TOP ACTIVATIONS
MAX = 0.838

on fire , the Brad enton Herald reported .
Next , take a kn otted thread and needle and draw
how to bring the kn otted thread up from the wrong
things : Decre ases blood glucose .
amounts of criticism for esp ousing ideas that are seen as
ven Miner Fab ric ate vs Ever gl ove
glucose . Decre ases insulin level .
for charismatic worship , spr outing churches which have grown from
Strike within days . Fin ishing The Flood perhaps will take
ce lling and Straight Ske leton Sub division ; both based
have a crunch y gran ola mentality running things as if
said . Sm oke Music manager Mark de Jong
wrote : Cl arity Gaming will also be releasing
During the cart oon crisis a
bike . Gl enn , co - owner of
studied prior to actually impl anting it into a person ,
wrote : Cl arity Gaming will also be releasing
If Lee ends up impl anting the Love t ron 9
S overe ign Lux ury Travel ( 08 44 415
regarding the future of Cl arity Gaming Cl arity Gaming will

MIN ACTIVATIONS
MIN = -0.741

New castle United are reintrodu cing the Club 's official Fans
up to for prom isc uous behaviour .
man Institute . Amid plac ards including The Future
000 crore has been vandal ized in Roh t ak and
P AND EM IC AL ERT PH AS ES Phase 1
immortal eld ritch mon stros ities year after year and held
front of the Shaw Amen ities Building , also called
if this cemetery was vandal ized and what 's going on
one of the st aun chest supporters of Trump 's hard
of her r he umat oid arthritis . Trying to keep
ag it ators , vandal ized and set on fire in
those uber - wealth y , climate change - den
s idea that psycho analysis stigmat izes human sexuality .
that Sa 'd judgment acc ords with that of the law
iger goal Hon ours Club
education ." Mis guided political effort The
. S overe ign Lux ury Travel ( 08
inches , and taking splash y , cash y advantage of
a new mood of cens orious political correctness sweeping university campuses
W alth am and Som erville 's Union Square .

INTERVAL 0.443 - 0.838
CONTAINS 0.019%

of Cl arity Gaming Cl arity Gaming will also be releasing
е р д и т ь и
b . sh orter Ax is , space ); // 3
ojure / math . comb inator ics | 372 | |
S overe ign Lux ury Travel ( 08 44 415

INTERVAL 0.048 - 0.443
CONTAINS 22.822%

his political career , Bernie s current Millenn ial
The victim was able to put out the fire and called
er found out about Josh s history , leading
F ocal ac ral hyper ker at osis ( also known
based in New Jersey , said on Thursday that the Food

INTERVAL -0.346 - 0.048
CONTAINS 77.089%

gallery id = 159 ] The unfortunate bulk of
s our job , not theirs .
is job one . Lots of systems in place to check
however , is allowed to do so . Mc
Over the past few months we have been hearing

INTERVAL -0.741 - -0.346
CONTAINS 0.069%

these tasty , super - nut rit ious wild plants assuming
declines to disclose his tax rate , stating in an ABC
Se eker Ph yt ot itan vs Torch ling
to practice Lac anian psycho analysis . This is bullshit .
in the city of Daytona Beach where Whites and Blacks could
Token on
Token ID319
Feature activation+4.37e-02

Pos logit contributions
isphere+0.166
ethe+0.166
ITY+0.161
ities+0.158
oir+0.147
Neg logit contributions
ranch-0.162
otten-0.144
hammad-0.143
 fir-0.141
athered-0.141
Token fire
Token ID2046
Feature activation+1.85e-01

Pos logit contributions
ranch+0.068
otten+0.059
hammad+0.058
 fir+0.057
athered+0.057
Neg logit contributions
isphere-0.111
ethe-0.110
ITY-0.108
ities-0.106
oir-0.100
Token,
Token ID11
Feature activation+4.28e-02

Pos logit contributions
ranch+0.494
otten+0.454
hammad+0.451
 fir+0.450
athered+0.447
Neg logit contributions
isphere-0.266
ethe-0.264
ITY-0.254
ities-0.246
agraph-0.220
Token the
Token ID262
Feature activation+6.76e-02

Pos logit contributions
ranch+0.093
otten+0.083
hammad+0.083
athered+0.082
ulla+0.082
Neg logit contributions
isphere-0.082
ethe-0.082
ITY-0.080
ities-0.078
agraph-0.072
Token Brad
Token ID8114
Feature activation+9.07e-02

Pos logit contributions
ranch+0.131
otten+0.116
hammad+0.114
 fir+0.114
athered+0.113
Neg logit contributions
isphere-0.147
ethe-0.146
ITY-0.142
ities-0.140
oir-0.131
Tokenenton
Token ID26673
Feature activation+8.38e-01

Pos logit contributions
ranch+0.138
otten+0.118
hammad+0.117
 fir+0.115
athered+0.115
Neg logit contributions
isphere-0.233
ethe-0.233
ITY-0.228
ities-0.225
oir-0.212
Token Herald
Token ID18277
Feature activation+3.21e-02

Pos logit contributions
ranch+1.870
otten+1.704
 fir+1.688
hammad+1.661
ucket+1.657
Neg logit contributions
isphere-1.573
ethe-1.545
ITY-1.490
ities-1.455
oir-1.350
Token reported
Token ID2098
Feature activation+1.35e-01

Pos logit contributions
ranch+0.072
otten+0.065
hammad+0.065
 fir+0.064
athered+0.064
Neg logit contributions
isphere-0.059
ethe-0.059
ITY-0.057
ities-0.056
oir-0.052
Token.
Token ID13
Feature activation+4.44e-02

Pos logit contributions
ranch+0.374
otten+0.346
hammad+0.344
 fir+0.342
ulla+0.339
Neg logit contributions
isphere-0.179
ethe-0.178
ITY-0.170
ities-0.166
agraph-0.147
Token
Token ID198
Feature activation+8.68e-02

Pos logit contributions
ranch+0.095
otten+0.085
hammad+0.084
 fir+0.084
athered+0.083
Neg logit contributions
isphere-0.087
ethe-0.087
ITY-0.084
ities-0.083
oir-0.076
Token
Token ID198
Feature activation+7.08e-02

Pos logit contributions
ranch+0.194
otten+0.175
hammad+0.173
 fir+0.172
athered+0.171
Neg logit contributions
isphere-0.163
ethe-0.162
ITY-0.157
ities-0.153
agraph-0.142
Token Next
Token ID7406
Feature activation+4.92e-02

Pos logit contributions
ranch+0.028
otten+0.025
hammad+0.024
 fir+0.024
athered+0.024
Neg logit contributions
isphere-0.028
ethe-0.028
ITY-0.027
ities-0.027
agraph-0.025
Token,
Token ID11
Feature activation+1.16e-02

Pos logit contributions
ranch+0.112
otten+0.101
hammad+0.100
 fir+0.100
athered+0.099
Neg logit contributions
isphere-0.090
ethe-0.089
ITY-0.087
ities-0.085
oir-0.078
Token take
Token ID1011
Feature activation+8.55e-02

Pos logit contributions
ranch+0.023
otten+0.021
hammad+0.021
 fir+0.021
athered+0.020
Neg logit contributions
isphere-0.024
ethe-0.024
ITY-0.023
ities-0.023
agraph-0.021
Token a
Token ID257
Feature activation-4.25e-03

Pos logit contributions
ranch+0.187
otten+0.168
hammad+0.167
 fir+0.166
athered+0.166
Neg logit contributions
isphere-0.163
ethe-0.162
ITY-0.158
ities-0.154
oir-0.143
Token kn
Token ID638
Feature activation+5.01e-02

Pos logit contributions
isphere+0.009
ethe+0.009
ITY+0.008
ities+0.008
agraph+0.008
Neg logit contributions
ranch-0.009
otten-0.008
hammad-0.008
 fir-0.008
athered-0.008
Tokenotted
Token ID8426
Feature activation+7.88e-01

Pos logit contributions
ranch+0.071
otten+0.060
hammad+0.059
 fir+0.058
ulla+0.058
Neg logit contributions
isphere-0.135
ethe-0.134
ITY-0.131
ities-0.130
oir-0.123
Token thread
Token ID4704
Feature activation+7.34e-02

Pos logit contributions
ranch+1.434
otten+1.251
 fir+1.250
hammad+1.232
ucket+1.227
Neg logit contributions
isphere-1.797
ethe-1.780
ITY-1.740
ities-1.705
oir-1.602
Token and
Token ID290
Feature activation+1.41e-02

Pos logit contributions
ranch+0.157
otten+0.140
 fir+0.139
hammad+0.139
athered+0.137
Neg logit contributions
isphere-0.144
ethe-0.143
ITY-0.140
ities-0.137
agraph-0.126
Token needle
Token ID17598
Feature activation-9.62e-02

Pos logit contributions
ranch+0.026
otten+0.023
hammad+0.023
 fir+0.023
athered+0.023
Neg logit contributions
isphere-0.031
ethe-0.031
ITY-0.031
ities-0.030
oir-0.028
Token and
Token ID290
Feature activation-1.95e-02

Pos logit contributions
isphere+0.186
ethe+0.185
ITY+0.180
ities+0.177
oir+0.164
Neg logit contributions
ranch-0.208
otten-0.187
hammad-0.185
 fir-0.184
athered-0.183
Token draw
Token ID3197
Feature activation+1.90e-01

Pos logit contributions
isphere+0.043
ethe+0.043
ITY+0.042
ities+0.041
agraph+0.039
Neg logit contributions
ranch-0.037
otten-0.032
hammad-0.032
 fir-0.032
athered-0.032
Token how
Token ID703
Feature activation+1.42e-02

Pos logit contributions
ranch+0.029
otten+0.026
hammad+0.026
 fir+0.026
athered+0.026
Neg logit contributions
isphere-0.022
ethe-0.022
ITY-0.021
ities-0.021
oir-0.019
Token to
Token ID284
Feature activation-3.62e-02

Pos logit contributions
ranch+0.032
otten+0.029
hammad+0.028
 fir+0.028
athered+0.028
Neg logit contributions
isphere-0.026
ethe-0.026
ITY-0.025
ities-0.025
oir-0.023
Token bring
Token ID2222
Feature activation+5.15e-02

Pos logit contributions
isphere+0.082
ethe+0.081
ITY+0.079
ities+0.078
oir+0.073
Neg logit contributions
ranch-0.067
otten-0.059
 fir-0.058
hammad-0.058
athered-0.058
Token the
Token ID262
Feature activation-6.67e-02

Pos logit contributions
ranch+0.115
otten+0.104
hammad+0.103
 fir+0.102
athered+0.102
Neg logit contributions
isphere-0.096
ethe-0.095
ITY-0.093
ities-0.091
oir-0.084
Token kn
Token ID638
Feature activation-1.90e-02

Pos logit contributions
isphere+0.147
ethe+0.146
ITY+0.142
ities+0.140
oir+0.131
Neg logit contributions
ranch-0.127
otten-0.112
hammad-0.111
 fir-0.110
athered-0.110
Tokenotted
Token ID8426
Feature activation+7.35e-01

Pos logit contributions
isphere+0.045
ethe+0.045
ITY+0.043
ities+0.043
oir+0.040
Neg logit contributions
ranch-0.033
otten-0.029
hammad-0.029
 fir-0.028
athered-0.028
Token thread
Token ID4704
Feature activation-2.76e-02

Pos logit contributions
ranch+1.416
otten+1.244
 fir+1.241
ulla+1.226
athered+1.219
Neg logit contributions
isphere-1.601
ethe-1.589
ITY-1.539
ities-1.498
oir-1.420
Token up
Token ID510
Feature activation-9.67e-02

Pos logit contributions
isphere+0.052
ethe+0.052
ITY+0.050
ities+0.049
agraph+0.045
Neg logit contributions
ranch-0.061
otten-0.055
hammad-0.054
 fir-0.054
athered-0.054
Token from
Token ID422
Feature activation-7.69e-02

Pos logit contributions
isphere+0.183
ethe+0.181
ITY+0.177
ities+0.173
agraph+0.160
Neg logit contributions
ranch-0.212
otten-0.191
 fir-0.191
hammad-0.190
athered-0.188
Token the
Token ID262
Feature activation-4.82e-02

Pos logit contributions
isphere+0.142
ethe+0.141
ITY+0.136
ities+0.134
oir+0.123
Neg logit contributions
ranch-0.174
otten-0.157
hammad-0.156
 fir-0.155
athered-0.154
Token wrong
Token ID2642
Feature activation+2.72e-02

Pos logit contributions
isphere+0.102
ethe+0.102
ITY+0.099
ities+0.097
oir+0.091
Neg logit contributions
ranch-0.096
otten-0.085
hammad-0.084
 fir-0.084
athered-0.083
Token things
Token ID1243
Feature activation+1.36e-01

Pos logit contributions
ranch+0.231
otten+0.207
hammad+0.206
 fir+0.205
athered+0.203
Neg logit contributions
isphere-0.218
ethe-0.215
ITY-0.209
ities-0.203
agraph-0.192
Token:
Token ID25
Feature activation+1.75e-01

Pos logit contributions
ranch+0.342
otten+0.313
hammad+0.312
 fir+0.310
athered+0.307
Neg logit contributions
isphere-0.216
ethe-0.214
ITY-0.205
ities-0.197
agraph-0.184
Token
Token ID198
Feature activation+8.93e-02

Pos logit contributions
ranch+0.390
otten+0.351
hammad+0.348
 fir+0.347
athered+0.344
Neg logit contributions
isphere-0.329
ethe-0.326
ITY-0.317
ities-0.310
agraph-0.288
Token
Token ID198
Feature activation+7.92e-02

Pos logit contributions
ranch+0.197
otten+0.177
hammad+0.175
 fir+0.174
athered+0.173
Neg logit contributions
isphere-0.171
ethe-0.169
ITY-0.164
ities-0.160
agraph-0.149
TokenDecre
Token ID43198
Feature activation-1.35e-01

Pos logit contributions
ranch+0.178
otten+0.159
hammad+0.158
 fir+0.157
ulla+0.156
Neg logit contributions
isphere-0.148
ethe-0.147
ITY-0.142
ities-0.139
agraph-0.130
Tokenases
Token ID1386
Feature activation+7.32e-01

Pos logit contributions
isphere+0.350
ethe+0.348
ITY+0.341
ities+0.336
oir+0.317
Neg logit contributions
ranch-0.203
otten-0.173
hammad-0.171
athered-0.168
 fir-0.168
Token blood
Token ID2910
Feature activation-2.23e-02

Pos logit contributions
ranch+1.496
otten+1.349
 fir+1.348
hammad+1.331
ulla+1.315
Neg logit contributions
isphere-1.491
ethe-1.462
ITY-1.423
ities-1.388
agraph-1.321
Token glucose
Token ID15701
Feature activation-3.10e-02

