
Token ID1743
Feature activation+1.55e-03

Pos logit contributions
Pope+0.178
angel+0.164
 Towards+0.141
 Deng+0.138
atum+0.136
Neg logit contributions
Story-0.153
ylan-0.152
 Brist-0.149
kok-0.143
 Kyr-0.137
Token of
Token ID286
Feature activation+3.99e-03

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token the
Token ID262
Feature activation-7.38e-04

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
Token Sund
Token ID3309
Feature activation+2.92e-01

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.000
 Deng-0.000
atum-0.000
Tokenarb
Token ID38039
Feature activation-2.72e-01

Pos logit contributions
Pope+0.332
angel+0.314
 Towards+0.282
 Deng+0.280
 Chu+0.276
Neg logit contributions
Story-0.121
ylan-0.119
 Brist-0.115
kok-0.107
 Kyr-0.099
Tokenans
Token ID504
Feature activation+5.80e-02

Pos logit contributions
Story+0.216
ylan+0.214
 Brist+0.210
kok+0.204
 Kyr+0.195
Neg logit contributions
Pope-0.206
angel-0.188
 Towards-0.159
 Deng-0.157
 Chu-0.154
Token in
Token ID287
Feature activation-3.35e-03

Pos logit contributions
Pope+0.045
angel+0.042
 Towards+0.035
 Deng+0.035
atum+0.034
Neg logit contributions
Story-0.045
ylan-0.044
 Brist-0.044
kok-0.042
 Kyr-0.040
Token Bangladesh
Token ID19483
Feature activation+1.16e-01

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.003
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token,
Token ID11
Feature activation+7.68e-03

Pos logit contributions
Pope+0.094
angel+0.087
 Towards+0.074
 Deng+0.073
 Chu+0.072
Neg logit contributions
Story-0.086
ylan-0.085
 Brist-0.084
kok-0.081
 Kyr-0.077
Token poor
Token ID3595
Feature activation+1.24e-01

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token health
Token ID1535
Feature activation+3.81e-02

Pos logit contributions
Pope+0.103
angel+0.095
 Towards+0.082
 Deng+0.081
 Chu+0.079
Neg logit contributions
Story-0.090
ylan-0.089
 Brist-0.087
kok-0.084
 Kyr-0.080
Token or
Token ID393
Feature activation-6.80e-02

Pos logit contributions
Pope+0.031
angel+0.028
 Towards+0.024
 Deng+0.024
 Chu+0.023
Neg logit contributions
Story-0.028
ylan-0.028
 Brist-0.028
kok-0.027
 Kyr-0.026
Token suffering
Token ID7195
Feature activation-1.30e-02

Pos logit contributions
Story+0.051
ylan+0.050
 Brist+0.050
kok+0.048
 saddle+0.046
Neg logit contributions
Pope-0.054
angel-0.050
 Towards-0.043
 Deng-0.042
atum-0.041
Token from
Token ID422
Feature activation-9.85e-03

Pos logit contributions
Story+0.009
ylan+0.009
 Brist+0.009
kok+0.009
 saddle+0.008
Neg logit contributions
Pope-0.011
angel-0.010
 Towards-0.008
 Deng-0.008
atum-0.008
Token burn
Token ID4245
Feature activation+2.98e-01

Pos logit contributions
Story+0.008
ylan+0.008
 Brist+0.008
kok+0.007
 saddle+0.007
Neg logit contributions
Pope-0.007
angel-0.007
 Towards-0.006
 Deng-0.006
atum-0.006
Tokenout
Token ID448
Feature activation+1.22e-01

Pos logit contributions
Pope+0.194
angel+0.176
 Towards+0.143
 Deng+0.140
 Chu+0.137
Neg logit contributions
Story-0.268
ylan-0.265
 Brist-0.261
kok-0.254
 saddle-0.245
Token retire
Token ID8058
Feature activation-5.49e-02

Pos logit contributions
Pope+0.098
angel+0.091
 Towards+0.077
 Deng+0.076
 Chu+0.075
Neg logit contributions
Story-0.091
ylan-0.090
 Brist-0.088
kok-0.085
 saddle-0.082
Token early
Token ID1903
Feature activation+3.14e-01

Pos logit contributions
Story+0.047
ylan+0.046
 Brist+0.046
kok+0.044
 Kyr+0.042
Neg logit contributions
Pope-0.039
angel-0.035
 Towards-0.029
 Deng-0.029
 Chu-0.028
Token while
Token ID981
Feature activation-1.42e-02

Pos logit contributions
Pope+0.245
angel+0.228
 Towards+0.192
 Deng+0.191
 Chu+0.186
Neg logit contributions
Story-0.240
ylan-0.239
 Brist-0.234
kok-0.226
 Kyr-0.216
Token those
Token ID883
Feature activation+9.81e-02

Pos logit contributions
Story+0.011
ylan+0.011
 Brist+0.011
kok+0.010
 Kyr+0.010
Neg logit contributions
Pope-0.011
angel-0.010
 Towards-0.009
 Deng-0.009
 Chu-0.009
Token up
Token ID510
Feature activation-1.88e-01

Pos logit contributions
Story+0.033
ylan+0.032
 Brist+0.032
kok+0.030
 Kyr+0.028
Neg logit contributions
Pope-0.062
angel-0.058
 Towards-0.051
 Deng-0.051
 Chu-0.050
Token more
Token ID517
Feature activation-4.99e-02

Pos logit contributions
Story+0.135
ylan+0.133
 Brist+0.131
kok+0.126
 Kyr+0.121
Neg logit contributions
Pope-0.157
angel-0.146
 Towards-0.125
 Deng-0.123
atum-0.121
Token or
Token ID393
Feature activation-5.86e-02

Pos logit contributions
Story+0.035
ylan+0.034
 Brist+0.034
kok+0.032
 Kyr+0.031
Neg logit contributions
Pope-0.043
angel-0.040
 Towards-0.034
 Deng-0.034
atum-0.033
Token less
Token ID1342
Feature activation+2.81e-02

Pos logit contributions
Story+0.045
ylan+0.045
 Brist+0.044
kok+0.042
 Kyr+0.041
Neg logit contributions
Pope-0.046
angel-0.042
 Towards-0.036
 Deng-0.035
 Chu-0.035
Token mirror
Token ID10162
Feature activation+1.55e-01

Pos logit contributions
Pope+0.023
angel+0.022
 Towards+0.019
 Deng+0.018
atum+0.018
Neg logit contributions
Story-0.020
ylan-0.020
 Brist-0.020
kok-0.019
 Kyr-0.018
Tokening
Token ID278
Feature activation+3.25e-01

Pos logit contributions
Pope+0.068
angel+0.059
 Towards+0.042
 Deng+0.041
 Chu+0.039
Neg logit contributions
Story-0.172
ylan-0.171
 Brist-0.169
kok-0.165
 Kyr-0.161
Token the
Token ID262
Feature activation+4.07e-03

Pos logit contributions
Pope+0.264
angel+0.245
 Towards+0.208
 Deng+0.206
atum+0.202
Neg logit contributions
Story-0.239
ylan-0.237
 Brist-0.234
kok-0.224
 Kyr-0.216
Token Rab
Token ID28559
Feature activation+5.65e-02

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.003
 Deng+0.003
atum+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
Tokenid
Token ID312
Feature activation-3.12e-01