Pos logit contributions
isphere+0.047
ethe+0.047
ITY+0.046
ities+0.045
agraph+0.042
Neg logit contributions
ranch-0.044
otten-0.039
hammad-0.039
 fir-0.039
ulla-0.039
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
isphere+0.054
ethe+0.054
ITY+0.052
ities+0.051
agraph+0.047
Neg logit contributions
ranch-0.073
otten-0.066
hammad-0.066
 fir-0.065
athered-0.065
Token
Token ID198
Feature activation+1.25e-01

Pos logit contributions
ranch+0.221
otten+0.198
hammad+0.196
 fir+0.194
athered+0.194
Neg logit contributions
isphere-0.209
ethe-0.207
ITY-0.201
ities-0.198
agraph-0.184
Token
Token ID198
Feature activation+1.09e-01

Pos logit contributions
ranch+0.278
otten+0.250
hammad+0.247
 fir+0.246
athered+0.244
Neg logit contributions
isphere-0.238
ethe-0.236
ITY-0.228
ities-0.223
agraph-0.208
Token amounts
Token ID6867
Feature activation+5.86e-02

Pos logit contributions
ranch+0.003
otten+0.002
hammad+0.002
 fir+0.002
athered+0.002
Neg logit contributions
isphere-0.003
ethe-0.003
ITY-0.003
ities-0.003
oir-0.003
Token of
Token ID286
Feature activation+7.82e-02

Pos logit contributions
ranch+0.126
otten+0.113
hammad+0.112
 fir+0.111
athered+0.111
Neg logit contributions
isphere-0.115
ethe-0.114
ITY-0.111
ities-0.109
agraph-0.101
Token criticism
Token ID7734
Feature activation-1.16e-01

Pos logit contributions
ranch+0.158
otten+0.142
 fir+0.140
hammad+0.139
athered+0.139
Neg logit contributions
isphere-0.162
ethe-0.162
ITY-0.157
ities-0.154
oir-0.144
Token for
Token ID329
Feature activation+1.18e-01

Pos logit contributions
isphere+0.211
ethe+0.210
ITY+0.204
ities+0.198
oir+0.183
Neg logit contributions
ranch-0.263
otten-0.239
hammad-0.237
 fir-0.236
athered-0.234
Token esp
Token ID15024
Feature activation+7.57e-02

Pos logit contributions
ranch+0.254
otten+0.229
 fir+0.228
hammad+0.227
athered+0.224
Neg logit contributions
isphere-0.229
ethe-0.229
ITY-0.221
ities-0.216
oir-0.201
Tokenousing
Token ID12752
Feature activation+7.22e-01

Pos logit contributions
ranch+0.118
otten+0.101
hammad+0.100
 fir+0.099
athered+0.099
Neg logit contributions
isphere-0.192
ethe-0.192
ITY-0.187
ities-0.185
agraph-0.175
Token ideas
Token ID4213
Feature activation+1.59e-01

Pos logit contributions
ranch+1.501
otten+1.347
 fir+1.333
hammad+1.332
athered+1.320
Neg logit contributions
isphere-1.451
ethe-1.446
ITY-1.406
ities-1.370
oir-1.281
Token that
Token ID326
Feature activation+6.64e-02

Pos logit contributions
ranch+0.349
otten+0.317
 fir+0.315
hammad+0.313
athered+0.311
Neg logit contributions
isphere-0.298
ethe-0.298
ITY-0.288
ities-0.280
oir-0.262
Token are
Token ID389
Feature activation+2.47e-02

Pos logit contributions
ranch+0.137
otten+0.122
hammad+0.121
 fir+0.120
athered+0.120
Neg logit contributions
isphere-0.136
ethe-0.135
ITY-0.131
ities-0.129
oir-0.120
Token seen
Token ID1775
Feature activation+1.52e-01

Pos logit contributions
ranch+0.051
otten+0.046
hammad+0.045
 fir+0.045
athered+0.045
Neg logit contributions
isphere-0.050
ethe-0.050
ITY-0.049
ities-0.048
oir-0.044
Token as
Token ID355
Feature activation+7.32e-02

Pos logit contributions
ranch+0.361
otten+0.332
 fir+0.330
hammad+0.330
athered+0.325
Neg logit contributions
isphere-0.259
ethe-0.256
ITY-0.248
ities-0.241
agraph-0.223
Tokenven
Token ID574
Feature activation+1.30e-01

Pos logit contributions
isphere+0.060
ethe+0.059
ITY+0.058
ities+0.057
agraph+0.054
Neg logit contributions
ranch-0.042
otten-0.037
hammad-0.037
 fir-0.036
athered-0.036
Token Miner
Token ID29295
Feature activation+4.23e-02

Pos logit contributions
ranch+0.283
otten+0.255
hammad+0.252
 fir+0.251
ulla+0.250
Neg logit contributions
isphere-0.250
ethe-0.249
ITY-0.242
ities-0.237
agraph-0.220
Token
Token ID198
Feature activation-4.72e-03

Pos logit contributions
ranch+0.100
otten+0.091
hammad+0.090
 fir+0.089
ulla+0.089
Neg logit contributions
isphere-0.073
ethe-0.073
ITY-0.071
ities-0.069
agraph-0.063
Token
Token ID198
Feature activation-9.28e-03

Pos logit contributions
isphere+0.009
ethe+0.009
ITY+0.009
ities+0.008
agraph+0.008
Neg logit contributions
ranch-0.010
otten-0.009
hammad-0.009
 fir-0.009
athered-0.009
TokenFab
Token ID43957
Feature activation+4.31e-02

Pos logit contributions
isphere+0.017
ethe+0.017
ITY+0.017
ities+0.016
agraph+0.015
Neg logit contributions
ranch-0.021
otten-0.019
hammad-0.018
athered-0.018
 fir-0.018
Tokenric
Token ID1173
Feature activation+7.13e-01

Pos logit contributions
ranch+0.085
otten+0.075
hammad+0.074
 fir+0.074
athered+0.073
Neg logit contributions
isphere-0.092
ethe-0.092
ITY-0.090
ities-0.088
oir-0.082
Tokenate
Token ID378
Feature activation+3.11e-01

Pos logit contributions
ranch+1.606
otten+1.463
athered+1.432
 fir+1.429
hammad+1.427
Neg logit contributions
isphere-1.296
ethe-1.292
ITY-1.243
ities-1.219
oir-1.132
Token vs
Token ID3691
Feature activation+8.36e-02

Pos logit contributions
ranch+0.711
otten+0.646
hammad+0.636
 fir+0.636
athered+0.632
Neg logit contributions
isphere-0.557
ethe-0.556
ITY-0.539
ities-0.526
agraph-0.487
Token Ever
Token ID10776
Feature activation+1.30e-01

Pos logit contributions
ranch+0.177
otten+0.159
hammad+0.157
 fir+0.156
athered+0.155
Neg logit contributions
isphere-0.166
ethe-0.165
ITY-0.160
ities-0.157
agraph-0.146
Tokengl
Token ID4743
Feature activation+1.14e-01

Pos logit contributions
ranch+0.274
otten+0.245
hammad+0.243
athered+0.241
 fir+0.241
Neg logit contributions
isphere-0.258
ethe-0.258
ITY-0.251
ities-0.246
agraph-0.228
Tokenove
Token ID659
Feature activation+5.29e-02

Pos logit contributions
ranch+0.226
otten+0.203
hammad+0.199
athered+0.198
 fir+0.197
Neg logit contributions
isphere-0.239
ethe-0.238
ITY-0.233
ities-0.228
agraph-0.212
Token glucose
Token ID15701
Feature activation-3.10e-02

Pos logit contributions
isphere+0.047
ethe+0.047
ITY+0.046
ities+0.045
agraph+0.042
Neg logit contributions
ranch-0.044
otten-0.039
hammad-0.039
 fir-0.039
ulla-0.039
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
isphere+0.054
ethe+0.054
ITY+0.052
ities+0.051
agraph+0.047
Neg logit contributions
ranch-0.073
otten-0.066
hammad-0.066
 fir-0.065
athered-0.065
Token
Token ID198
Feature activation+1.25e-01

Pos logit contributions
ranch+0.221
otten+0.198
hammad+0.196
 fir+0.194
athered+0.194
Neg logit contributions
isphere-0.209
ethe-0.207
ITY-0.201
ities-0.198
agraph-0.184
Token
Token ID198
Feature activation+1.09e-01

Pos logit contributions
ranch+0.278
otten+0.250
hammad+0.247
 fir+0.246
athered+0.244
Neg logit contributions
isphere-0.238
ethe-0.236
ITY-0.228
ities-0.223
agraph-0.208
TokenDecre
Token ID43198
Feature activation-1.57e-01

Pos logit contributions
ranch+0.247
otten+0.222
hammad+0.220
 fir+0.218
ulla+0.217
Neg logit contributions
isphere-0.200
ethe-0.198
ITY-0.191
ities-0.187
agraph-0.174
Tokenases
Token ID1386
Feature activation+6.94e-01

Pos logit contributions
isphere+0.404
ethe+0.403
ITY+0.394
ities+0.389
agraph+0.367
Neg logit contributions
ranch-0.238
otten-0.204
hammad-0.201
 fir-0.199
athered-0.198
Token insulin
Token ID14588
Feature activation+1.23e-02

Pos logit contributions
ranch+1.446
otten+1.296
 fir+1.294
hammad+1.281
ulla+1.270
Neg logit contributions
isphere-1.391
ethe-1.366
ITY-1.333
ities-1.303
agraph-1.231
Token level
Token ID1241
Feature activation-6.23e-02

Pos logit contributions
ranch+0.025
otten+0.023
hammad+0.022
 fir+0.022
athered+0.022
Neg logit contributions
isphere-0.025
ethe-0.025
ITY-0.024
ities-0.024
oir-0.022
Token.
Token ID13
Feature activation+1.44e-01

Pos logit contributions
isphere+0.089
ethe+0.088
ITY+0.085
ities+0.083
agraph+0.074
Neg logit contributions
ranch-0.167
otten-0.153
hammad-0.152
 fir-0.151
athered-0.151
Token
Token ID198
Feature activation+1.66e-01

Pos logit contributions
ranch+0.327
otten+0.296
hammad+0.294
athered+0.291
 fir+0.290
Neg logit contributions
isphere-0.262
ethe-0.262
ITY-0.254
ities-0.249
oir-0.229
Token
Token ID198
Feature activation+1.33e-01

Pos logit contributions
ranch+0.367
otten+0.330
hammad+0.327
 fir+0.325
athered+0.322
Neg logit contributions
isphere-0.318
ethe-0.315
ITY-0.304
ities-0.297
agraph-0.277
Token for
Token ID329
Feature activation-2.87e-02

Pos logit contributions
ranch+0.197
otten+0.176
hammad+0.174
 fir+0.173
athered+0.173
Neg logit contributions
ethe-0.186
isphere-0.185
ITY-0.180
ities-0.176
agraph-0.164
Token charismatic
Token ID34996
Feature activation+4.82e-02

Pos logit contributions
isphere+0.056
ethe+0.056
ITY+0.054
ities+0.053
agraph+0.049
Neg logit contributions
ranch-0.062
otten-0.055
hammad-0.055
 fir-0.055
athered-0.054
Token worship
Token ID11892
Feature activation+1.76e-01

Pos logit contributions
ranch+0.103
otten+0.092
 fir+0.091
hammad+0.091
athered+0.090
Neg logit contributions
isphere-0.095
ethe-0.094
ITY-0.092
ities-0.089
agraph-0.083
Token,
Token ID11
Feature activation+1.35e-02

Pos logit contributions
ranch+0.413
otten+0.374
hammad+0.371
 fir+0.368
athered+0.367
Neg logit contributions
isphere-0.310
ethe-0.308
ITY-0.299
ities-0.292
oir-0.268
Token spr
Token ID7500
Feature activation+2.60e-02

Pos logit contributions
ranch+0.029
otten+0.026
hammad+0.026
ulla+0.026
athered+0.026
Neg logit contributions
isphere-0.026
ethe-0.026
ITY-0.025
ities-0.025
agraph-0.023
Tokenouting
Token ID13660
Feature activation+6.86e-01

Pos logit contributions
ranch+0.036
otten+0.030
hammad+0.029
 fir+0.029
athered+0.029
Neg logit contributions
isphere-0.071
ethe-0.071
ITY-0.069
ities-0.069
oir-0.065
Token churches
Token ID14422
Feature activation+1.22e-01

Pos logit contributions
ranch+1.467
otten+1.316
 fir+1.314
hammad+1.302
athered+1.295
Neg logit contributions
isphere-1.343
ethe-1.331
ITY-1.297
ities-1.263
oir-1.183
Token which
Token ID543
Feature activation+1.92e-02

Pos logit contributions
ranch+0.282
otten+0.256
hammad+0.253
 fir+0.253
athered+0.252
Neg logit contributions
isphere-0.217
ethe-0.217
ITY-0.210
ities-0.204
oir-0.189
Token have
Token ID423
Feature activation+9.63e-02

Pos logit contributions
ranch+0.038
otten+0.034
hammad+0.033
 fir+0.033
athered+0.033
Neg logit contributions
isphere-0.041
ethe-0.041
ITY-0.040
ities-0.039
agraph-0.036
Token grown
Token ID7334
Feature activation+1.52e-01

Pos logit contributions
ranch+0.185
otten+0.164
hammad+0.162
 fir+0.162
athered+0.161
Neg logit contributions
isphere-0.210
ethe-0.209
ITY-0.204
ities-0.200
oir-0.187
Token from
Token ID422
Feature activation+7.43e-02

Pos logit contributions
ranch+0.338
otten+0.305
 fir+0.302
hammad+0.302
athered+0.300
Neg logit contributions
isphere-0.286
ethe-0.285
ITY-0.276
ities-0.270
oir-0.251
Token Strike
Token ID12282
Feature activation-1.64e-01

Pos logit contributions
isphere+0.056
ethe+0.056
ITY+0.055
ities+0.053
oir+0.050
Neg logit contributions
ranch-0.060
otten-0.054
hammad-0.054
 fir-0.054
athered-0.053
Token within
Token ID1626
Feature activation-7.99e-02

Pos logit contributions
isphere+0.298
ethe+0.296
ITY+0.287
ities+0.281
agraph+0.258
Neg logit contributions
ranch-0.377
otten-0.341
hammad-0.338
 fir-0.336
athered-0.334
Token days
Token ID1528
Feature activation-2.74e-02

Pos logit contributions
isphere+0.157
ethe+0.156
ITY+0.151
ities+0.148
oir+0.137
Neg logit contributions
ranch-0.171
otten-0.154
hammad-0.152
 fir-0.152
athered-0.150
Token.
Token ID13
Feature activation-1.09e-01