Pos logit contributions
Pope+0.047
angel+0.044
 Towards+0.037
 Deng+0.037
 Chu+0.036
Neg logit contributions
Story-0.041
ylan-0.040
 Brist-0.039
kok-0.038
 Kyr-0.036
Token Pupp
Token ID20926
Feature activation-1.08e-01

Pos logit contributions
Story+0.196
ylan+0.193
 Brist+0.189
kok+0.180
 Kyr+0.172
Neg logit contributions
Pope-0.288
angel-0.269
 Towards-0.235
 Deng-0.232
 Chu-0.228
Tokenies
Token ID444
Feature activation+2.41e-01

Pos logit contributions
Story+0.105
ylan+0.105
 Brist+0.102
kok+0.100
 saddle+0.097
Neg logit contributions
Pope-0.063
angel-0.056
 Towards-0.044
 Deng-0.044
 Chu-0.041
Token may
Token ID743
Feature activation-1.42e-02

Pos logit contributions
Pope+0.064
angel+0.059
 Towards+0.050
 Deng+0.049
atum+0.049
Neg logit contributions
Story-0.060
ylan-0.059
 Brist-0.058
kok-0.056
 Kyr-0.053
Token not
Token ID407
Feature activation+5.00e-02

Pos logit contributions
Story+0.011
ylan+0.010
 Brist+0.010
kok+0.010
 Kyr+0.009
Neg logit contributions
Pope-0.012
angel-0.011
 Towards-0.009
 Deng-0.009
 Chu-0.009
Token be
Token ID307
Feature activation-3.66e-03

Pos logit contributions
Pope+0.041
angel+0.038
 Towards+0.032
 Deng+0.032
 Chu+0.031
Neg logit contributions
Story-0.037
ylan-0.037
 Brist-0.036
kok-0.035
 Kyr-0.033
Token that
Token ID326
Feature activation-2.57e-02

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.003
 Kyr+0.002
Neg logit contributions
Pope-0.003
angel-0.003
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token young
Token ID1862
Feature activation+1.28e-01

Pos logit contributions
Story+0.019
ylan+0.019
 Brist+0.018
kok+0.018
 Kyr+0.017
Neg logit contributions
Pope-0.021
angel-0.020
 Towards-0.017
 Deng-0.016
atum-0.016
Token evangelicals
Token ID44881
Feature activation+4.43e-01

Pos logit contributions
Pope+0.078
angel+0.071
 Towards+0.057
 Deng+0.056
 Chu+0.054
Neg logit contributions
Story-0.120
ylan-0.119
 Brist-0.117
kok-0.114
 Kyr-0.110
Token are
Token ID389
Feature activation+1.49e-02

Pos logit contributions
Pope+0.352
angel+0.327
 Towards+0.276
 Deng+0.273
 Chu+0.268
Neg logit contributions
Story-0.335
ylan-0.332
 Brist-0.327
kok-0.315
 Kyr-0.302
Token abandoning
Token ID31309
Feature activation-1.38e-02

Pos logit contributions
Pope+0.012
angel+0.011
 Towards+0.010
 Deng+0.010
 Chu+0.009
Neg logit contributions
Story-0.011
ylan-0.011
 Brist-0.011
kok-0.010
 Kyr-0.010
Token their
Token ID511
Feature activation+1.52e-02

Pos logit contributions
Story+0.010
ylan+0.010
 Brist+0.010
kok+0.010
 Kyr+0.009
Neg logit contributions
Pope-0.011
angel-0.010
 Towards-0.009
 Deng-0.008
atum-0.008
Token faith
Token ID4562
Feature activation-4.97e-02

Pos logit contributions
Pope+0.013
angel+0.012
 Towards+0.010
 Deng+0.010
 Chu+0.010
Neg logit contributions
Story-0.011
ylan-0.011
 Brist-0.011
kok-0.010
 Kyr-0.010
Token,
Token ID11
Feature activation-3.18e-03

Pos logit contributions
Story+0.038
ylan+0.037
 Brist+0.037
kok+0.035
 Kyr+0.034
Neg logit contributions
Pope-0.039
angel-0.036
 Towards-0.031
 Deng-0.030
 Chu-0.030
Token and
Token ID290
Feature activation+1.65e-03

Pos logit contributions
Story+0.000
ylan+0.000
 Brist+0.000
kok+0.000
 Kyr+0.000
Neg logit contributions
Pope-0.000
angel-0.000
 Towards-0.000
 Deng-0.000
 Chu-0.000
Token we
Token ID356
Feature activation+8.98e-03

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token went
Token ID1816
Feature activation+1.31e-01

Pos logit contributions
Pope+0.007
angel+0.007
 Towards+0.006
 Deng+0.006
 Chu+0.005
Neg logit contributions
Story-0.007
ylan-0.007
 Brist-0.007
kok-0.006
 Kyr-0.006
Token to
Token ID284
Feature activation-6.27e-03

Pos logit contributions
Pope+0.104
angel+0.097
 Towards+0.082
 Deng+0.081
 Chu+0.080
Neg logit contributions
Story-0.098
ylan-0.098
 Brist-0.096
kok-0.092
 Kyr-0.088
Token his
Token ID465
Feature activation+1.82e-02

Pos logit contributions
Story+0.005
ylan+0.005
 Brist+0.005
kok+0.005
 Kyr+0.005
Neg logit contributions
Pope-0.005
angel-0.004
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token home
Token ID1363
Feature activation+2.96e-01

Pos logit contributions
Pope+0.013
angel+0.012
 Towards+0.009
 Deng+0.009
 Chu+0.009
Neg logit contributions
Story-0.016
ylan-0.016
 Brist-0.015
kok-0.015
 Kyr-0.014
Token.
Token ID13
Feature activation-4.53e-03

Pos logit contributions
Pope+0.234
angel+0.217
 Towards+0.183
 Deng+0.181
 Chu+0.178
Neg logit contributions
Story-0.225
ylan-0.223
 Brist-0.219
kok-0.211
 Kyr-0.202
Token We
Token ID775
Feature activation+4.79e-02

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.003
 Kyr+0.003
Neg logit contributions
Pope-0.004
angel-0.003
 Towards-0.003
 Deng-0.003
 Chu-0.003
Token went
Token ID1816
Feature activation+1.30e-01

Pos logit contributions
Pope+0.039
angel+0.036
 Towards+0.031
 Deng+0.030
 Chu+0.030
Neg logit contributions
Story-0.035
ylan-0.035
 Brist-0.035
kok-0.033
 Kyr-0.032
Token to
Token ID284
Feature activation-2.62e-03

Pos logit contributions
Pope+0.102
angel+0.095
 Towards+0.080
 Deng+0.079
 Chu+0.078
Neg logit contributions
Story-0.099
ylan-0.098
 Brist-0.096
kok-0.093
 Kyr-0.089
Token a
Token ID257
Feature activation+2.99e-03

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token oil
Token ID3056
Feature activation-2.35e-01

Pos logit contributions
Pope+0.048
angel+0.045
 Towards+0.038
 Deng+0.037
 Chu+0.037
Neg logit contributions
Story-0.046
ylan-0.045
 Brist-0.044
kok-0.043
 Kyr-0.041
Token company
Token ID1664
Feature activation-8.57e-03