Pos logit contributions
isphere+0.049
ethe+0.048
ITY+0.047
ities+0.046
agraph+0.042
Neg logit contributions
ranch-0.063
otten-0.058
hammad-0.057
 fir-0.057
athered-0.057
Token Fin
Token ID4463
Feature activation+1.21e-01

Pos logit contributions
isphere+0.216
ethe+0.216
ITY+0.210
ities+0.206
oir+0.191
Neg logit contributions
ranch-0.233
otten-0.208
hammad-0.207
athered-0.205
 fir-0.204
Tokenishing
Token ID3929
Feature activation+6.52e-01

Pos logit contributions
ranch+0.254
otten+0.227
hammad+0.224
athered+0.223
 fir+0.222
Neg logit contributions
isphere-0.242
ethe-0.241
ITY-0.235
ities-0.230
oir-0.214
Token The
Token ID383
Feature activation+2.93e-02

Pos logit contributions
ranch+1.416
otten+1.273
 fir+1.254
hammad+1.247
athered+1.242
Neg logit contributions
isphere-1.259
ethe-1.232
ITY-1.210
ities-1.178
oir-1.091
Token Flood
Token ID25588
Feature activation-5.36e-02

Pos logit contributions
ranch+0.044
otten+0.038
hammad+0.037
 fir+0.037
athered+0.036
Neg logit contributions
isphere-0.076
ethe-0.076
ITY-0.074
ities-0.073
oir-0.069
Token perhaps
Token ID3737
Feature activation-7.10e-02

Pos logit contributions
isphere+0.100
ethe+0.099
ITY+0.097
ities+0.094
agraph+0.087
Neg logit contributions
ranch-0.120
otten-0.108
hammad-0.107
 fir-0.106
ulla-0.106
Token will
Token ID481
Feature activation-9.82e-02

Pos logit contributions
isphere+0.137
ethe+0.136
ITY+0.132
ities+0.129
oir+0.120
Neg logit contributions
ranch-0.154
otten-0.139
hammad-0.138
 fir-0.137
athered-0.136
Token take
Token ID1011
Feature activation-5.26e-02

Pos logit contributions
isphere+0.214
ethe+0.212
ITY+0.207
ities+0.203
agraph+0.190
Neg logit contributions
ranch-0.190
otten-0.168
hammad-0.165
 fir-0.165
athered-0.164
Tokence
Token ID344
Feature activation+3.51e-02

Pos logit contributions
isphere+0.117
ethe+0.117
ITY+0.111
ities+0.107
oir+0.098
Neg logit contributions
ranch-0.199
otten-0.180
athered-0.178
hammad-0.178
ulla-0.177
Tokenlling
Token ID2680
Feature activation+7.56e-02

Pos logit contributions
ranch+0.067
otten+0.059
athered+0.058
hammad+0.058
 fir+0.058
Neg logit contributions
isphere-0.078
ethe-0.077
ITY-0.075
ities-0.073
oir-0.069
Token and
Token ID290
Feature activation+8.75e-02

Pos logit contributions
ranch+0.166
otten+0.149
hammad+0.147
 fir+0.146
athered+0.145
Neg logit contributions
isphere-0.145
ethe-0.144
ITY-0.139
ities-0.136
agraph-0.126
Token Straight
Token ID27680
Feature activation+4.86e-02

Pos logit contributions
ranch+0.196
otten+0.176
hammad+0.174
 fir+0.174
athered+0.173
Neg logit contributions
isphere-0.164
ethe-0.163
ITY-0.157
ities-0.154
oir-0.142
Token Ske
Token ID19460
Feature activation+3.54e-02

Pos logit contributions
ranch+0.098
otten+0.088
hammad+0.086
 fir+0.086
athered+0.086
Neg logit contributions
isphere-0.101
ethe-0.100
ITY-0.098
ities-0.096
oir-0.089
Tokenleton
Token ID10565
Feature activation+6.38e-01

Pos logit contributions
ranch+0.066
otten+0.058
hammad+0.057
athered+0.057
ulla+0.056
Neg logit contributions
isphere-0.079
ethe-0.078
ITY-0.077
ities-0.076
agraph-0.071
Token Sub
Token ID3834
Feature activation-2.32e-02

Pos logit contributions
ranch+1.361
otten+1.215
hammad+1.196
 fir+1.194
athered+1.186
Neg logit contributions
isphere-1.262
ethe-1.253
ITY-1.208
ities-1.181
oir-1.104
Tokendivision
Token ID21426
Feature activation-6.85e-03

Pos logit contributions
isphere+0.047
ethe+0.047
ITY+0.045
ities+0.044
oir+0.041
Neg logit contributions
ranch-0.049
otten-0.043
hammad-0.043
athered-0.042
ulla-0.042
Token;
Token ID26
Feature activation+1.01e-01

Pos logit contributions
isphere+0.010
ethe+0.010
ITY+0.010
ities+0.009
agraph+0.008
Neg logit contributions
ranch-0.018
otten-0.017
hammad-0.016
 fir-0.016
athered-0.016
Token both
Token ID1111
Feature activation+4.73e-02

Pos logit contributions
ranch+0.233
otten+0.210
hammad+0.209
 fir+0.207
athered+0.206
Neg logit contributions
isphere-0.183
ethe-0.182
ITY-0.177
ities-0.173
oir-0.159
Token based
Token ID1912
Feature activation+4.90e-02

Pos logit contributions
ranch+0.097
otten+0.087
hammad+0.086
 fir+0.086
athered+0.085
Neg logit contributions
isphere-0.097
ethe-0.096
ITY-0.094
ities-0.092
agraph-0.086
Token have
Token ID423
Feature activation+1.45e-01

Pos logit contributions
ranch+0.032
otten+0.028
hammad+0.028
athered+0.028
 fir+0.027
Neg logit contributions
isphere-0.035
ethe-0.035
ITY-0.034
ities-0.033
agraph-0.031
Token a
Token ID257
Feature activation+9.04e-02

Pos logit contributions
ranch+0.301
otten+0.269
hammad+0.266
 fir+0.265
athered+0.265
Neg logit contributions
isphere-0.294
ethe-0.292
ITY-0.284
ities-0.278
agraph-0.259
Token crunch
Token ID23527
Feature activation-5.46e-03

Pos logit contributions
ranch+0.180
otten+0.160
hammad+0.158
 fir+0.158
athered+0.157
Neg logit contributions
isphere-0.191
ethe-0.190
ITY-0.184
ities-0.181
agraph-0.170
Tokeny
Token ID88
Feature activation+1.52e-01

Pos logit contributions
isphere+0.010
ethe+0.010
ITY+0.010
ities+0.010
agraph+0.009
Neg logit contributions
ranch-0.012
otten-0.011
hammad-0.011
 fir-0.011
athered-0.011
Token gran
Token ID19468
Feature activation+1.70e-01

Pos logit contributions
ranch+0.314
otten+0.281
hammad+0.278
 fir+0.276
athered+0.275
Neg logit contributions
isphere-0.310
ethe-0.309
ITY-0.300
ities-0.295
agraph-0.274
Tokenola
Token ID5708
Feature activation+6.36e-01

Pos logit contributions
ranch+0.310
otten+0.272
hammad+0.268
 fir+0.268
athered+0.266
Neg logit contributions
isphere-0.387
ethe-0.385
ITY-0.376
ities-0.369
agraph-0.346
Token mentality
Token ID21332
Feature activation+2.13e-02

Pos logit contributions
ranch+1.220
otten+1.079
 fir+1.064
athered+1.059
hammad+1.059
Neg logit contributions
isphere-1.381
ethe-1.378
ITY-1.338
ities-1.319
oir-1.235
Token running
Token ID2491
Feature activation+9.10e-02

Pos logit contributions
ranch+0.052
otten+0.047
hammad+0.047
 fir+0.047
athered+0.047
Neg logit contributions
isphere-0.035
ethe-0.035
ITY-0.034
ities-0.033
agraph-0.030
Token things
Token ID1243
Feature activation+9.92e-02

Pos logit contributions
ranch+0.200
otten+0.179
 fir+0.178
hammad+0.177
athered+0.176
Neg logit contributions
isphere-0.174
ethe-0.172
ITY-0.167
ities-0.163
agraph-0.152
Token as
Token ID355
Feature activation+1.89e-02

Pos logit contributions
ranch+0.241
otten+0.220
 fir+0.218
athered+0.217
hammad+0.217
Neg logit contributions
isphere-0.165
ethe-0.163
ITY-0.158
ities-0.153
agraph-0.142
Token if
Token ID611
Feature activation+1.13e-01

Pos logit contributions
ranch+0.042
otten+0.038
hammad+0.038
 fir+0.037
athered+0.037
Neg logit contributions
isphere-0.035
ethe-0.035
ITY-0.034
ities-0.033
agraph-0.031
Token said
Token ID531
Feature activation+4.58e-02

Pos logit contributions
isphere+0.131
ethe+0.131
ITY+0.127
ities+0.125
agraph+0.117
Neg logit contributions
ranch-0.106
otten-0.093
hammad-0.092
 fir-0.091
athered-0.091
Token.
Token ID13
Feature activation+3.47e-02

Pos logit contributions
ranch+0.126
otten+0.116
hammad+0.115
 fir+0.115
ulla+0.114
Neg logit contributions
isphere-0.062
ethe-0.061
ITY-0.059
ities-0.057
oir-0.051
Token
Token ID198
Feature activation+1.91e-02

Pos logit contributions
ranch+0.078
otten+0.070
hammad+0.070
 fir+0.069
athered+0.069
Neg logit contributions
ethe-0.064
isphere-0.064
ITY-0.062
ities-0.061
oir-0.056
Token
Token ID198
Feature activation-1.89e-03

Pos logit contributions
ranch+0.043
otten+0.038
hammad+0.038
 fir+0.038
athered+0.038
Neg logit contributions
isphere-0.036
ethe-0.036
ITY-0.035
ities-0.034
agraph-0.031
TokenSm
Token ID7556
Feature activation+8.90e-02

Pos logit contributions
isphere+0.003
ethe+0.003
ITY+0.003
ities+0.003
agraph+0.003
Neg logit contributions
ranch-0.004
otten-0.004
hammad-0.004
athered-0.004
ulla-0.004
Tokenoke
Token ID2088
Feature activation+6.31e-01

Pos logit contributions
ranch+0.177
otten+0.157
hammad+0.155
athered+0.154
ulla+0.154
Neg logit contributions
isphere-0.188
ethe-0.187
ITY-0.184
ities-0.180
agraph-0.167
Token Music
Token ID7849
Feature activation-8.99e-02

Pos logit contributions
ranch+1.449
otten+1.320
hammad+1.299
 fir+1.297
ulla+1.294
Neg logit contributions
isphere-1.124
ethe-1.119
ITY-1.091
ities-1.059
agraph-0.977
Token manager
Token ID4706
Feature activation+1.21e-01

Pos logit contributions
isphere+0.163
ethe+0.163
ITY+0.157
ities+0.154
agraph+0.142
Neg logit contributions
ranch-0.205
otten-0.186
hammad-0.184
 fir-0.183
athered-0.182
Token Mark
Token ID2940
Feature activation+1.14e-02

Pos logit contributions
ranch+0.262
otten+0.236
hammad+0.234
 fir+0.233
athered+0.231
Neg logit contributions
isphere-0.235
ethe-0.234
ITY-0.226
ities-0.221
agraph-0.206
Token de
Token ID390
Feature activation+1.59e-03

Pos logit contributions
ranch+0.023
otten+0.020
hammad+0.020
ulla+0.020
 fir+0.020
Neg logit contributions
isphere-0.024
ethe-0.024
ITY-0.024
ities-0.023
agraph-0.022
Token Jong
Token ID17960
Feature activation+1.10e-01

Pos logit contributions
ranch+0.003
otten+0.003
hammad+0.003
 fir+0.003
athered+0.003
Neg logit contributions
isphere-0.003
ethe-0.003
ITY-0.003
ities-0.003
oir-0.003
Token wrote
Token ID2630
Feature activation+1.32e-01

Pos logit contributions
isphere+0.104
ethe+0.103
ITY+0.100
ities+0.099
agraph+0.091
Neg logit contributions
ranch-0.130
otten-0.117
hammad-0.116
athered-0.115
 fir-0.115
Token:
Token ID25
Feature activation+7.06e-02

Pos logit contributions
ranch+0.384
otten+0.355
hammad+0.351
 fir+0.350
llan+0.348
Neg logit contributions
isphere-0.159
ethe-0.157
ITY-0.148
ities-0.142
agraph-0.128
Token
Token ID198
Feature activation+1.49e-01

Pos logit contributions
ranch+0.157
otten+0.141
hammad+0.140
 fir+0.139
athered+0.138
Neg logit contributions
isphere-0.133
ethe-0.132
ITY-0.128
ities-0.125
agraph-0.116
Token
Token ID198
Feature activation+1.45e-01

Pos logit contributions
ranch+0.328
otten+0.295
hammad+0.291
 fir+0.290
athered+0.288
Neg logit contributions
isphere-0.286
ethe-0.282
ITY-0.273
ities-0.267
agraph-0.249
TokenCl
Token ID2601
Feature activation+1.22e-01

Pos logit contributions
ranch+0.338
otten+0.306
hammad+0.302
athered+0.298
ucket+0.298
Neg logit contributions
isphere-0.255
ethe-0.253
ITY-0.245
ities-0.242
agraph-0.222
Tokenarity
Token ID6806
Feature activation+6.22e-01

Pos logit contributions
ranch+0.239
otten+0.212
hammad+0.210
 fir+0.208
athered+0.207
Neg logit contributions
isphere-0.261
ethe-0.261
ITY-0.254
ities-0.249
oir-0.233
Token Gaming
Token ID14426
Feature activation+3.12e-03

Pos logit contributions
ranch+1.402
otten+1.265
 fir+1.253
hammad+1.245
athered+1.238
Neg logit contributions
isphere-1.137
ethe-1.128
ITY-1.090
ities-1.070
oir-0.988
Token will
Token ID481
Feature activation+5.14e-02

Pos logit contributions
ranch+0.007
otten+0.006
hammad+0.006
 fir+0.006
athered+0.006
Neg logit contributions
isphere-0.006
ethe-0.006
ITY-0.006
ities-0.006
agraph-0.005
Token also
Token ID635
Feature activation+6.15e-02

Pos logit contributions
ranch+0.098
otten+0.087
 fir+0.086
athered+0.085
hammad+0.085
Neg logit contributions
isphere-0.113
ethe-0.112
ITY-0.109
ities-0.107
agraph-0.101
Token be
Token ID307
Feature activation-4.94e-03

Pos logit contributions
ranch+0.116
otten+0.101
 fir+0.100
athered+0.100
hammad+0.100
Neg logit contributions
isphere-0.137
ethe-0.136
ITY-0.133
ities-0.131
agraph-0.123
Token releasing
Token ID13011
Feature activation+1.03e-01

Pos logit contributions
isphere+0.010
ethe+0.010
ITY+0.010
ities+0.010
agraph+0.009
Neg logit contributions
ranch-0.010
otten-0.009
 fir-0.009
hammad-0.009
athered-0.009
Token During
Token ID5856
Feature activation+2.38e-02

Pos logit contributions
ranch+0.036
otten+0.032
hammad+0.032
 fir+0.032
athered+0.032
Neg logit contributions
isphere-0.038
ethe-0.038
ITY-0.037
ities-0.036
oir-0.033
Token the
Token ID262
Feature activation+2.39e-03

Pos logit contributions
ranch+0.053
otten+0.048
hammad+0.047
athered+0.047
ulla+0.047
Neg logit contributions
isphere-0.045
ethe-0.045
ITY-0.043
ities-0.042
agraph-0.039
Token
Token ID564
Feature activation+3.55e-02

Pos logit contributions
ranch+0.005
otten+0.004
hammad+0.004
 fir+0.004
athered+0.004
Neg logit contributions
isphere-0.005
ethe-0.005
ITY-0.005
ities-0.005
oir-0.004
Token
Token ID246
Feature activation+1.27e-01

Pos logit contributions
ranch+0.078
otten+0.070
hammad+0.070
 fir+0.069
athered+0.069
Neg logit contributions
isphere-0.068
ethe-0.067
ITY-0.066
ities-0.065
oir-0.059
Tokencart
Token ID26674
Feature activation-9.40e-02

Pos logit contributions
ranch+0.266
otten+0.238
hammad+0.236
athered+0.233
 fir+0.233
Neg logit contributions
isphere-0.255
ethe-0.253
ITY-0.247
ities-0.243
oir-0.225
Tokenoon
Token ID2049
Feature activation+6.21e-01

Pos logit contributions
isphere+0.181
ethe+0.180
ITY+0.175
ities+0.171
agraph+0.159
Neg logit contributions
ranch-0.204
otten-0.184
hammad-0.182
athered-0.181
 fir-0.180
Token crisis
Token ID4902
Feature activation-3.56e-02

Pos logit contributions
ranch+1.444
otten+1.314
hammad+1.301
 fir+1.299
athered+1.294
Neg logit contributions
isphere-1.081
ethe-1.074
ITY-1.045
ities-1.009
oir-0.934
Token
Token ID447
Feature activation+5.57e-02

Pos logit contributions
isphere+0.061
ethe+0.061
ITY+0.059
ities+0.058
oir+0.053
Neg logit contributions
ranch-0.084
otten-0.077
hammad-0.076
 fir-0.075
athered-0.075
Token
Token ID247
Feature activation+2.12e-02

Pos logit contributions
ranch+0.114
otten+0.101
hammad+0.100
athered+0.099
 fir+0.099
Neg logit contributions
ethe-0.115
isphere-0.114
ITY-0.111
ities-0.109
oir-0.101
Token
Token ID851
Feature activation-5.87e-02

Pos logit contributions
ranch+0.049
otten+0.045
hammad+0.044
 fir+0.044
athered+0.044
Neg logit contributions
isphere-0.038
ethe-0.038
ITY-0.037
ities-0.036
agraph-0.033
Token a
Token ID257
Feature activation+4.00e-02

Pos logit contributions
isphere+0.111
ethe+0.111
ITY+0.107
ities+0.105
agraph+0.097
Neg logit contributions
ranch-0.130
otten-0.117
hammad-0.116
ulla-0.115
athered-0.115
Token bike
Token ID7161
Feature activation-9.02e-03

Pos logit contributions
isphere+0.144
ethe+0.144
ITY+0.140
ities+0.138
oir+0.129
Neg logit contributions
ranch-0.115
otten-0.101
hammad-0.100
 fir-0.099
athered-0.099
Token.
Token ID13
Feature activation-2.24e-02

Pos logit contributions
isphere+0.013
ethe+0.013
ITY+0.012
ities+0.012
agraph+0.011
Neg logit contributions
ranch-0.024
otten-0.022
hammad-0.022
 fir-0.022
athered-0.022
Token
Token ID198
Feature activation+1.91e-02

Pos logit contributions
isphere+0.043
ethe+0.043
ITY+0.041
ities+0.041
agraph+0.038
Neg logit contributions
ranch-0.049
otten-0.044
hammad-0.044
 fir-0.043
athered-0.043
Token
Token ID198
Feature activation+2.05e-03

Pos logit contributions
ranch+0.043
otten+0.039
hammad+0.038
 fir+0.038
athered+0.038
Neg logit contributions
isphere-0.035
ethe-0.035
ITY-0.034
ities-0.033
agraph-0.031
TokenGl
Token ID9861
Feature activation+1.33e-01

Pos logit contributions
ranch+0.005
otten+0.004
hammad+0.004
athered+0.004
 fir+0.004
Neg logit contributions
isphere-0.004
ethe-0.004
ITY-0.004
ities-0.004
oir-0.003
Tokenenn
Token ID1697
Feature activation+6.20e-01

Pos logit contributions
ranch+0.300
otten+0.271
hammad+0.268
athered+0.266
 fir+0.265
Neg logit contributions
isphere-0.245
ethe-0.243
ITY-0.237
ities-0.231
agraph-0.213
Token,
Token ID11
Feature activation+4.14e-02

Pos logit contributions
ranch+1.246
otten+1.115
 fir+1.112
hammad+1.104
athered+1.103
Neg logit contributions
isphere-1.279
ethe-1.276
ITY-1.240
ities-1.205
agraph-1.132
Token co
Token ID763
Feature activation+9.36e-02

Pos logit contributions
ranch+0.097
otten+0.087
hammad+0.087
 fir+0.086
athered+0.086
Neg logit contributions
isphere-0.073
ethe-0.073
ITY-0.070
ities-0.069
oir-0.063
Token-
Token ID12
Feature activation-4.65e-02

Pos logit contributions
ranch+0.239
otten+0.219
hammad+0.218
 fir+0.216
ulla+0.215
Neg logit contributions
ethe-0.144
isphere-0.143
ITY-0.138
ities-0.135
oir-0.122
Tokenowner
Token ID18403
Feature activation+1.46e-01

Pos logit contributions
isphere+0.071
ethe+0.071
ITY+0.068
ities+0.066
agraph+0.060
Neg logit contributions
ranch-0.120
otten-0.109
hammad-0.109
 fir-0.108
athered-0.108
Token of
Token ID286
Feature activation-1.93e-02

Pos logit contributions
ranch+0.313
otten+0.281
hammad+0.279
 fir+0.276
athered+0.275
Neg logit contributions
isphere-0.287
ethe-0.286
ITY-0.278
ities-0.272
agraph-0.253
Token studied
Token ID9713
Feature activation-3.88e-02

Pos logit contributions
ranch+0.117
otten+0.104
hammad+0.103
 fir+0.103
athered+0.102
Neg logit contributions
isphere-0.129
ethe-0.128
ITY-0.125
ities-0.123
oir-0.115
Token prior
Token ID3161
Feature activation+1.82e-02

Pos logit contributions
isphere+0.071
ethe+0.070
ITY+0.068
ities+0.066
agraph+0.062
Neg logit contributions
ranch-0.088
otten-0.080
hammad-0.079
 fir-0.079
athered-0.078
Token to
Token ID284
Feature activation-7.50e-02

Pos logit contributions
ranch+0.040
otten+0.036
hammad+0.036
 fir+0.035
athered+0.035
Neg logit contributions
isphere-0.035
ethe-0.035
ITY-0.034
ities-0.033
agraph-0.030
Token actually
Token ID1682
Feature activation+8.52e-03

Pos logit contributions
isphere+0.155
ethe+0.153
ITY+0.149
ities+0.146
oir+0.137
Neg logit contributions
ranch-0.153
otten-0.137
 fir-0.136
hammad-0.136
athered-0.134
Token impl
Token ID4114
Feature activation+1.04e-01

Pos logit contributions
ranch+0.017
otten+0.015
 fir+0.015
hammad+0.015
athered+0.015
Neg logit contributions
isphere-0.018
ethe-0.018
ITY-0.017
ities-0.017
oir-0.016
Tokenanting
Token ID20482
Feature activation+6.20e-01

Pos logit contributions
ranch+0.174
otten+0.151
hammad+0.149
athered+0.147
 fir+0.147
Neg logit contributions
isphere-0.255
ethe-0.254
ITY-0.248
ities-0.244
oir-0.230
Token it
Token ID340
Feature activation-3.93e-02

Pos logit contributions
ranch+1.440
otten+1.316
 fir+1.311
hammad+1.304
athered+1.291
Neg logit contributions
isphere-1.097
ethe-1.064
ITY-1.032
ities-1.003
oir-0.934
Token into
Token ID656
Feature activation-4.97e-02

Pos logit contributions
isphere+0.060
ethe+0.059
ITY+0.057
ities+0.055
oir+0.050
Neg logit contributions
ranch-0.101
otten-0.092
 fir-0.092
hammad-0.092
athered-0.091
Token a
Token ID257
Feature activation-5.04e-03

Pos logit contributions
isphere+0.096
ethe+0.094
ITY+0.091
ities+0.089
agraph+0.083
Neg logit contributions
ranch-0.108
otten-0.098
hammad-0.098
 fir-0.097
ulla-0.096
Token person
Token ID1048
Feature activation-1.59e-02

Pos logit contributions
isphere+0.009
ethe+0.009
ITY+0.009
ities+0.009
agraph+0.008
Neg logit contributions
ranch-0.012
otten-0.011
 fir-0.010
hammad-0.010
ulla-0.010
Token,
Token ID11
Feature activation-3.49e-04

Pos logit contributions
isphere+0.024
ethe+0.024
ITY+0.023
ities+0.022
agraph+0.020
Neg logit contributions
ranch-0.041
otten-0.038
hammad-0.038
 fir-0.037
athered-0.037
Token wrote
Token ID2630
Feature activation+9.65e-02

Pos logit contributions
isphere+0.053
ethe+0.053
ITY+0.051
ities+0.050
oir+0.046
Neg logit contributions
ranch-0.072
otten-0.066
hammad-0.065
 fir-0.064
athered-0.064
Token:
Token ID25
Feature activation-1.30e-02

Pos logit contributions
ranch+0.282
otten+0.261
hammad+0.258
 fir+0.258
athered+0.256
Neg logit contributions
isphere-0.115
ethe-0.113
ITY-0.107
ities-0.102
agraph-0.092
Token
Token ID198
Feature activation+9.05e-02

Pos logit contributions
isphere+0.025
ethe+0.025
ITY+0.024
ities+0.023
agraph+0.022
Neg logit contributions
ranch-0.029
otten-0.026
hammad-0.025
 fir-0.025
athered-0.025
Token
Token ID198
Feature activation+9.35e-02

Pos logit contributions
ranch+0.200
otten+0.180
hammad+0.178
 fir+0.176
athered+0.175
Neg logit contributions
isphere-0.173
ethe-0.171
ITY-0.165
ities-0.162
agraph-0.151
TokenCl
Token ID2601
Feature activation+1.14e-01

Pos logit contributions
ranch+0.214
otten+0.192
hammad+0.190
athered+0.189
 fir+0.188
Neg logit contributions
isphere-0.170
ethe-0.169
ITY-0.163
ities-0.160
oir-0.148
Tokenarity
Token ID6806
Feature activation+6.18e-01

Pos logit contributions
ranch+0.169
otten+0.144
hammad+0.142
athered+0.140
 fir+0.138
Neg logit contributions
isphere-0.299
ethe-0.298
ITY-0.291
ities-0.287
oir-0.272
Token Gaming
Token ID14426
Feature activation+1.44e-02

Pos logit contributions
ranch+1.388
 fir+1.257
otten+1.254
hammad+1.243
ulla+1.232
Neg logit contributions
isphere-1.131
ethe-1.130
ITY-1.083
ities-1.055
oir-0.995
Token will
Token ID481
Feature activation+3.38e-02

Pos logit contributions
ranch+0.031
otten+0.028
hammad+0.028
 fir+0.028
athered+0.028
Neg logit contributions
isphere-0.028
ethe-0.028
ITY-0.027
ities-0.026
agraph-0.024
Token also
Token ID635
Feature activation+5.90e-02

Pos logit contributions
ranch+0.085
otten+0.077
hammad+0.077
 fir+0.076
ulla+0.076
Neg logit contributions
isphere-0.054
ethe-0.054
ITY-0.052
ities-0.050
agraph-0.046
Token be
Token ID307
Feature activation-2.64e-02

Pos logit contributions
ranch+0.110
otten+0.097
hammad+0.096
 fir+0.096
athered+0.095
Neg logit contributions
isphere-0.132
ethe-0.131
ITY-0.128
ities-0.125
agraph-0.118
Token releasing
Token ID13011
Feature activation+9.78e-02

Pos logit contributions
isphere+0.059
ethe+0.058
ITY+0.057
ities+0.056
oir+0.052
Neg logit contributions
ranch-0.050
otten-0.044
 fir-0.044
hammad-0.044
ulla-0.043
TokenIf
Token ID1532
Feature activation+8.28e-02

Pos logit contributions
isphere+0.020
ethe+0.020
ITY+0.019
ities+0.019
agraph+0.017
Neg logit contributions
ranch-0.028
otten-0.025
hammad-0.025
athered-0.025
ulla-0.025
Token Lee
Token ID5741
Feature activation+7.54e-02

Pos logit contributions
ranch+0.187
otten+0.171
hammad+0.169
 fir+0.168
athered+0.167
Neg logit contributions
isphere-0.152
ethe-0.150
ITY-0.145
ities-0.143
oir-0.131
Token ends
Token ID5645
Feature activation-2.30e-01

Pos logit contributions
ranch+0.158
otten+0.143
 fir+0.141
hammad+0.141
athered+0.140
Neg logit contributions
isphere-0.150
ethe-0.149
ITY-0.145
ities-0.142
agraph-0.132
Token up
Token ID510
Feature activation-4.70e-02

Pos logit contributions
isphere+0.422
ethe+0.413
ITY+0.402
ities+0.394
oir+0.366
Neg logit contributions
ranch-0.524
otten-0.476
hammad-0.470
 fir-0.468
athered-0.466
Token impl
Token ID4114
Feature activation+9.30e-02