Pos logit contributions
Story+0.163
ylan+0.161
 Brist+0.158
kok+0.152
 Kyr+0.145
Neg logit contributions
Pope-0.201
angel-0.187
 Towards-0.161
 Deng-0.159
 Chu-0.156
Token Petro
Token ID36863
Feature activation+6.29e-02

Pos logit contributions
Story+0.007
ylan+0.007
 Brist+0.007
kok+0.006
 Kyr+0.006
Neg logit contributions
Pope-0.007
angel-0.006
 Towards-0.005
 Deng-0.005
 Chu-0.005
Tokenbr
Token ID1671
Feature activation-1.42e-01

Pos logit contributions
Pope+0.061
angel+0.057
 Towards+0.050
 Deng+0.050
 Chu+0.049
Neg logit contributions
Story-0.036
ylan-0.036
 Brist-0.035
kok-0.034
 Kyr-0.032
Tokenas
Token ID292
Feature activation-1.81e-02

Pos logit contributions
ylan+0.099
Story+0.098
 Brist+0.094
kok+0.092
earch+0.087
Neg logit contributions
Pope-0.122
angel-0.112
 Towards-0.099
 Deng-0.097
 Chu-0.095
Token.
Token ID13
Feature activation-2.61e-03

Pos logit contributions
Story+0.014
ylan+0.013
 Brist+0.013
kok+0.013
 Kyr+0.012
Neg logit contributions
Pope-0.014
angel-0.013
 Towards-0.011
 Deng-0.011
 Chu-0.011
Token
Token ID198
Feature activation+4.03e-03

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token
Token ID198
Feature activation+4.44e-03

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.003
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
TokenThe
Token ID464
Feature activation+1.44e-02

Pos logit contributions
Pope+0.004
angel+0.003
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 Kyr-0.003
Token arms
Token ID5101
Feature activation+8.08e-02

Pos logit contributions
Pope+0.012
angel+0.011
 Towards+0.009
 Deng+0.009
 Chu+0.009
Neg logit contributions
Story-0.011
ylan-0.011
 Brist-0.011
kok-0.010
 Kyr-0.010
Token dealer
Token ID16456
Feature activation-5.25e-02

Pos logit contributions
Pope+0.054
angel+0.049
 Towards+0.040
 Deng+0.039
 Chu+0.038
Neg logit contributions
Story-0.072
ylan-0.071
 Brist-0.070
kok-0.068
 Kyr-0.066
Token 1982
Token ID14489
Feature activation-9.38e-03

Pos logit contributions
Pope+0.041
angel+0.039
 Towards+0.034
 Deng+0.033
 Chu+0.033
Neg logit contributions
Story-0.029
ylan-0.028
 Brist-0.028
kok-0.026
 saddle-0.025
Token V
Token ID569
Feature activation+1.55e-01

Pos logit contributions
Story+0.008
ylan+0.008
 Brist+0.008
kok+0.008
 saddle+0.008
Neg logit contributions
Pope-0.006
angel-0.006
 Towards-0.005
 Deng-0.004
 Chu-0.004
Tokenitus
Token ID17506
Feature activation+2.50e-01

Pos logit contributions
Pope+0.085
angel+0.075
 Towards+0.058
 Deng+0.057
 Chu+0.055
Neg logit contributions
Story-0.156
ylan-0.155
 Brist-0.153
kok-0.149
 Kyr-0.144
Token road
Token ID2975
Feature activation+1.74e-01

Pos logit contributions
Pope+0.207
angel+0.192
 Towards+0.164
 Deng+0.162
 Chu+0.159
Neg logit contributions
Story-0.182
ylan-0.180
 Brist-0.177
kok-0.170
 Kyr-0.163
Token bike
Token ID7161
Feature activation-1.56e-01

Pos logit contributions
Pope+0.172
angel+0.162
 Towards+0.142
 Deng+0.141
 Chu+0.139
Neg logit contributions
Story-0.098
ylan-0.097
 Brist-0.094
kok-0.090
 Kyr-0.084
Token.
Token ID13
Feature activation-3.06e-03

Pos logit contributions
Story+0.117
ylan+0.116
 Brist+0.114
kok+0.110
 Kyr+0.106
Neg logit contributions
Pope-0.124
angel-0.115
 Towards-0.098
 Deng-0.097
 Chu-0.095
Token
Token ID198
Feature activation+5.75e-03

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 saddle+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token
Token ID198
Feature activation+4.66e-03

Pos logit contributions
Pope+0.005
angel+0.004
 Towards+0.004
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
TokenGl
Token ID9861
Feature activation-2.78e-02

Pos logit contributions
Pope+0.004
angel+0.003
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.003
kok-0.003
 Kyr-0.003
Tokenenn
Token ID1697
Feature activation-9.72e-02

Pos logit contributions
Story+0.018
ylan+0.017
 Brist+0.017
kok+0.016
 Kyr+0.016
Neg logit contributions
Pope-0.026
angel-0.024
 Towards-0.021
 Deng-0.021
atum-0.020
Token,
Token ID11
Feature activation+8.38e-03

Pos logit contributions
Story+0.070
ylan+0.070
 Brist+0.068
kok+0.066
 Kyr+0.063
Neg logit contributions
Pope-0.080
angel-0.075
 Towards-0.064
 Deng-0.063
 Chu-0.062
Token beings
Token ID9791
Feature activation-7.38e-02

Pos logit contributions
Story+0.028
ylan+0.028
 Brist+0.027
kok+0.026
 Kyr+0.025
Neg logit contributions
Pope-0.032
angel-0.029
 Towards-0.025
 Deng-0.025
 Chu-0.024
Token possess
Token ID8588
Feature activation+6.43e-02

Pos logit contributions
Story+0.056
ylan+0.055
 Brist+0.054
kok+0.052
 saddle+0.050
Neg logit contributions
Pope-0.059
angel-0.055
 Towards-0.046
 Deng-0.046
 Chu-0.045
Token reason
Token ID1738
Feature activation+1.93e-01

Pos logit contributions
Pope+0.052
angel+0.048
 Towards+0.041
 Deng+0.040
atum+0.039
Neg logit contributions
Story-0.048
ylan-0.048
 Brist-0.047
kok-0.045
 saddle-0.043
Token in
Token ID287
Feature activation-1.14e-02

Pos logit contributions
Pope+0.155
angel+0.143
 Towards+0.122
 Deng+0.120
 Chu+0.118
Neg logit contributions
Story-0.144
ylan-0.143
 Brist-0.140
kok-0.135
 Kyr-0.129
Token equal
Token ID4961
Feature activation-1.41e-02

Pos logit contributions
Story+0.009
ylan+0.009
 Brist+0.009
kok+0.009
 Kyr+0.008
Neg logit contributions
Pope-0.009
angel-0.008
 Towards-0.007
 Deng-0.007
atum-0.006
Token measure
Token ID3953
Feature activation+2.11e-01

Pos logit contributions
Story+0.014
ylan+0.014
 Brist+0.013
kok+0.013
 Kyr+0.013
Neg logit contributions
Pope-0.008
angel-0.007
 Towards-0.006
 Deng-0.006
 Chu-0.005
Token,
Token ID11
Feature activation+4.02e-03

Pos logit contributions
Pope+0.169
angel+0.156
 Towards+0.133
 Deng+0.131
 Chu+0.128
Neg logit contributions
Story-0.159
ylan-0.157
 Brist-0.154
kok-0.149
 Kyr-0.142
Token Hume
Token ID45485
Feature activation+1.35e-02