Pos logit contributions
isphere+0.095
ethe+0.095
ITY+0.092
ities+0.090
oir+0.085
Neg logit contributions
ranch-0.097
otten-0.087
 fir-0.086
hammad-0.086
athered-0.086
Tokenanting
Token ID20482
Feature activation+6.13e-01

Pos logit contributions
ranch+0.153
otten+0.134
hammad+0.131
athered+0.130
ulla+0.129
Neg logit contributions
isphere-0.229
ethe-0.228
ITY-0.223
ities-0.219
agraph-0.206
Token the
Token ID262
Feature activation+7.38e-02

Pos logit contributions
ranch+1.320
otten+1.198
hammad+1.190
 fir+1.188
ulla+1.177
Neg logit contributions
isphere-1.187
ethe-1.165
ITY-1.133
ities-1.111
oir-1.032
Token Love
Token ID5896
Feature activation-1.13e-01

Pos logit contributions
ranch+0.164
otten+0.148
hammad+0.147
 fir+0.146
athered+0.145
Neg logit contributions
isphere-0.139
ethe-0.138
ITY-0.133
ities-0.131
oir-0.121
Tokent
Token ID83
Feature activation-5.14e-02

Pos logit contributions
isphere+0.212
ethe+0.211
ITY+0.206
ities+0.201
agraph+0.185
Neg logit contributions
ranch-0.250
otten-0.226
hammad-0.223
 fir-0.221
athered-0.221
Tokenron
Token ID1313
Feature activation+1.04e-01

Pos logit contributions
isphere+0.106
ethe+0.106
ITY+0.103
ities+0.101
agraph+0.094
Neg logit contributions
ranch-0.105
otten-0.093
hammad-0.092
athered-0.091
ulla-0.091
Token9
Token ID24
Feature activation-2.10e-02

Pos logit contributions
ranch+0.225
otten+0.202
hammad+0.199
 fir+0.199
athered+0.197
Neg logit contributions
isphere-0.203
ethe-0.202
ITY-0.196
ities-0.192
oir-0.177
Token
Token ID198
Feature activation+1.91e-02

Pos logit contributions
ranch+0.053
otten+0.048
hammad+0.047
 fir+0.047
athered+0.046
Neg logit contributions
isphere-0.045
ethe-0.045
ITY-0.043
ities-0.043
agraph-0.040
TokenS
Token ID50
Feature activation+3.19e-02

Pos logit contributions
ranch+0.043
otten+0.039
hammad+0.038
athered+0.038
 fir+0.038
Neg logit contributions
isphere-0.035
ethe-0.035
ITY-0.034
ities-0.033
agraph-0.031
Tokenovere
Token ID33518
Feature activation+8.21e-02

Pos logit contributions
ranch+0.065
otten+0.058
hammad+0.057
athered+0.056
 fir+0.056
Neg logit contributions
isphere-0.066
ethe-0.066
ITY-0.064
ities-0.063
agraph-0.059
Tokenign
Token ID570
Feature activation-5.31e-01

Pos logit contributions
ranch+0.187
otten+0.169
hammad+0.168
athered+0.167
 fir+0.166
Neg logit contributions
isphere-0.150
ethe-0.149
ITY-0.144
ities-0.141
oir-0.130
Token Lux
Token ID17145
Feature activation-1.62e-01

Pos logit contributions
isphere+1.039
ethe+1.035
ITY+1.005
ities+0.987
oir+0.913
Neg logit contributions
ranch-1.138
otten-1.021
hammad-1.013
 fir-1.003
athered-1.001
Tokenury
Token ID1601
Feature activation+6.11e-01

Pos logit contributions
isphere+0.413
ethe+0.412
ITY+0.402
ities+0.396
oir+0.373
Neg logit contributions
ranch-0.253
otten-0.217
hammad-0.214
 fir-0.211
athered-0.210
Token Travel
Token ID13524
Feature activation-1.91e-01

Pos logit contributions
ranch+1.323
otten+1.180
 fir+1.174
hammad+1.170
athered+1.165
Neg logit contributions
isphere-1.182
ethe-1.179
ITY-1.130
ities-1.102
agraph-1.030
Token (
Token ID357
Feature activation-2.12e-02

Pos logit contributions
isphere+0.363
ethe+0.362
ITY+0.351
ities+0.344
oir+0.318
Neg logit contributions
ranch-0.421
otten-0.379
hammad-0.376
 fir-0.372
athered-0.372
Token08
Token ID2919
Feature activation-5.25e-02

Pos logit contributions
isphere+0.040
ethe+0.039
ITY+0.038
ities+0.038
oir+0.035
Neg logit contributions
ranch-0.048
otten-0.043
hammad-0.042
athered-0.042
 fir-0.042
Token44
Token ID2598
Feature activation+4.31e-02

Pos logit contributions
isphere+0.097
ethe+0.096
ITY+0.093
ities+0.091
agraph+0.084
Neg logit contributions
ranch-0.118
otten-0.107
hammad-0.106
 fir-0.105
athered-0.105
Token 415
Token ID40643
Feature activation+9.52e-02

Pos logit contributions
ranch+0.097
otten+0.088
hammad+0.087
 fir+0.087
athered+0.086
Neg logit contributions
isphere-0.080
ethe-0.079
ITY-0.076
ities-0.075
agraph-0.069
Token regarding
Token ID5115
Feature activation-4.82e-02

Pos logit contributions
isphere+0.067
ethe+0.067
ITY+0.065
ities+0.063
oir+0.058
Neg logit contributions
ranch-0.089
otten-0.081
 fir-0.080
hammad-0.080
athered-0.079
Token the
Token ID262
Feature activation+2.63e-02

Pos logit contributions
isphere+0.091
ethe+0.090
ITY+0.088
ities+0.086
agraph+0.079
Neg logit contributions
ranch-0.107
otten-0.096
hammad-0.095
 fir-0.095
athered-0.094
Token future
Token ID2003
Feature activation+3.86e-02

Pos logit contributions
ranch+0.057
otten+0.051
hammad+0.050
 fir+0.050
athered+0.050
Neg logit contributions
isphere-0.051
ethe-0.051
ITY-0.049
ities-0.049
oir-0.045
Token of
Token ID286
Feature activation+2.73e-02

Pos logit contributions
ranch+0.083
otten+0.074
 fir+0.074
hammad+0.073
athered+0.072
Neg logit contributions
ethe-0.075
isphere-0.074
ITY-0.073
ities-0.071
agraph-0.066
Token Cl
Token ID1012
Feature activation-3.77e-02

Pos logit contributions
ranch+0.065
otten+0.059
hammad+0.058
 fir+0.058
athered+0.058
Neg logit contributions
isphere-0.047
ethe-0.047
ITY-0.046
ities-0.045
agraph-0.041
Tokenarity
Token ID6806
Feature activation+6.09e-01

Pos logit contributions
isphere+0.097
ethe+0.097
ITY+0.095
ities+0.094
oir+0.088
Neg logit contributions
ranch-0.057
otten-0.049
hammad-0.048
 fir-0.048
athered-0.048
Token Gaming
Token ID14426
Feature activation+4.18e-02

Pos logit contributions
ranch+1.455
otten+1.316
 fir+1.311
hammad+1.300
ulla+1.292
Neg logit contributions
isphere-1.026
ethe-1.021
ITY-0.983
ities-0.960
oir-0.891
Token Cl
Token ID1012
Feature activation-5.44e-03

Pos logit contributions
ranch+0.109
otten+0.099
 fir+0.098
hammad+0.098
athered+0.097
Neg logit contributions
isphere-0.063
ethe-0.063
ITY-0.060
ities-0.059
agraph-0.053
Tokenarity
Token ID6806
Feature activation+6.08e-01

Pos logit contributions
isphere+0.014
ethe+0.014
ITY+0.014
ities+0.014
oir+0.013
Neg logit contributions
ranch-0.008
otten-0.007
hammad-0.007
 fir-0.007
athered-0.007
Token Gaming
Token ID14426
Feature activation+9.14e-02

Pos logit contributions
ranch+1.395
otten+1.258
hammad+1.252
 fir+1.250
ulla+1.237
Neg logit contributions
ethe-1.083
isphere-1.083
ITY-1.041
ities-1.018
oir-0.953
Token will
Token ID481
Feature activation-6.42e-03

Pos logit contributions
ranch+0.199
otten+0.179
hammad+0.177
 fir+0.177
athered+0.176
Neg logit contributions
isphere-0.175
ethe-0.175
ITY-0.169
ities-0.166
oir-0.154
TokenNew
Token ID3791
Feature activation-1.48e-01

Pos logit contributions
isphere+0.040
ethe+0.040
ITY+0.038
ities+0.038
agraph+0.035
Neg logit contributions
ranch-0.049
otten-0.045
hammad-0.044
athered-0.044
 fir-0.044
Tokencastle
Token ID18676
Feature activation+3.78e-02

Pos logit contributions
isphere+0.291
ethe+0.290
ITY+0.281
ities+0.276
oir+0.256
Neg logit contributions
ranch-0.315
otten-0.282
hammad-0.279
 fir-0.278
athered-0.276
Token United
Token ID1578
Feature activation-1.27e-01

Pos logit contributions
ranch+0.079
otten+0.071
 fir+0.070
hammad+0.070
athered+0.070
Neg logit contributions
isphere-0.076
ethe-0.076
ITY-0.073
ities-0.072
agraph-0.067
Token are
Token ID389
Feature activation-2.59e-02

Pos logit contributions
isphere+0.247
ethe+0.246
ITY+0.236
ities+0.232
oir+0.217
Neg logit contributions
ranch-0.273
otten-0.245
 fir-0.244
athered-0.243
hammad-0.242
Token reintrodu
Token ID38368
Feature activation+2.96e-02

Pos logit contributions
isphere+0.054
ethe+0.053
ITY+0.052
ities+0.051
oir+0.048
Neg logit contributions
ranch-0.052
otten-0.047
 fir-0.046
hammad-0.046
athered-0.046
Tokencing
Token ID2259
Feature activation-7.41e-01

Pos logit contributions
ranch+0.056
otten+0.050
hammad+0.049
 fir+0.049
athered+0.049
Neg logit contributions
isphere-0.065
ethe-0.065
ITY-0.063
ities-0.062
oir-0.058
Token the
Token ID262
Feature activation+5.69e-03

Pos logit contributions
isphere+1.419
ethe+1.415
ITY+1.374
ities+1.348
agraph+1.245
Neg logit contributions
ranch-1.619
otten-1.457
hammad-1.445
 fir-1.429
athered-1.428
Token Club
Token ID6289
Feature activation-6.83e-02

Pos logit contributions
ranch+0.012
otten+0.011
hammad+0.011
 fir+0.011
athered+0.011
Neg logit contributions
isphere-0.011
ethe-0.011
ITY-0.011
ities-0.011
oir-0.010
Token's
Token ID338
Feature activation-2.78e-02

Pos logit contributions
isphere+0.122
ethe+0.121
ITY+0.118
ities+0.116
oir+0.107
Neg logit contributions
ranch-0.157
otten-0.143
hammad-0.141
athered-0.140
 fir-0.140
Token official
Token ID1743
Feature activation+6.69e-02

Pos logit contributions
isphere+0.055
ethe+0.055
ITY+0.053
ities+0.052
agraph+0.048
Neg logit contributions
ranch-0.059
otten-0.053
hammad-0.052
 fir-0.052
athered-0.052
Token Fans
Token ID24964
Feature activation+2.25e-03

Pos logit contributions
ranch+0.146
otten+0.131
hammad+0.130
 fir+0.130
athered+0.129
Neg logit contributions
isphere-0.129
ethe-0.128
ITY-0.124
ities-0.121
oir-0.113
Token up
Token ID510
Feature activation-1.91e-02

Pos logit contributions
ranch+0.078
 fir+0.071
otten+0.070
hammad+0.070
athered+0.069
Neg logit contributions
isphere-0.072
ethe-0.071
ITY-0.069
ities-0.068
agraph-0.063
Token to
Token ID284
Feature activation+2.78e-02

Pos logit contributions
isphere+0.036
ethe+0.036
ITY+0.035
ities+0.034
agraph+0.032
Neg logit contributions
ranch-0.042
otten-0.038
 fir-0.038
hammad-0.038
athered-0.038
Token for
Token ID329
Feature activation-2.62e-02

Pos logit contributions
ranch+0.052
otten+0.046
 fir+0.046
athered+0.045
hammad+0.045
Neg logit contributions
isphere-0.062
ethe-0.061
ITY-0.060
ities-0.059
agraph-0.055
Token prom
Token ID1552
Feature activation-2.41e-01

Pos logit contributions
isphere+0.056
ethe+0.055
ITY+0.054
ities+0.053
oir+0.049
Neg logit contributions
ranch-0.052
otten-0.046
hammad-0.046
 fir-0.045
athered-0.045
Tokenisc
Token ID2304
Feature activation-2.47e-01

Pos logit contributions
isphere+0.469
ethe+0.460
ITY+0.451
ities+0.442
agraph+0.411
Neg logit contributions
ranch-0.518
otten-0.467
hammad-0.462
 fir-0.460
ulla-0.458
Tokenuous
Token ID5623
Feature activation-7.30e-01

Pos logit contributions
isphere+0.479
ethe+0.476
ITY+0.463
ities+0.454
agraph+0.420
Neg logit contributions
ranch-0.535
otten-0.481
hammad-0.477
 fir-0.472
athered-0.472
Token behaviour
Token ID9172
Feature activation+9.08e-03

Pos logit contributions
isphere+1.423
ethe+1.420
ITY+1.380
ities+1.355
oir+1.252
Neg logit contributions
ranch-1.571
otten-1.410
hammad-1.398
athered-1.383
 fir-1.383
Token.
Token ID13
Feature activation-2.77e-02

Pos logit contributions
ranch+0.023
otten+0.021
hammad+0.021
 fir+0.021
ulla+0.021
Neg logit contributions
isphere-0.014
ethe-0.014
ITY-0.013
ities-0.013
agraph-0.012
Token
Token ID447
Feature activation+5.88e-02

Pos logit contributions
isphere+0.053
ethe+0.053
ITY+0.051
ities+0.050
agraph+0.046
Neg logit contributions
ranch-0.060
otten-0.055
hammad-0.054
 fir-0.053
ulla-0.053
Token
Token ID251
Feature activation-3.75e-02

Pos logit contributions
ranch+0.121
otten+0.108
hammad+0.107
 fir+0.106
ulla+0.106
Neg logit contributions
isphere-0.120
ethe-0.120
ITY-0.116
ities-0.114
oir-0.106
Token
Token ID198
Feature activation-2.84e-02

Pos logit contributions
isphere+0.072
ethe+0.070
ITY+0.068
ities+0.067
agraph+0.062
Neg logit contributions
ranch-0.083
otten-0.075
hammad-0.074
 fir-0.074
ulla-0.073
Tokenman
Token ID805
Feature activation-1.74e-01

Pos logit contributions
isphere+0.196
ethe+0.194
ITY+0.190
ities+0.185
oir+0.173
Neg logit contributions
ranch-0.228
otten-0.206
hammad-0.203
 fir-0.201
ulla-0.201
Token Institute
Token ID5136
Feature activation-4.93e-02

Pos logit contributions
isphere+0.314
ethe+0.312
ITY+0.302
ities+0.294
agraph+0.274
Neg logit contributions
ranch-0.401
otten-0.363
hammad-0.359
 fir-0.358
athered-0.357
Token.
Token ID13
Feature activation-4.95e-02

Pos logit contributions
isphere+0.076
ethe+0.075
ITY+0.072
ities+0.070
agraph+0.064
Neg logit contributions
ranch-0.126
otten-0.116
hammad-0.115
 fir-0.114
athered-0.114
TokenAmid
Token ID43541
Feature activation-3.02e-02

Pos logit contributions
isphere+0.092
ethe+0.091
ITY+0.088
ities+0.087
agraph+0.080
Neg logit contributions
ranch-0.111
otten-0.101
hammad-0.100
 fir-0.099
athered-0.099
Token plac
Token ID21957
Feature activation-1.06e-01

Pos logit contributions
isphere+0.055
ethe+0.055
ITY+0.053
ities+0.052
oir+0.048
Neg logit contributions
ranch-0.069
otten-0.062
hammad-0.062
 fir-0.061
athered-0.061
Tokenards
Token ID1371
Feature activation-6.03e-01

Pos logit contributions
isphere+0.247
ethe+0.245
ITY+0.243
ities+0.235
oir+0.223
Neg logit contributions
ranch-0.187
otten-0.165
hammad-0.163
ulla-0.161
athered-0.161
Token including
Token ID1390
Feature activation-1.21e-01

Pos logit contributions
isphere+1.134
ethe+1.130
ITY+1.096
ities+1.074
oir+0.992
Neg logit contributions
ranch-1.338
otten-1.206
hammad-1.197
 fir-1.186
athered-1.184
Token
Token ID564
Feature activation-7.12e-02

Pos logit contributions
isphere+0.221
ethe+0.219
ITY+0.212
ities+0.208
oir+0.192
Neg logit contributions
ranch-0.276
otten-0.250
hammad-0.248
 fir-0.246
athered-0.245
Token
Token ID250
Feature activation+1.80e-02

Pos logit contributions
isphere+0.152
ethe+0.151
ITY+0.147
ities+0.145
oir+0.135
Neg logit contributions
ranch-0.140
otten-0.125
hammad-0.123
athered-0.122
 fir-0.122
TokenThe
Token ID464
Feature activation-1.55e-02

Pos logit contributions
ranch+0.041
otten+0.037
hammad+0.037
athered+0.036
 fir+0.036
Neg logit contributions
isphere-0.033
ethe-0.032
ITY-0.031
ities-0.031
agraph-0.029
Token Future
Token ID10898
Feature activation+6.32e-02

Pos logit contributions
isphere+0.030
ethe+0.030
ITY+0.029
ities+0.028
agraph+0.026
Neg logit contributions
ranch-0.033
otten-0.030
hammad-0.030
 fir-0.030
athered-0.030
Token000
Token ID830
Feature activation+2.86e-02

Pos logit contributions
isphere+0.044
ethe+0.043
ITY+0.042
ities+0.041
agraph+0.039
Neg logit contributions
ranch-0.042
otten-0.038
hammad-0.037
 fir-0.037
athered-0.037
Token crore
Token ID22306
Feature activation-1.07e-02

Pos logit contributions
ranch+0.070
otten+0.063
hammad+0.063
 fir+0.063
athered+0.063
Neg logit contributions
isphere-0.048
ethe-0.047
ITY-0.045
ities-0.044
agraph-0.041
Token has
Token ID468
Feature activation+6.18e-02

Pos logit contributions
isphere+0.021
ethe+0.021
ITY+0.020
ities+0.020
agraph+0.019
Neg logit contributions
ranch-0.023
otten-0.020
hammad-0.020
 fir-0.020
athered-0.020
Token been
Token ID587
Feature activation+4.59e-02

Pos logit contributions
ranch+0.111
otten+0.098
hammad+0.097
 fir+0.096
athered+0.096
Neg logit contributions
isphere-0.142
ethe-0.141
ITY-0.138
ities-0.135
agraph-0.127
Token vandal
Token ID26271
Feature activation+6.00e-02

Pos logit contributions
ranch+0.074
otten+0.064
hammad+0.063
 fir+0.063
athered+0.063
Neg logit contributions
isphere-0.114
ethe-0.114
ITY-0.111
ities-0.109
agraph-0.103
Tokenized
Token ID1143
Feature activation-5.89e-01

Pos logit contributions
ranch+0.150
otten+0.136
hammad+0.135
athered+0.135
 fir+0.135
Neg logit contributions
isphere-0.097
ethe-0.096
ITY-0.092
ities-0.089
agraph-0.082
Token in
Token ID287
Feature activation+5.29e-03

Pos logit contributions
isphere+1.130
ethe+1.126
ITY+1.093
ities+1.071
agraph+0.991
Neg logit contributions
ranch-1.285
otten-1.157
hammad-1.147
 fir-1.137
athered-1.135
Token Roh
Token ID32694
Feature activation-1.82e-01

Pos logit contributions
ranch+0.011
otten+0.010
hammad+0.010
 fir+0.010
athered+0.010
Neg logit contributions
isphere-0.011
ethe-0.011
ITY-0.010
ities-0.010
oir-0.010
Tokent
Token ID83
Feature activation-3.81e-02

Pos logit contributions
isphere+0.334
ethe+0.333
ITY+0.323
ities+0.317
oir+0.292
Neg logit contributions
ranch-0.410
otten-0.370
hammad-0.367
 fir-0.364
athered-0.363
Tokenak
Token ID461
Feature activation+4.58e-02

Pos logit contributions
isphere+0.098
ethe+0.098
ITY+0.096
ities+0.094
agraph+0.089
Neg logit contributions
ranch-0.058
otten-0.050
hammad-0.049
 fir-0.049
athered-0.048
Token and
Token ID290
Feature activation-2.36e-02

Pos logit contributions
ranch+0.101
otten+0.091
hammad+0.090
 fir+0.090
ulla+0.089
Neg logit contributions
isphere-0.087
ethe-0.087
ITY-0.084
ities-0.082
agraph-0.076
Token P
Token ID350
Feature activation+3.63e-02

Pos logit contributions
isphere+0.330
ethe+0.329
ITY+0.319
ities+0.313
oir+0.291
Neg logit contributions
ranch-0.351
otten-0.314
hammad-0.312
 fir-0.309
athered-0.308
TokenAND
Token ID6981
Feature activation-1.12e-01

Pos logit contributions
ranch+0.082
otten+0.074
hammad+0.073
athered+0.073
ucket+0.073
Neg logit contributions
isphere-0.067
ethe-0.067
ITY-0.063
ities-0.062
agraph-0.058
TokenEM
Token ID3620
Feature activation-1.37e-01

Pos logit contributions
ethe+0.169
isphere+0.168
ities+0.156
ITY+0.156
oir+0.141
Neg logit contributions
ranch-0.289
otten-0.265
hammad-0.262
athered-0.260
 fir-0.260
TokenIC
Token ID2149
Feature activation-6.03e-02

Pos logit contributions
isphere+0.238
ethe+0.237
ities+0.224
ITY+0.223
agraph+0.206
Neg logit contributions
ranch-0.323
otten-0.294
 fir-0.290
hammad-0.289
athered-0.289
Token AL
Token ID8355
Feature activation+6.72e-04

Pos logit contributions
isphere+0.103
ethe+0.103
ITY+0.097
ities+0.096
agraph+0.088
Neg logit contributions
ranch-0.144
otten-0.131
hammad-0.130
 fir-0.130
ulla-0.129
TokenERT
Token ID17395
Feature activation-5.86e-01

Pos logit contributions
ranch+0.002
otten+0.002
hammad+0.002
 fir+0.002
ulla+0.002
Neg logit contributions
isphere-0.001
ethe-0.001
ITY-0.001
ities-0.001
agraph-0.001
Token PH
Token ID9370
Feature activation-1.46e-01

Pos logit contributions
isphere+1.040
ethe+1.036
ITY+1.001
ities+0.981
agraph+0.901
Neg logit contributions
ranch-1.365
otten-1.236
hammad-1.227
 fir-1.216
athered-1.214
TokenAS
Token ID1921
Feature activation-2.58e-01

Pos logit contributions
isphere+0.235
ethe+0.235
ITY+0.221
ities+0.219
agraph+0.199
Neg logit contributions
ranch-0.365
otten-0.333
hammad-0.330
 fir-0.327
ucket-0.326
TokenES
Token ID1546
Feature activation-3.03e-01

Pos logit contributions
isphere+0.364
ethe+0.361
ITY+0.335
ities+0.335
agraph+0.307
Neg logit contributions
ranch-0.690
otten-0.636
hammad-0.628
 fir-0.627
ulla-0.624
Token Phase
Token ID18983
Feature activation-7.12e-02

Pos logit contributions
isphere+0.567
ethe+0.565
ITY+0.541
ities+0.533
agraph+0.495
Neg logit contributions
ranch-0.675
otten-0.610
hammad-0.605
 fir-0.602
athered-0.598
Token 1
Token ID352
Feature activation+3.69e-02

Pos logit contributions
isphere+0.140
ethe+0.140
ITY+0.136
ities+0.133
agraph+0.124
Neg logit contributions
ranch-0.152
otten-0.135
hammad-0.134
 fir-0.134
athered-0.133
Token immortal
Token ID26156
Feature activation+1.19e-01

Pos logit contributions
isphere+0.461
ethe+0.459
ITY+0.445
ities+0.436
oir+0.403
Neg logit contributions
ranch-0.543
otten-0.489
hammad-0.485
 fir-0.481
athered-0.480
Token eld
Token ID18441
Feature activation+4.04e-02

Pos logit contributions
ranch+0.256
otten+0.231
hammad+0.228
 fir+0.227
athered+0.226
Neg logit contributions
isphere-0.232
ethe-0.230
ITY-0.223
ities-0.219
agraph-0.204
Tokenritch
Token ID46510
Feature activation+1.20e-01

Pos logit contributions
ranch+0.073
otten+0.064
hammad+0.064
 fir+0.063
athered+0.063
Neg logit contributions
isphere-0.093
ethe-0.092
ITY-0.090
ities-0.088
agraph-0.083
Token mon
Token ID937
Feature activation-1.98e-02

Pos logit contributions
ranch+0.230
otten+0.205
hammad+0.202
 fir+0.201
athered+0.200
Neg logit contributions
isphere-0.259
ethe-0.258
ITY-0.251
ities-0.246
agraph-0.231
Tokenstros
Token ID48288
Feature activation-1.38e-01

Pos logit contributions
isphere+0.019
ethe+0.019
ITY+0.018
ities+0.017
agraph+0.014
Neg logit contributions
ranch-0.062
otten-0.058
hammad-0.057
athered-0.057
ulla-0.057
Tokenities
Token ID871
Feature activation-5.84e-01

Pos logit contributions
isphere+0.028
ethe+0.027
ITY+0.014
ities+0.001
agraph-0.006
Neg logit contributions
ranch-0.535
otten-0.506
hammad-0.502
athered-0.501
ulla-0.500
Token year
Token ID614
Feature activation-3.28e-02

Pos logit contributions
isphere+1.060
ethe+1.055
ITY+1.022
ities+1.000
agraph+0.922
Neg logit contributions
ranch-1.332
otten-1.206
hammad-1.196
 fir-1.187
athered-1.184
Token after
Token ID706
Feature activation-1.07e-01

Pos logit contributions
isphere+0.053
ethe+0.053
ITY+0.051
ities+0.050
agraph+0.046
Neg logit contributions
ranch-0.081
otten-0.074
hammad-0.073
 fir-0.073
athered-0.073
Token year
Token ID614
Feature activation+4.65e-03

Pos logit contributions
isphere+0.263
ethe+0.263
ITY+0.256
ities+0.252
oir+0.238
Neg logit contributions
ranch-0.176
otten-0.153
hammad-0.151
 fir-0.151
athered-0.149
Token and
Token ID290
Feature activation+9.83e-03

Pos logit contributions
ranch+0.012
otten+0.011
 fir+0.011
hammad+0.011
athered+0.011
Neg logit contributions
isphere-0.007
ethe-0.007
ITY-0.007
ities-0.007
agraph-0.006
Token held
Token ID2714
Feature activation-3.92e-02

Pos logit contributions
ranch+0.019
otten+0.017
 fir+0.017
athered+0.017
hammad+0.017
Neg logit contributions
isphere-0.021
ethe-0.021
ITY-0.020
ities-0.020
oir-0.019
Token front
Token ID2166
Feature activation-3.27e-02

Pos logit contributions
ranch+0.033
otten+0.029
hammad+0.029
 fir+0.029
athered+0.029
Neg logit contributions
isphere-0.036
ethe-0.035
ITY-0.035
ities-0.034
oir-0.032
Token of
Token ID286
Feature activation+7.63e-02

Pos logit contributions
isphere+0.063
ethe+0.063
ITY+0.061
ities+0.060
oir+0.055
Neg logit contributions
ranch-0.071
otten-0.064
hammad-0.063
 fir-0.063
athered-0.063
Token the
Token ID262
Feature activation+1.82e-02

Pos logit contributions
ranch+0.161
otten+0.144
hammad+0.143
 fir+0.142
athered+0.142
Neg logit contributions
isphere-0.152
ethe-0.151
ITY-0.146
ities-0.144
agraph-0.134
Token Shaw
Token ID18193
Feature activation-8.77e-02

Pos logit contributions
ranch+0.037
otten+0.033
hammad+0.033
 fir+0.033
athered+0.033
Neg logit contributions
isphere-0.037
ethe-0.037
ITY-0.036
ities-0.035
agraph-0.033
Token Amen
Token ID34717
Feature activation+2.66e-02

Pos logit contributions
isphere+0.166
ethe+0.166
ITY+0.161
ities+0.157
agraph+0.146
Neg logit contributions
ranch-0.193
otten-0.174
hammad-0.172
 fir-0.171
ulla-0.171
Tokenities
Token ID871
Feature activation-5.80e-01

Pos logit contributions
ranch+0.088
hammad+0.082
otten+0.082
ulla+0.081
athered+0.081
Neg logit contributions
isphere-0.021
ethe-0.020
ITY-0.018
ities-0.016
agraph-0.014
Token Building
Token ID11819
Feature activation-8.97e-02