Pos logit contributions
Pope+0.003
angel+0.003
 Towards+0.003
 Deng+0.003
 Chu+0.002
Neg logit contributions
Story-0.003
ylan-0.003
 Brist-0.003
kok-0.003
 saddle-0.003
Token's
Token ID338
Feature activation-3.33e-02

Pos logit contributions
Pope+0.012
angel+0.011
 Towards+0.009
 Deng+0.009
 Chu+0.009
Neg logit contributions
Story-0.009
ylan-0.009
 Brist-0.009
kok-0.009
 Kyr-0.008
Token endorsement
Token ID17819
Feature activation+7.40e-02

Pos logit contributions
Story+0.025
ylan+0.024
 Brist+0.024
kok+0.023
 saddle+0.022
Neg logit contributions
Pope-0.027
angel-0.025
 Towards-0.021
 Deng-0.021
 Chu-0.021
Token of
Token ID286
Feature activation+2.36e-03

Pos logit contributions
Pope+0.059
angel+0.054
 Towards+0.046
 Deng+0.045
 Chu+0.044
Neg logit contributions
Story-0.056
ylan-0.055
 Brist-0.055
kok-0.053
 Kyr-0.050
Token we
Token ID356
Feature activation+4.92e-03

Pos logit contributions
Story+0.018
ylan+0.018
 Brist+0.018
kok+0.017
 Kyr+0.017
Neg logit contributions
Pope-0.019
angel-0.017
 Towards-0.015
 Deng-0.014
atum-0.014
Token had
Token ID550
Feature activation+2.45e-02

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.003
kok-0.003
 Kyr-0.003
Token reached
Token ID4251
Feature activation-1.27e-03

Pos logit contributions
Pope+0.020
angel+0.019
 Towards+0.016
 Deng+0.015
atum+0.015
Neg logit contributions
Story-0.018
ylan-0.018
 Brist-0.018
kok-0.017
 Kyr-0.016
Token the
Token ID262
Feature activation-2.45e-03

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
atum-0.001
Token final
Token ID2457
Feature activation-5.70e-02

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
atum-0.002
Token part
Token ID636
Feature activation+2.36e-01

Pos logit contributions
Story+0.044
ylan+0.043
 Brist+0.043
kok+0.041
 saddle+0.040
Neg logit contributions
Pope-0.045
angel-0.041
 Towards-0.035
 Deng-0.034
atum-0.034
Token of
Token ID286
Feature activation+8.23e-03

Pos logit contributions
Pope+0.186
angel+0.172
 Towards+0.146
 Deng+0.144
 Chu+0.141
Neg logit contributions
Story-0.180
ylan-0.178
 Brist-0.175
kok-0.169
 Kyr-0.162
Token the
Token ID262
Feature activation-2.96e-03

Pos logit contributions
Pope+0.007
angel+0.006
 Towards+0.005
 Deng+0.005
atum+0.005
Neg logit contributions
Story-0.006
ylan-0.006
 Brist-0.006
kok-0.006
 Kyr-0.005
Token process
Token ID1429
Feature activation-2.36e-03

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
atum-0.002
Token.
Token ID13
Feature activation+1.69e-03

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.001
atum-0.001
Token She
Token ID1375
Feature activation+3.00e-02

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
atum+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token if
Token ID611
Feature activation+1.06e-01

Pos logit contributions
Pope+0.025
angel+0.023
 Towards+0.020
 Deng+0.019
 Chu+0.019
Neg logit contributions
Story-0.026
ylan-0.026
 Brist-0.025
kok-0.024
 Kyr-0.023
Token I
Token ID314
Feature activation-4.99e-03

Pos logit contributions
Pope+0.085
angel+0.079
 Towards+0.067
 Deng+0.066
 Chu+0.065
Neg logit contributions
Story-0.079
ylan-0.079
 Brist-0.077
kok-0.075
 Kyr-0.071
Token'm
Token ID1101
Feature activation-3.93e-02

Pos logit contributions
Story+0.004
ylan+0.004
 Brist+0.004
kok+0.003
 Kyr+0.003
Neg logit contributions
Pope-0.004
angel-0.004
 Towards-0.003
 Deng-0.003
 Chu-0.003
Token making
Token ID1642
Feature activation-2.36e-02

Pos logit contributions
Story+0.029
ylan+0.029
 Brist+0.029
kok+0.028
 Kyr+0.026
Neg logit contributions
Pope-0.031
angel-0.029
 Towards-0.025
 Deng-0.024
atum-0.024
Token news
Token ID1705
Feature activation-8.77e-02

Pos logit contributions
Story+0.017
ylan+0.017
 Brist+0.017
kok+0.016
 Kyr+0.016
Neg logit contributions
Pope-0.019
angel-0.018
 Towards-0.015
 Deng-0.015
atum-0.015
Token here
Token ID994
Feature activation+7.45e-02

Pos logit contributions
Story+0.064
ylan+0.063
 Brist+0.062
kok+0.060
 Kyr+0.057
Neg logit contributions
Pope-0.072
angel-0.067
 Towards-0.057
 Deng-0.056
atum-0.055
Token,"
Token ID553
Feature activation-6.41e-02

Pos logit contributions
Pope+0.062
angel+0.058
 Towards+0.050
 Deng+0.049
 Chu+0.048
Neg logit contributions
Story-0.053
ylan-0.053
 Brist-0.052
kok-0.050
 Kyr-0.048
Token National
Token ID2351
Feature activation+5.55e-02

Pos logit contributions
Story+0.048
ylan+0.047
 Brist+0.047
kok+0.045
 Kyr+0.043
Neg logit contributions
Pope-0.052
angel-0.048
 Towards-0.041
 Deng-0.040
atum-0.039
Token Review
Token ID6602
Feature activation+6.30e-02

Pos logit contributions
Pope+0.041
angel+0.038
 Towards+0.032
 Deng+0.031
 Chu+0.030
Neg logit contributions
Story-0.045
ylan-0.045
 Brist-0.044
kok-0.042
 Kyr-0.041
Token's
Token ID338
Feature activation-3.82e-02

Pos logit contributions
Pope+0.052
angel+0.048
 Towards+0.041
 Deng+0.041
atum+0.040
Neg logit contributions
Story-0.046
ylan-0.045
 Brist-0.045
kok-0.043
 Kyr-0.041
Token Jonah
Token ID45447
Feature activation-1.20e-01

Pos logit contributions
Story+0.028
ylan+0.028
 Brist+0.027
kok+0.026
 Kyr+0.025
Neg logit contributions
Pope-0.031
angel-0.029
 Towards-0.025
 Deng-0.025
 Chu-0.024
Token run
Token ID1057
Feature activation+7.55e-02

Pos logit contributions
Pope+0.013
angel+0.012
 Towards+0.010
 Deng+0.010
 Chu+0.010
Neg logit contributions
Story-0.013
ylan-0.012
 Brist-0.012
kok-0.012
 saddle-0.011
Token the
Token ID262
Feature activation+6.27e-04

Pos logit contributions
Pope+0.062
angel+0.057
 Towards+0.049
 Deng+0.048
 Chu+0.047
Neg logit contributions
Story-0.055
ylan-0.055
 Brist-0.054
kok-0.052
 Kyr-0.049
Token sl
Token ID1017
Feature activation-5.84e-02