Pos logit contributions
isphere+1.076
ethe+1.071
ITY+1.037
ities+1.016
agraph+0.938
Neg logit contributions
ranch-1.306
otten-1.176
hammad-1.168
 fir-1.159
athered-1.156
Token,
Token ID11
Feature activation+5.49e-02

Pos logit contributions
isphere+0.154
ethe+0.152
ITY+0.147
ities+0.144
agraph+0.132
Neg logit contributions
ranch-0.215
otten-0.195
hammad-0.193
 fir-0.192
athered-0.192
Token also
Token ID635
Feature activation+2.84e-02

Pos logit contributions
ranch+0.118
otten+0.106
hammad+0.105
 fir+0.103
athered+0.103
Neg logit contributions
isphere-0.108
ethe-0.107
ITY-0.104
ities-0.102
agraph-0.095
Token called
Token ID1444
Feature activation-1.39e-01

Pos logit contributions
ranch+0.060
otten+0.054
hammad+0.053
 fir+0.053
athered+0.053
Neg logit contributions
isphere-0.056
ethe-0.056
ITY-0.055
ities-0.053
oir-0.050
Token
Token ID564
Feature activation+1.67e-02

Pos logit contributions
isphere+0.274
ethe+0.271
ITY+0.264
ities+0.259
oir+0.240
Neg logit contributions
ranch-0.299
otten-0.268
hammad-0.265
 fir-0.263
athered-0.262
Token if
Token ID611
Feature activation+6.45e-02

Pos logit contributions
isphere+0.031
ethe+0.031
ITY+0.030
ities+0.029
oir+0.027
Neg logit contributions
ranch-0.036
otten-0.033
hammad-0.033
 fir-0.032
athered-0.032
Token this
Token ID428
Feature activation-5.61e-02

Pos logit contributions
ranch+0.152
otten+0.138
 fir+0.137
hammad+0.137
athered+0.135
Neg logit contributions
isphere-0.113
ethe-0.111
ITY-0.108
ities-0.105
agraph-0.097
Token cemetery
Token ID27316
Feature activation+6.96e-02

Pos logit contributions
isphere+0.104
ethe+0.103
ITY+0.100
ities+0.098
agraph+0.091
Neg logit contributions
ranch-0.126
otten-0.114
 fir-0.113
hammad-0.113
athered-0.112
Token was
Token ID373
Feature activation-3.96e-02

Pos logit contributions
ranch+0.155
otten+0.139
hammad+0.138
 fir+0.137
athered+0.137
Neg logit contributions
isphere-0.131
ethe-0.130
ITY-0.126
ities-0.124
agraph-0.114
Token vandal
Token ID26271
Feature activation+9.84e-02

Pos logit contributions
isphere+0.082
ethe+0.081
ITY+0.079
ities+0.078
agraph+0.072
Neg logit contributions
ranch-0.081
otten-0.072
hammad-0.071
 fir-0.071
athered-0.070
Tokenized
Token ID1143
Feature activation-5.67e-01

Pos logit contributions
ranch+0.250
otten+0.228
 fir+0.226
hammad+0.226
athered+0.225
Neg logit contributions
isphere-0.153
ethe-0.153
ITY-0.146
ities-0.142
agraph-0.130
Token and
Token ID290
Feature activation+7.74e-03

Pos logit contributions
isphere+0.995
ethe+0.990
ITY+0.958
ities+0.937
agraph+0.860
Neg logit contributions
ranch-1.329
otten-1.205
hammad-1.196
 fir-1.187
athered-1.184
Token what
Token ID644
Feature activation+3.62e-02

Pos logit contributions
ranch+0.016
otten+0.014
 fir+0.014
hammad+0.014
athered+0.014
Neg logit contributions
isphere-0.016
ethe-0.016
ITY-0.016
ities-0.015
agraph-0.014
Token's
Token ID338
Feature activation+1.03e-02

Pos logit contributions
ranch+0.077
otten+0.069
 fir+0.069
hammad+0.069
athered+0.068
Neg logit contributions
isphere-0.071
ethe-0.071
ITY-0.069
ities-0.067
agraph-0.063
Token going
Token ID1016
Feature activation-1.85e-02

Pos logit contributions
ranch+0.022
otten+0.020
 fir+0.020
hammad+0.019
athered+0.019
Neg logit contributions
isphere-0.020
ethe-0.020
ITY-0.020
ities-0.019
agraph-0.018
Token on
Token ID319
Feature activation-1.84e-02

Pos logit contributions
isphere+0.031
ethe+0.031
ITY+0.030
ities+0.029
agraph+0.027
Neg logit contributions
ranch-0.044
otten-0.041
hammad-0.040
 fir-0.040
athered-0.040
Token one
Token ID530
Feature activation+7.24e-03

Pos logit contributions
ranch+0.035
otten+0.031
 fir+0.031
hammad+0.031
athered+0.031
Neg logit contributions
isphere-0.031
ethe-0.031
ITY-0.030
ities-0.030
agraph-0.028
Token of
Token ID286
Feature activation+6.17e-02

Pos logit contributions
ranch+0.016
otten+0.014
hammad+0.014
 fir+0.014
athered+0.014
Neg logit contributions
isphere-0.014
ethe-0.014
ITY-0.014
ities-0.013
oir-0.012
Token the
Token ID262
Feature activation+1.96e-02

Pos logit contributions
ranch+0.126
otten+0.113
hammad+0.112
 fir+0.112
athered+0.111
Neg logit contributions
isphere-0.127
ethe-0.126
ITY-0.122
ities-0.120
oir-0.112
Token st
Token ID336
Feature activation+1.60e-01

Pos logit contributions
ranch+0.041
otten+0.037
 fir+0.037
athered+0.036
hammad+0.036
Neg logit contributions
isphere-0.039
ethe-0.039
ITY-0.038
ities-0.037
oir-0.035
Tokenaun
Token ID1942
Feature activation+4.31e-02

Pos logit contributions
ranch+0.278
otten+0.243
hammad+0.241
 fir+0.238
athered+0.237
Neg logit contributions
isphere-0.377
ethe-0.376
ITY-0.367
ities-0.361
oir-0.339
Tokenchest
Token ID46713
Feature activation-5.66e-01

Pos logit contributions
ranch+0.108
otten+0.099
 fir+0.097
hammad+0.097
athered+0.097
Neg logit contributions
isphere-0.069
ethe-0.068
ITY-0.066
ities-0.064
agraph-0.058
Token supporters
Token ID5941
Feature activation-1.97e-01

Pos logit contributions
isphere+0.805
ethe+0.801
ITY+0.770
ities+0.748
agraph+0.672
Neg logit contributions
ranch-1.517
otten-1.392
hammad-1.382
 fir-1.375
athered-1.371
Token of
Token ID286
Feature activation-7.66e-02

Pos logit contributions
isphere+0.380
ethe+0.379
ITY+0.368
ities+0.361
oir+0.334
Neg logit contributions
ranch-0.427
otten-0.383
hammad-0.380
 fir-0.376
athered-0.376
Token Trump
Token ID1301
Feature activation-5.95e-02

Pos logit contributions
isphere+0.155
ethe+0.154
ITY+0.150
ities+0.147
oir+0.137
Neg logit contributions
ranch-0.160
otten-0.143
hammad-0.142
 fir-0.141
athered-0.140
Token's
Token ID338
Feature activation+7.22e-02

Pos logit contributions
isphere+0.097
ethe+0.097
ITY+0.093
ities+0.091
agraph+0.083
Neg logit contributions
ranch-0.146
otten-0.134
hammad-0.133
 fir-0.132
athered-0.131
Token hard
Token ID1327
Feature activation-9.60e-03

Pos logit contributions
ranch+0.156
otten+0.140
 fir+0.139
hammad+0.139
athered+0.138
Neg logit contributions
isphere-0.140
ethe-0.140
ITY-0.134
ities-0.131
agraph-0.123
Token of
Token ID286
Feature activation+2.24e-02

Pos logit contributions
isphere+0.107
ethe+0.107
ITY+0.103
ities+0.101
agraph+0.092
Neg logit contributions
ranch-0.158
otten-0.144
hammad-0.143
 fir-0.142
ulla-0.141
Token her
Token ID607
Feature activation+4.40e-03

Pos logit contributions
ranch+0.047
otten+0.042
hammad+0.042
 fir+0.041
athered+0.041
Neg logit contributions
isphere-0.045
ethe-0.045
ITY-0.044
ities-0.043
agraph-0.040
Token r
Token ID374
Feature activation+5.45e-02

Pos logit contributions
ranch+0.010
otten+0.009
 fir+0.009
hammad+0.009
ulla+0.009
Neg logit contributions
isphere-0.008
ethe-0.008
ITY-0.008
ities-0.008
agraph-0.007
Tokenhe
Token ID258
Feature activation+2.45e-01

Pos logit contributions
ranch+0.069
otten+0.057
hammad+0.057
 fir+0.056
athered+0.055
Neg logit contributions
isphere-0.154
ethe-0.154
ITY-0.151
ities-0.149
oir-0.141
Tokenumat
Token ID27798
Feature activation-9.68e-02

Pos logit contributions
ranch+0.433
otten+0.379
hammad+0.374
 fir+0.370
athered+0.369
Neg logit contributions
isphere-0.571
ethe-0.570
ITY-0.557
ities-0.546
agraph-0.513
Tokenoid
Token ID1868
Feature activation-5.58e-01

Pos logit contributions
isphere+0.103
ethe+0.102
ITY+0.097
ities+0.092
oir+0.080
Neg logit contributions
ranch-0.294
otten-0.272
hammad-0.270
athered-0.269
ulla-0.269
Token arthritis
Token ID37954
Feature activation+4.45e-02

Pos logit contributions
isphere+1.225
ethe+1.219
ITY+1.194
ities+1.186
agraph+1.087
Neg logit contributions
ranch-1.049
hammad-0.938
otten-0.938
athered-0.913
ashington-0.907
Token.
Token ID13
Feature activation+3.30e-03

Pos logit contributions
ranch+0.117
otten+0.107
hammad+0.107
 fir+0.106
athered+0.106
Neg logit contributions
isphere-0.065
ethe-0.065
ITY-0.062
ities-0.060
agraph-0.055
Token Trying
Token ID31165
Feature activation+8.53e-02

Pos logit contributions
ranch+0.007
otten+0.006
hammad+0.006
 fir+0.006
athered+0.006
Neg logit contributions
isphere-0.007
ethe-0.007
ITY-0.006
ities-0.006
agraph-0.006
Token to
Token ID284
Feature activation+9.48e-02

Pos logit contributions
ranch+0.186
otten+0.167
hammad+0.165
 fir+0.164
athered+0.164
Neg logit contributions
isphere-0.164
ethe-0.163
ITY-0.159
ities-0.155
oir-0.144
Token keep
Token ID1394
Feature activation+6.19e-02

Pos logit contributions
ranch+0.173
otten+0.150
 fir+0.149
athered+0.149
hammad+0.148
Neg logit contributions
isphere-0.217
ethe-0.216
ITY-0.211
ities-0.206
agraph-0.194
Token ag
Token ID556
Feature activation+1.03e-01

Pos logit contributions
ranch+0.023
otten+0.021
hammad+0.021
 fir+0.021
athered+0.021
Neg logit contributions
isphere-0.021
ethe-0.021
ITY-0.020
ities-0.020
oir-0.018
Tokenit
Token ID270
Feature activation+1.55e-01

Pos logit contributions
ranch+0.235
otten+0.211
hammad+0.210
athered+0.208
 fir+0.208
Neg logit contributions
isphere-0.188
ethe-0.187
ITY-0.182
ities-0.177
agraph-0.164
Tokenators
Token ID2024
Feature activation+1.50e-01

Pos logit contributions
ranch+0.381
otten+0.347
hammad+0.345
 fir+0.342
athered+0.341
Neg logit contributions
isphere-0.255
ethe-0.254
ITY-0.245
ities-0.240
agraph-0.219
Token,
Token ID11
Feature activation+6.36e-02

Pos logit contributions
ranch+0.384
otten+0.353
hammad+0.350
 fir+0.349
athered+0.347
Neg logit contributions
isphere-0.231
ethe-0.228
ITY-0.220
ities-0.213
agraph-0.194
Token vandal
Token ID26271
Feature activation+1.21e-01

Pos logit contributions
ranch+0.136
otten+0.122
hammad+0.121
 fir+0.120
athered+0.120
Neg logit contributions
isphere-0.125
ethe-0.124
ITY-0.121
ities-0.119
oir-0.110
Tokenized
Token ID1143
Feature activation-5.53e-01

Pos logit contributions
ranch+0.315
otten+0.289
hammad+0.287
 fir+0.287
ulla+0.286
Neg logit contributions
isphere-0.182
ethe-0.180
ITY-0.172
ities-0.165
agraph-0.152
Token and
Token ID290
Feature activation+1.38e-02

Pos logit contributions
isphere+0.999
ethe+0.995
ITY+0.964
ities+0.943
agraph+0.868
Neg logit contributions
ranch-1.269
otten-1.147
hammad-1.139
 fir-1.129
athered-1.127
Token set
Token ID900
Feature activation-2.20e-02

Pos logit contributions
ranch+0.025
otten+0.022
hammad+0.022
 fir+0.021
athered+0.021
Neg logit contributions
isphere-0.032
ethe-0.032
ITY-0.031
ities-0.030
agraph-0.029
Token on
Token ID319
Feature activation+2.21e-02

Pos logit contributions
isphere+0.042
ethe+0.042
ITY+0.041
ities+0.040
agraph+0.037
Neg logit contributions
ranch-0.048
otten-0.043
hammad-0.043
 fir-0.043
ulla-0.042
Token fire
Token ID2046
Feature activation+1.79e-01

Pos logit contributions
ranch+0.025
otten+0.020
hammad+0.020
 fir+0.020
athered+0.019
Neg logit contributions
isphere-0.065
ethe-0.065
ITY-0.064
ities-0.063
agraph-0.060
Token in
Token ID287
Feature activation+1.58e-02

Pos logit contributions
ranch+0.478
otten+0.438
hammad+0.437
 fir+0.435
athered+0.433
Neg logit contributions
isphere-0.258
ethe-0.254
ITY-0.245
ities-0.236
agraph-0.213
Token
Token ID851
Feature activation-5.73e-03

Pos logit contributions
isphere+0.250
ethe+0.249
ITY+0.240
ities+0.234
oir+0.215
Neg logit contributions
ranch-0.370
otten-0.338
hammad-0.334
 fir-0.333
athered-0.332
Token those
Token ID883
Feature activation-6.29e-02