Pos logit contributions
Pope+0.001
angel+0.000
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.000
ylan-0.000
 Brist-0.000
kok-0.000
 Kyr-0.000
Tokens
Token ID82
Feature activation+5.17e-03

Pos logit contributions
Story+0.043
ylan+0.043
 Brist+0.042
kok+0.041
 Kyr+0.039
Neg logit contributions
Pope-0.047
angel-0.044
 Towards-0.037
 Deng-0.037
 Chu-0.036
Token deploy
Token ID6061
Feature activation+1.95e-01

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
Token command
Token ID3141
Feature activation-6.77e-02

Pos logit contributions
Pope+0.169
angel+0.158
 Towards+0.136
 Deng+0.135
 Chu+0.132
Neg logit contributions
Story-0.132
ylan-0.131
 Brist-0.129
kok-0.123
 Kyr-0.118
Token,
Token ID11
Feature activation-8.32e-05

Pos logit contributions
Story+0.051
ylan+0.051
 Brist+0.050
kok+0.048
 Kyr+0.046
Neg logit contributions
Pope-0.054
angel-0.050
 Towards-0.042
 Deng-0.042
 Chu-0.041
Token the
Token ID262
Feature activation+3.16e-03

Pos logit contributions
Story+0.000
ylan+0.000
 Brist+0.000
kok+0.000
 Kyr+0.000
Neg logit contributions
Pope-0.000
angel-0.000
 Towards-0.000
 Deng-0.000
 Chu-0.000
Token following
Token ID1708
Feature activation+5.30e-02

Pos logit contributions
Pope+0.003
angel+0.002
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.002
Token things
Token ID1243
Feature activation-5.64e-02

Pos logit contributions
Pope+0.041
angel+0.038
 Towards+0.032
 Deng+0.031
 Chu+0.031
Neg logit contributions
Story-0.041
ylan-0.041
 Brist-0.040
kok-0.039
 Kyr-0.037
Token happen
Token ID1645
Feature activation+2.97e-02

Pos logit contributions
Story+0.042
ylan+0.042
 Brist+0.041
kok+0.040
 Kyr+0.038
Neg logit contributions
Pope-0.045
angel-0.042
 Towards-0.036
 Deng-0.035
 Chu-0.034
Token from
Token ID422
Feature activation-6.69e-03

Pos logit contributions
Pope+0.125
angel+0.116
 Towards+0.099
 Deng+0.098
 Chu+0.096
Neg logit contributions
Story-0.115
ylan-0.114
 Brist-0.112
kok-0.108
 Kyr-0.103
Token processes
Token ID7767
Feature activation+2.93e-02

Pos logit contributions
Story+0.005
ylan+0.005
 Brist+0.005
kok+0.005
 Kyr+0.005
Neg logit contributions
Pope-0.005
angel-0.005
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token in
Token ID287
Feature activation-2.99e-03

Pos logit contributions
Pope+0.023
angel+0.021
 Towards+0.018
 Deng+0.018
atum+0.017
Neg logit contributions
Story-0.022
ylan-0.022
 Brist-0.022
kok-0.021
 Kyr-0.020
Token the
Token ID262
Feature activation+3.04e-03

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
atum-0.002
Token planet
Token ID5440
Feature activation+1.86e-01

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.002
 Deng+0.002
atum+0.002
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 saddle-0.002
Token's
Token ID338
Feature activation-3.46e-02

Pos logit contributions
Pope+0.154
angel+0.144
 Towards+0.123
 Deng+0.122
 Chu+0.120
Neg logit contributions
Story-0.134
ylan-0.133
 Brist-0.131
kok-0.126
 Kyr-0.119
Token mantle
Token ID32107
Feature activation+4.39e-02

Pos logit contributions
Story+0.027
ylan+0.027
 Brist+0.026
kok+0.025
 saddle+0.024
Neg logit contributions
Pope-0.027
angel-0.025
 Towards-0.021
 Deng-0.020
 Chu-0.020
Token beneath
Token ID11061
Feature activation+5.11e-02

Pos logit contributions
Pope+0.036
angel+0.033
 Towards+0.028
 Deng+0.028
 Chu+0.027
Neg logit contributions
Story-0.033
ylan-0.032
 Brist-0.032
kok-0.030
 saddle-0.029
Token the
Token ID262
Feature activation+1.89e-03

Pos logit contributions
Pope+0.040
angel+0.037
 Towards+0.032
 Deng+0.031
 Chu+0.031
Neg logit contributions
Story-0.039
ylan-0.038
 Brist-0.038
kok-0.036
 Kyr-0.035
Token crust
Token ID20048
Feature activation-7.64e-02

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
atum+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 saddle-0.001
Token,
Token ID11
Feature activation+3.74e-03

Pos logit contributions
Story+0.057
ylan+0.056
 Brist+0.055
kok+0.053
 Kyr+0.051
Neg logit contributions
Pope-0.062
angel-0.057
 Towards-0.048
 Deng-0.048
 Chu-0.047
Token future
Token ID2003
Feature activation+9.34e-02

Pos logit contributions
Story+0.040
ylan+0.039
 Brist+0.039
kok+0.037
 Kyr+0.036
Neg logit contributions
Pope-0.042
angel-0.038
 Towards-0.033
 Deng-0.032
atum-0.032
Token husbands
Token ID27742
Feature activation+3.15e-01

Pos logit contributions
Pope+0.069
angel+0.063
 Towards+0.053
 Deng+0.052
atum+0.051
Neg logit contributions
Story-0.076
ylan-0.076
 Brist-0.074
kok-0.072
 Kyr-0.069
Token.
Token ID13
Feature activation-3.49e-03

Pos logit contributions
Pope+0.251
angel+0.232
 Towards+0.197
 Deng+0.195
 Chu+0.190
Neg logit contributions
Story-0.238
ylan-0.235
 Brist-0.231
kok-0.223
 Kyr-0.214
Token Then
Token ID3244
Feature activation-1.15e-01

Pos logit contributions
Story+0.003
ylan+0.003
 Brist+0.003
kok+0.003
 Kyr+0.002
Neg logit contributions
Pope-0.003
angel-0.003
 Towards-0.002
 Deng-0.002
atum-0.002
Token we
Token ID356
Feature activation+9.95e-03

Pos logit contributions
Story+0.087
ylan+0.086
 Brist+0.085
kok+0.081
 Kyr+0.078
Neg logit contributions
Pope-0.092
angel-0.085
 Towards-0.072
 Deng-0.071
atum-0.069
Token were
Token ID547
Feature activation-2.52e-02

Pos logit contributions
Pope+0.008
angel+0.007
 Towards+0.006
 Deng+0.006
 Chu+0.006
Neg logit contributions
Story-0.007
ylan-0.007
 Brist-0.007
kok-0.007
 Kyr-0.007
Token blind
Token ID7770
Feature activation+5.56e-02

Pos logit contributions
Story+0.017
ylan+0.017
 Brist+0.016
kok+0.016
 Kyr+0.015
Neg logit contributions
Pope-0.022
angel-0.021
 Towards-0.018
 Deng-0.018
 Chu-0.018
Tokenfold
Token ID11379
Feature activation-2.20e-02

Pos logit contributions
Pope+0.051
angel+0.048
 Towards+0.042
 Deng+0.041
 Chu+0.041
Neg logit contributions
Story-0.035
ylan-0.034
 Brist-0.034
kok-0.032
 Kyr-0.031
Tokened
Token ID276
Feature activation+3.00e-03

Pos logit contributions
Story+0.015
ylan+0.015
 Brist+0.015
kok+0.014
 Kyr+0.014
Neg logit contributions
Pope-0.019
angel-0.017
 Towards-0.015
 Deng-0.015
 Chu-0.014
Token.
Token ID13
Feature activation+1.36e-03

Pos logit contributions
Pope+0.002
angel+0.002
 Towards+0.002
 Deng+0.002
 Chu+0.002
Neg logit contributions
Story-0.002
ylan-0.002
 Brist-0.002
kok-0.002
 Kyr-0.002
Token
Token ID198
Feature activation+7.33e-03

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token he
Token ID339
Feature activation-3.16e-02

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.002
angel-0.002
 Towards-0.002
 Deng-0.002
 Chu-0.002
Token thinks
Token ID6834
Feature activation-4.32e-02

Pos logit contributions
Story+0.023
ylan+0.022
 Brist+0.022
kok+0.021
 Kyr+0.020
Neg logit contributions
Pope-0.026
angel-0.025
 Towards-0.021
 Deng-0.021
 Chu-0.020
Token interest
Token ID1393
Feature activation-1.55e-01

Pos logit contributions
Story+0.032
ylan+0.032
 Brist+0.031
kok+0.030
 Kyr+0.029
Neg logit contributions
Pope-0.035
angel-0.032
 Towards-0.027
 Deng-0.027
 Chu-0.026
Token will
Token ID481
Feature activation+1.68e-03

Pos logit contributions
Story+0.115
ylan+0.114
 Brist+0.112
kok+0.108
 Kyr+0.104
Neg logit contributions
Pope-0.124
angel-0.115
 Towards-0.098
 Deng-0.097
 Chu-0.095
Token rapidly
Token ID8902
Feature activation-2.84e-02

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 saddle-0.001
Token grow
Token ID1663
Feature activation-3.34e-02

Pos logit contributions
Story+0.019
ylan+0.019
 Brist+0.019
kok+0.018
 saddle+0.017
Neg logit contributions
Pope-0.025
angel-0.023
 Towards-0.020
 Deng-0.020
 Chu-0.019
Token in
Token ID287
Feature activation-7.11e-03

Pos logit contributions
Story+0.025
ylan+0.025
 Brist+0.025
kok+0.024
 Kyr+0.023
Neg logit contributions
Pope-0.027
angel-0.025
 Towards-0.021
 Deng-0.021
 Chu-0.020
Token the
Token ID262
Feature activation-6.37e-03

Pos logit contributions
Story+0.005
ylan+0.005
 Brist+0.005
kok+0.005
 Kyr+0.005
Neg logit contributions
Pope-0.006
angel-0.005
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token mainstream
Token ID8661
Feature activation-3.84e-02

Pos logit contributions
Story+0.005
ylan+0.005
 Brist+0.005
kok+0.005
 Kyr+0.005
Neg logit contributions
Pope-0.005
angel-0.004
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token world
Token ID995
Feature activation+8.22e-03

Pos logit contributions
Story+0.028
ylan+0.028
 Brist+0.028
kok+0.027
 Kyr+0.026
Neg logit contributions
Pope-0.031
angel-0.029
 Towards-0.024
 Deng-0.024
 Chu-0.024
Token.
Token ID13
Feature activation-5.65e-03

Pos logit contributions
Pope+0.007
angel+0.006
 Towards+0.005
 Deng+0.005
 Chu+0.005
Neg logit contributions
Story-0.006
ylan-0.006
 Brist-0.006
kok-0.006
 Kyr-0.006
Tokenutions
Token ID3508
Feature activation-1.11e-01

Pos logit contributions
Pope+0.055
angel+0.051
 Towards+0.044
 Deng+0.043
atum+0.043
Neg logit contributions
Story-0.042
ylan-0.042
 Brist-0.041
kok-0.039
 Kyr-0.037
Token
Token ID447
Feature activation+1.94e-03

Pos logit contributions
Story+0.084
ylan+0.083
 Brist+0.082
kok+0.079
 Kyr+0.075
Neg logit contributions
Pope-0.088
angel-0.082
 Towards-0.069
 Deng-0.069
 Chu-0.067
Token
Token ID251
Feature activation-6.18e-03

Pos logit contributions
Pope+0.002
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token does
Token ID857
Feature activation+6.97e-04

Pos logit contributions
Story+0.005
ylan+0.005
 Brist+0.005
kok+0.004
 Kyr+0.004
Neg logit contributions
Pope-0.005
angel-0.005
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token not
Token ID407
Feature activation+5.85e-02

Pos logit contributions
Pope+0.001
angel+0.000
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 saddle-0.001
Token reflect
Token ID4079
Feature activation-6.42e-02

Pos logit contributions
Pope+0.048
angel+0.045
 Towards+0.038
 Deng+0.038
 Chu+0.037
Neg logit contributions
Story-0.043
ylan-0.042
 Brist-0.041
kok-0.040
 saddle-0.038
Token a
Token ID257
Feature activation+6.35e-03

Pos logit contributions
Story+0.049
ylan+0.049
 Brist+0.048
kok+0.046
 Kyr+0.044
Neg logit contributions
Pope-0.050
angel-0.047
 Towards-0.039
 Deng-0.039
 Chu-0.038
Token belief
Token ID4901
Feature activation-1.11e-01

Pos logit contributions
Pope+0.005
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.004
 Kyr-0.004
Token that
Token ID326
Feature activation-2.56e-02

Pos logit contributions
Story+0.082
ylan+0.081
 Brist+0.080
kok+0.077
 Kyr+0.073
Neg logit contributions
Pope-0.090
angel-0.083
 Towards-0.071
 Deng-0.070
 Chu-0.069
Token he
Token ID339
Feature activation-2.36e-02

Pos logit contributions
Story+0.019
ylan+0.019
 Brist+0.019
kok+0.018
 Kyr+0.017
Neg logit contributions
Pope-0.021
angel-0.019
 Towards-0.016
 Deng-0.016
 Chu-0.016
Token never
Token ID1239
Feature activation-3.11e-02

Pos logit contributions
Story+0.017
ylan+0.017
 Brist+0.017
kok+0.016
 Kyr+0.015
Neg logit contributions
Pope-0.019
angel-0.018
 Towards-0.015
 Deng-0.015
 Chu-0.015
Token-
Token ID12
Feature activation-1.82e-02

Pos logit contributions
Story+0.045
ylan+0.045
 Brist+0.044
kok+0.043
 saddle+0.041
Neg logit contributions
Pope-0.052
angel-0.049
 Towards-0.042
 Deng-0.041
 Chu-0.041
Token150
Token ID8628
Feature activation+3.57e-02

Pos logit contributions
Story+0.014
ylan+0.014
 Brist+0.014
kok+0.014
 Kyr+0.013
Neg logit contributions
Pope-0.014
angel-0.013
 Towards-0.011
 Deng-0.011
 Chu-0.010
Token Eco
Token ID38719
Feature activation-7.00e-02

Pos logit contributions
Pope+0.030
angel+0.027
 Towards+0.024
 Deng+0.023
 Chu+0.023
Neg logit contributions
Story-0.026
ylan-0.026
 Brist-0.025
kok-0.024
 saddle-0.023
TokenBoost
Token ID45686
Feature activation-1.50e-02

Pos logit contributions
Story+0.050
ylan+0.049
 Brist+0.048
kok+0.046
 saddle+0.044
Neg logit contributions
Pope-0.059
angel-0.055
 Towards-0.047
 Deng-0.046
 Chu-0.046
Token Tort
Token ID28467
Feature activation-1.59e-01

Pos logit contributions
Story+0.011
ylan+0.011
 Brist+0.011
kok+0.011
 saddle+0.010
Neg logit contributions
Pope-0.012
angel-0.011
 Towards-0.009
 Deng-0.009
 Chu-0.009
Tokenure
Token ID495
Feature activation-3.27e-01

Pos logit contributions
Story+0.109
ylan+0.108
 Brist+0.106
kok+0.101
 saddle+0.096
Neg logit contributions
Pope-0.138
angel-0.129
 Towards-0.111
 Deng-0.110
 Chu-0.108
Token Test
Token ID6208
Feature activation-1.45e-01

Pos logit contributions
Story+0.247
ylan+0.242
 Brist+0.240
kok+0.229
 saddle+0.223
Neg logit contributions
Pope-0.261
angel-0.242
 Towards-0.203
 Deng-0.201
 Chu-0.198
Token truck
Token ID7779
Feature activation+5.18e-03

Pos logit contributions
Story+0.108
ylan+0.107
 Brist+0.106
kok+0.101
 saddle+0.098
Neg logit contributions
Pope-0.117
angel-0.108
 Towards-0.092
 Deng-0.091
 Chu-0.089
Token in
Token ID287
Feature activation-1.14e-02

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 saddle-0.003
Token the
Token ID262
Feature activation-6.84e-03

Pos logit contributions
Story+0.008
ylan+0.008
 Brist+0.008
kok+0.007
 Kyr+0.007
Neg logit contributions
Pope-0.010
angel-0.009
 Towards-0.008
 Deng-0.008
 Chu-0.008
Token 2010
Token ID3050
Feature activation-1.56e-01

Pos logit contributions
Story+0.005
ylan+0.005
 Brist+0.005
kok+0.005
 Kyr+0.004
Neg logit contributions
Pope-0.006
angel-0.005
 Towards-0.004
 Deng-0.004
 Chu-0.004
Token rankings
Token ID16905
Feature activation+3.64e-02

Pos logit contributions
Story+0.047
ylan+0.047
 Brist+0.046
kok+0.044
 Kyr+0.042
Neg logit contributions
Pope-0.051
angel-0.048
 Towards-0.040
 Deng-0.040
 Chu-0.039
Token.
Token ID13
Feature activation-3.12e-04

Pos logit contributions
Pope+0.029
angel+0.027
 Towards+0.023
 Deng+0.023
 Chu+0.022
Neg logit contributions
Story-0.027
ylan-0.027
 Brist-0.027
kok-0.026
 Kyr-0.024
Token
Token ID198
Feature activation+1.22e-02

Pos logit contributions
Story+0.000
ylan+0.000
 Brist+0.000
kok+0.000
 Kyr+0.000
Neg logit contributions
Pope-0.000
angel-0.000
 Towards-0.000
 Deng-0.000
 Chu-0.000
Token
Token ID198
Feature activation+5.28e-03

Pos logit contributions
Pope+0.010
angel+0.009
 Towards+0.008
 Deng+0.007
 Chu+0.007
Neg logit contributions
Story-0.009
ylan-0.009
 Brist-0.009
kok-0.009
 Kyr-0.008
TokenR
Token ID49
Feature activation-5.13e-02

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
TokenANK
Token ID15154
Feature activation-3.48e-01

Pos logit contributions
Story+0.037
ylan+0.037
 Brist+0.036
kok+0.034
 Kyr+0.033
Neg logit contributions
Pope-0.043
angel-0.040
 Towards-0.034
 Deng-0.034
 Chu-0.033
Token 1
Token ID352
Feature activation+9.55e-02

Pos logit contributions
Story+0.279
ylan+0.277
 Brist+0.273
kok+0.263
 Kyr+0.253
Neg logit contributions
Pope-0.261
angel-0.240
 Towards-0.201
 Deng-0.199
 Chu-0.194
Token Josh
Token ID8518
Feature activation-7.62e-02

Pos logit contributions
Pope+0.077
angel+0.071
 Towards+0.060
 Deng+0.060
 Chu+0.058
Neg logit contributions
Story-0.072
ylan-0.071
 Brist-0.070
kok-0.067
 Kyr-0.064
Token Norman
Token ID19636
Feature activation-1.12e-01

Pos logit contributions
Story+0.062
ylan+0.062
 Brist+0.061
kok+0.059
 Kyr+0.057
Neg logit contributions
Pope-0.055
angel-0.051
 Towards-0.042
 Deng-0.042
atum-0.041
Token,
Token ID11
Feature activation+1.48e-03

Pos logit contributions
Story+0.084
ylan+0.083
 Brist+0.082
kok+0.079
 Kyr+0.076
Neg logit contributions
Pope-0.089
angel-0.083
 Towards-0.070
 Deng-0.069
 Chu-0.068
Token Redskins
Token ID22038
Feature activation+7.90e-02

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
TokenAdvertisement
Token ID4723
Feature activation-1.30e-01

Pos logit contributions
Pope+0.005
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
Token Continue
Token ID10054
Feature activation-1.34e-01

Pos logit contributions
Story+0.076
ylan+0.076
 Brist+0.074
kok+0.071
 Kyr+0.067
Neg logit contributions
Pope-0.124
angel-0.117
 Towards-0.102
 Deng-0.101
 Chu-0.100
Token reading
Token ID3555
Feature activation-1.55e-02

Pos logit contributions
Story+0.100
ylan+0.099
 Brist+0.098
kok+0.094
 Kyr+0.090
Neg logit contributions
Pope-0.108
angel-0.100
 Towards-0.085
 Deng-0.084
 Chu-0.082
Token the
Token ID262
Feature activation+1.78e-03

Pos logit contributions
ylan+0.012
Story+0.012
 Brist+0.012
kok+0.011
 saddle+0.011
Neg logit contributions
Pope-0.012
angel-0.011
 Towards-0.009
 Deng-0.009
 Chu-0.009
Token main
Token ID1388
Feature activation-1.92e-02

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001
Token story
Token ID1621
Feature activation-3.53e-01

Pos logit contributions
ylan+0.006
 Brist+0.006
Story+0.006
kok+0.006
 Kyr+0.005
Neg logit contributions
Pope-0.023
angel-0.022
 Deng-0.020
 Towards-0.020
 Chu-0.020
Token
Token ID198
Feature activation+8.93e-03

Pos logit contributions
Story+0.267
ylan+0.263
 Brist+0.258
kok+0.249
 Kyr+0.239
Neg logit contributions
Pope-0.281
angel-0.261
 Towards-0.221
 Deng-0.218
atum-0.215
Token
Token ID198
Feature activation+7.03e-03

Pos logit contributions
Pope+0.007
angel+0.007
 Towards+0.006
 Deng+0.005
 Chu+0.005
Neg logit contributions
Story-0.007
ylan-0.007
 Brist-0.007
kok-0.006
 Kyr-0.006
TokenIn
Token ID818
Feature activation+2.53e-02

Pos logit contributions
Pope+0.006
angel+0.005
 Towards+0.004
 Deng+0.004
 Chu+0.004
Neg logit contributions
Story-0.005
ylan-0.005
 Brist-0.005
kok-0.005
 Kyr-0.005
Token the
Token ID262
Feature activation+5.30e-03

Pos logit contributions
Pope+0.021
angel+0.020
 Towards+0.017
 Deng+0.017
 Chu+0.016
Neg logit contributions
Story-0.018
ylan-0.018
 Brist-0.017
kok-0.017
 Kyr-0.016
Token capital
Token ID3139
Feature activation+2.07e-01

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.004
kok-0.004
 Kyr-0.004
Token,
Token ID11
Feature activation+5.17e-05

Pos logit contributions
Pope+0.083
angel+0.077
 Towards+0.065
 Deng+0.064
 Chu+0.063
Neg logit contributions
Story-0.078
ylan-0.077
 Brist-0.076
kok-0.073
 Kyr-0.070
Token he
Token ID339
Feature activation-2.64e-02

Pos logit contributions
Pope+0.000
angel+0.000
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.000
ylan-0.000
 Brist-0.000
kok-0.000
 Kyr-0.000
Token is
Token ID318
Feature activation-1.63e-03

Pos logit contributions
Story+0.019
ylan+0.019
 Brist+0.019
kok+0.018
 Kyr+0.017
Neg logit contributions
Pope-0.022
angel-0.020
 Towards-0.017
 Deng-0.017
 Chu-0.017
Token an
Token ID281
Feature activation-4.38e-04

Pos logit contributions
Story+0.001
ylan+0.001
 Brist+0.001
kok+0.001
 Kyr+0.001
Neg logit contributions
Pope-0.001
angel-0.001
 Towards-0.001
 Deng-0.001
 Chu-0.001
Token instinct
Token ID13311
Feature activation+1.24e-01

Pos logit contributions
Story+0.000
ylan+0.000
 Brist+0.000
kok+0.000
 Kyr+0.000
Neg logit contributions
Pope-0.000
angel-0.000
 Towards-0.000
 Deng-0.000
 Chu-0.000
Tokenive
Token ID425
Feature activation-3.48e-01

Pos logit contributions
Pope+0.144
angel+0.136
 Towards+0.123
 Deng+0.122
 Chu+0.120
Neg logit contributions
Story-0.048
ylan-0.047
 Brist-0.045
kok-0.042
 Kyr-0.039
Token leader
Token ID3554
Feature activation-6.25e-02

Pos logit contributions
Story+0.239
ylan+0.236
 Brist+0.232
kok+0.222
 Kyr+0.213
Neg logit contributions
Pope-0.301
angel-0.280
 Towards-0.241
 Deng-0.238
 Chu-0.234
Token and
Token ID290
Feature activation+9.02e-03

Pos logit contributions
Story+0.047
ylan+0.047
 Brist+0.046
kok+0.045
 Kyr+0.043
Neg logit contributions
Pope-0.049
angel-0.046
 Towards-0.039
 Deng-0.038
 Chu-0.038
Token a
Token ID257
Feature activation+4.95e-03

Pos logit contributions
Pope+0.007
angel+0.007
 Towards+0.006
 Deng+0.006
 Chu+0.006
Neg logit contributions
Story-0.007
ylan-0.007
 Brist-0.006
kok-0.006
 Kyr-0.006
Token perfectly
Token ID7138
Feature activation+1.37e-01

Pos logit contributions
Pope+0.004
angel+0.004
 Towards+0.003
 Deng+0.003
 Chu+0.003
Neg logit contributions
Story-0.004
ylan-0.004
 Brist-0.003
kok-0.003
 Kyr-0.003
Token efficient
Token ID6942
Feature activation+1.67e-01

Pos logit contributions
Pope+0.110
angel+0.102
 Towards+0.087
 Deng+0.086
 Chu+0.084
Neg logit contributions
Story-0.102
ylan-0.102
 Brist-0.100
kok-0.096
 Kyr-0.092
Token Chin
Token ID22604
Feature activation-1.17e-01

Pos logit contributions
Story+0.002
ylan+0.002
 Brist+0.002
kok+0.002
 Kyr+0.002
Neg logit contributions
Pope-0.003
angel-0.003
 Towards-0.002
 Deng-0.002
 Chu-0.002
Tokenook
Token ID566
Feature activation-9.26e-02

Pos logit contributions
Story+0.072
ylan+0.071
 Brist+0.070
kok+0.067
 Kyr+0.063
Neg logit contributions
Pope-0.110
angel-0.103
 Towards-0.090
 Deng-0.089
 Chu-0.087
Token and
Token ID290
Feature activation+4.74e-04

Pos logit contributions
Story+0.049
ylan+0.048
 Brist+0.047
kok+0.044
 Kyr+0.042
Neg logit contributions
Pope-0.095
angel-0.089
 Towards-0.079
 Deng-0.078
 Chu-0.077
Token Cit
Token ID15792
Feature activation-3.33e-01

Pos logit contributions
Pope+0.000
angel+0.000
 Towards+0.000
 Deng+0.000
 Chu+0.000
Neg logit contributions
Story-0.000
ylan-0.000
 Brist-0.000
kok-0.000
 Kyr-0.000
Tokenra
Token ID430
Feature activation-4.98e-02

Pos logit contributions
Story+0.231
ylan+0.230
 Brist+0.226
kok+0.216
 saddle+0.206
Neg logit contributions
Pope-0.285
angel-0.266
 Towards-0.228
 Deng-0.226
 Chu-0.222
Token hops
Token ID29438
Feature activation-3.29e-01

Pos logit contributions
Story+0.021
ylan+0.021
 Brist+0.020
kok+0.019
 Kyr+0.018
Neg logit contributions
Pope-0.056
angel-0.053
 Towards-0.047
 Deng-0.047
 Chu-0.046
Token in
Token ID287
Feature activation-1.06e-02

Pos logit contributions
Story+0.248
ylan+0.246
 Brist+0.242
kok+0.233
 Kyr+0.223
Neg logit contributions
Pope-0.262
angel-0.243
 Towards-0.205
 Deng-0.203
 Chu-0.199
Token the
Token ID262
Feature activation-1.14e-02

Pos logit contributions
Story+0.008
ylan+0.008
 Brist+0.008
kok+0.007
 Kyr+0.007
Neg logit contributions
Pope-0.009
angel-0.008
 Towards-0.007
 Deng-0.007
 Chu-0.007
Token kettle
Token ID40231
Feature activation-1.00e-01

Pos logit contributions
Story+0.008
ylan+0.008
 Brist+0.008
kok+0.008
 Kyr+0.007
Neg logit contributions
Pope-0.009
angel-0.009
 Towards-0.007
 Deng-0.007
 Chu-0.007
Token and
Token ID290
Feature activation+1.57e-03

Pos logit contributions
Story+0.075
ylan+0.074
 Brist+0.073
kok+0.070
 saddle+0.067
Neg logit contributions
Pope-0.080
angel-0.074
 Towards-0.063
 Deng-0.063
 Chu-0.061
Token dry
Token ID5894
Feature activation+7.55e-03

Pos logit contributions
Pope+0.001
angel+0.001
 Towards+0.001
 Deng+0.001
 Chu+0.001
Neg logit contributions
Story-0.001
ylan-0.001
 Brist-0.001
kok-0.001
 Kyr-0.001