Pos logit contributions
isphere+0.011
ethe+0.011
ITY+0.010
ities+0.010
oir+0.009
Neg logit contributions
ranch-0.013
otten-0.011
hammad-0.011
 fir-0.011
athered-0.011
Token uber
Token ID48110
Feature activation-6.21e-02

Pos logit contributions
isphere+0.118
ethe+0.118
ITY+0.114
ities+0.112
oir+0.104
Neg logit contributions
ranch-0.140
otten-0.126
hammad-0.124
 fir-0.124
athered-0.124
Token-
Token ID12
Feature activation+3.27e-02

Pos logit contributions
isphere+0.103
ethe+0.103
ITY+0.100
ities+0.097
oir+0.089
Neg logit contributions
ranch-0.152
otten-0.138
hammad-0.137
 fir-0.136
athered-0.136
Tokenwealth
Token ID14298
Feature activation-2.36e-02

Pos logit contributions
ranch+0.069
otten+0.061
hammad+0.060
athered+0.060
 fir+0.060
Neg logit contributions
isphere-0.066
ethe-0.066
ITY-0.064
ities-0.063
agraph-0.058
Tokeny
Token ID88
Feature activation-5.45e-01

Pos logit contributions
isphere+0.035
ethe+0.034
ITY+0.033
ities+0.032
agraph+0.029
Neg logit contributions
ranch-0.062
otten-0.057
hammad-0.056
athered-0.056
 fir-0.056
Token,
Token ID11
Feature activation+3.20e-02

Pos logit contributions
isphere+1.006
ethe+1.004
ITY+0.974
ities+0.957
oir+0.878
Neg logit contributions
ranch-1.227
otten-1.108
hammad-1.102
athered-1.086
ulla-1.085
Token climate
Token ID4258
Feature activation+6.18e-03

Pos logit contributions
ranch+0.068
otten+0.061
 fir+0.060
hammad+0.060
athered+0.060
Neg logit contributions
isphere-0.063
ethe-0.063
ITY-0.061
ities-0.060
oir-0.056
Token change
Token ID1487
Feature activation+8.61e-02

Pos logit contributions
ranch+0.014
otten+0.012
hammad+0.012
 fir+0.012
athered+0.012
Neg logit contributions
isphere-0.012
ethe-0.012
ITY-0.011
ities-0.011
agraph-0.010
Token-
Token ID12
Feature activation-7.44e-02

Pos logit contributions
ranch+0.168
otten+0.149
hammad+0.148
 fir+0.147
athered+0.146
Neg logit contributions
isphere-0.185
ethe-0.184
ITY-0.180
ities-0.176
oir-0.164
Tokenden
Token ID6559
Feature activation+1.83e-01

Pos logit contributions
isphere+0.152
ethe+0.151
ITY+0.148
ities+0.145
agraph+0.135
Neg logit contributions
ranch-0.153
otten-0.136
hammad-0.135
athered-0.134
 fir-0.133
Token
Token ID247
Feature activation-5.80e-02

Pos logit contributions
ranch+0.017
otten+0.015
hammad+0.015
 fir+0.015
athered+0.015
Neg logit contributions
isphere-0.015
ethe-0.015
ITY-0.015
ities-0.015
oir-0.014
Tokens
Token ID82
Feature activation-9.03e-02

Pos logit contributions
isphere+0.103
ethe+0.101
ITY+0.098
ities+0.096
agraph+0.088
Neg logit contributions
ranch-0.136
otten-0.123
hammad-0.122
 fir-0.121
athered-0.121
Token idea
Token ID2126
Feature activation-4.19e-03

Pos logit contributions
isphere+0.182
ethe+0.180
ITY+0.175
ities+0.171
agraph+0.160
Neg logit contributions
ranch-0.189
otten-0.170
hammad-0.168
 fir-0.167
athered-0.166
Token that
Token ID326
Feature activation-8.55e-02

Pos logit contributions
isphere+0.008
ethe+0.008
ITY+0.008
ities+0.008
agraph+0.007
Neg logit contributions
ranch-0.009
otten-0.008
hammad-0.008
 fir-0.008
ulla-0.008
Token psycho
Token ID30731
Feature activation+9.82e-02

Pos logit contributions
isphere+0.164
ethe+0.163
ITY+0.158
ities+0.155
agraph+0.144
Neg logit contributions
ranch-0.187
otten-0.168
hammad-0.167
 fir-0.165
athered-0.165
Tokenanalysis
Token ID20930
Feature activation-5.44e-01

Pos logit contributions
ranch+0.243
otten+0.222
hammad+0.221
 fir+0.219
athered+0.218
Neg logit contributions
isphere-0.159
ethe-0.158
ITY-0.153
ities-0.148
oir-0.136
Token stigmat
Token ID43603
Feature activation+2.54e-02

Pos logit contributions
isphere+1.039
ethe+1.035
ITY+1.003
ities+0.988
oir+0.910
Neg logit contributions
ranch-1.194
otten-1.071
hammad-1.065
athered-1.052
ulla-1.051
Tokenizes
Token ID4340
Feature activation-2.34e-01

Pos logit contributions
ranch+0.064
otten+0.058
hammad+0.058
athered+0.058
 fir+0.057
Neg logit contributions
isphere-0.040
ethe-0.040
ITY-0.039
ities-0.037
agraph-0.034
Token human
Token ID1692
Feature activation-1.93e-01

Pos logit contributions
isphere+0.441
ethe+0.438
ITY+0.424
ities+0.415
agraph+0.385
Neg logit contributions
ranch-0.519
otten-0.468
hammad-0.465
 fir-0.461
athered-0.459
Token sexuality
Token ID16641
Feature activation-3.78e-02

Pos logit contributions
isphere+0.403
ethe+0.402
ITY+0.389
ities+0.381
oir+0.358
Neg logit contributions
ranch-0.388
otten-0.347
hammad-0.343
 fir-0.341
athered-0.339
Token.
Token ID13
Feature activation-7.02e-02

Pos logit contributions
isphere+0.058
ethe+0.058
ITY+0.055
ities+0.053
agraph+0.049
Neg logit contributions
ranch-0.096
otten-0.089
hammad-0.088
 fir-0.088
athered-0.087
Token that
Token ID326
Feature activation-1.24e-01

Pos logit contributions
isphere+0.091
ethe+0.090
ITY+0.087
ities+0.085
agraph+0.078
Neg logit contributions
ranch-0.126
otten-0.114
hammad-0.113
 fir-0.112
athered-0.112
Token Sa
Token ID10318
Feature activation+3.70e-03

Pos logit contributions
isphere+0.237
ethe+0.236
ITY+0.229
ities+0.224
oir+0.207
Neg logit contributions
ranch-0.272
otten-0.245
hammad-0.243
 fir-0.241
athered-0.240
Token'd
Token ID1549
Feature activation-4.74e-02

Pos logit contributions
ranch+0.010
otten+0.009
hammad+0.009
 fir+0.009
athered+0.009
Neg logit contributions
isphere-0.005
ethe-0.005
ITY-0.005
ities-0.005
oir-0.004
Token judgment
Token ID8492
Feature activation-2.82e-02

Pos logit contributions
isphere+0.098
ethe+0.097
ITY+0.095
ities+0.093
oir+0.086
Neg logit contributions
ranch-0.097
otten-0.086
hammad-0.086
 fir-0.085
ulla-0.085
Token acc
Token ID697
Feature activation+1.03e-01

Pos logit contributions
isphere+0.056
ethe+0.055
ITY+0.054
ities+0.053
oir+0.049
Neg logit contributions
ranch-0.060
otten-0.054
hammad-0.054
 fir-0.053
athered-0.053
Tokenords
Token ID3669
Feature activation-5.34e-01

Pos logit contributions
ranch+0.293
otten+0.273
athered+0.268
ulla+0.267
hammad+0.267
Neg logit contributions
isphere-0.127
ethe-0.125
ITY-0.122
ities-0.115
agraph-0.104
Token with
Token ID351
Feature activation-2.06e-03

Pos logit contributions
isphere+0.990
ethe+0.987
ITY+0.956
ities+0.938
agraph+0.864
Neg logit contributions
ranch-1.200
otten-1.083
hammad-1.074
 fir-1.063
athered-1.062
Token that
Token ID326
Feature activation-8.74e-02

Pos logit contributions
isphere+0.004
ethe+0.004
ITY+0.004
ities+0.004
oir+0.003
Neg logit contributions
ranch-0.005
otten-0.004
hammad-0.004
 fir-0.004
athered-0.004
Token of
Token ID286
Feature activation-7.97e-02

Pos logit contributions
isphere+0.175
ethe+0.174
ITY+0.169
ities+0.166
oir+0.154
Neg logit contributions
ranch-0.184
otten-0.165
hammad-0.163
 fir-0.162
athered-0.161
Token the
Token ID262
Feature activation-6.70e-02

Pos logit contributions
isphere+0.153
ethe+0.153
ITY+0.148
ities+0.145
oir+0.134
Neg logit contributions
ranch-0.174
otten-0.156
hammad-0.155
 fir-0.154
athered-0.153
Token law
Token ID1099
Feature activation-2.06e-01

Pos logit contributions
isphere+0.139
ethe+0.138
ITY+0.135
ities+0.132
agraph+0.123
Neg logit contributions
ranch-0.136
otten-0.121
hammad-0.120
athered-0.118
 fir-0.118
Tokeniger
Token ID8254
Feature activation+1.48e-01

Pos logit contributions
ethe+0.374
isphere+0.358
ITY+0.338
ities+0.335
oir+0.317
Neg logit contributions
ranch-0.577
hammad-0.528
ucket-0.518
otten-0.517
ulla-0.517
Token goal
Token ID3061
Feature activation-2.23e-03

Pos logit contributions
ranch+0.309
otten+0.276
hammad+0.274
 fir+0.271
athered+0.270
Neg logit contributions
isphere-0.299
ethe-0.298
ITY-0.290
ities-0.284
oir-0.264
Token
Token ID198
Feature activation+2.08e-02

Pos logit contributions
isphere+0.004
ethe+0.004
ITY+0.004
ities+0.003
oir+0.003
Neg logit contributions
ranch-0.005
otten-0.005
hammad-0.005
 fir-0.005
athered-0.005
Token
Token ID198
Feature activation+2.83e-03

Pos logit contributions
ranch+0.047
otten+0.042
hammad+0.042
 fir+0.041
athered+0.041
Neg logit contributions
isphere-0.039
ethe-0.039
ITY-0.037
ities-0.037
agraph-0.034
TokenHon
Token ID29478
Feature activation+2.11e-01

Pos logit contributions
ranch+0.006
otten+0.006
hammad+0.005
athered+0.005
 fir+0.005
Neg logit contributions
isphere-0.005
ethe-0.005
ITY-0.005
ities-0.005
oir-0.005
Tokenours
Token ID4662
Feature activation-5.32e-01

Pos logit contributions
ranch+0.548
otten+0.505
hammad+0.501
athered+0.494
 fir+0.493
Neg logit contributions
isphere-0.310
ITY-0.306
ethe-0.306
ities-0.289
agraph-0.261
Token
Token ID198
Feature activation-7.45e-03

Pos logit contributions
isphere+1.016
ethe+1.013
ITY+0.983
ities+0.962
oir+0.891
Neg logit contributions
ranch-1.165
otten-1.049
hammad-1.039
 fir-1.032
athered-1.029
Token
Token ID198
Feature activation-2.04e-02

Pos logit contributions
isphere+0.014
ethe+0.014
ITY+0.013
ities+0.013
agraph+0.012
Neg logit contributions
ranch-0.017
otten-0.015
hammad-0.015
 fir-0.015
athered-0.015
TokenClub
Token ID42350
Feature activation-7.92e-02

Pos logit contributions
isphere+0.040
ethe+0.040
ITY+0.039
ities+0.038
oir+0.035
Neg logit contributions
ranch-0.044
otten-0.039
hammad-0.039
athered-0.038
 fir-0.038
Token
Token ID198
Feature activation+1.37e-02

Pos logit contributions
isphere+0.152
ethe+0.151
ITY+0.147
ities+0.143
oir+0.134
Neg logit contributions
ranch-0.173
otten-0.155
hammad-0.153
 fir-0.153
athered-0.152
Token
Token ID198
Feature activation-5.99e-03

Pos logit contributions
ranch+0.031
otten+0.028
hammad+0.027
 fir+0.027
athered+0.027
Neg logit contributions
isphere-0.026
ethe-0.026
ITY-0.025
ities-0.024
agraph-0.022
Token education
Token ID3707
Feature activation-1.03e-01

Pos logit contributions
ranch+0.140
otten+0.126
hammad+0.124
 fir+0.123
athered+0.123
Neg logit contributions
isphere-0.130
ethe-0.130
ITY-0.126
ities-0.124
oir-0.114
Token."
Token ID526
Feature activation-9.39e-02

Pos logit contributions
isphere+0.170
ethe+0.170
ITY+0.164
ities+0.160
agraph+0.147
Neg logit contributions
ranch-0.252
otten-0.229
hammad-0.228
 fir-0.227
athered-0.226
Token
Token ID198
Feature activation-7.89e-03

Pos logit contributions
isphere+0.175
ethe+0.175
ITY+0.169
ities+0.166
oir+0.153
Neg logit contributions
ranch-0.210
otten-0.189
hammad-0.187
 fir-0.186
athered-0.186
Token
Token ID198
Feature activation-2.40e-02

Pos logit contributions
isphere+0.015
ethe+0.015
ITY+0.014
ities+0.014
agraph+0.013
Neg logit contributions
ranch-0.018
otten-0.016
hammad-0.016
 fir-0.016
athered-0.016
TokenMis
Token ID31281
Feature activation-1.09e-01

Pos logit contributions
isphere+0.045
ethe+0.045
ITY+0.043
ities+0.042
oir+0.039
Neg logit contributions
ranch-0.054
otten-0.048
hammad-0.048
athered-0.047
 fir-0.047
Tokenguided
Token ID23657
Feature activation-5.32e-01

Pos logit contributions
isphere+0.230
ethe+0.230
ITY+0.224
ities+0.220
oir+0.205
Neg logit contributions
ranch-0.216
otten-0.192
hammad-0.191
 fir-0.189
athered-0.188
Token political
Token ID1964
Feature activation-6.10e-03

Pos logit contributions
isphere+1.090
ethe+1.089
ITY+1.060
ities+1.044
oir+0.965
Neg logit contributions
ranch-1.087
otten-0.972
hammad-0.962
athered-0.951
ulla-0.949
Token effort
Token ID3626
Feature activation+4.81e-02

Pos logit contributions
isphere+0.013
ethe+0.012
ITY+0.012
ities+0.012
agraph+0.011
Neg logit contributions
ranch-0.012
otten-0.011
hammad-0.011
 fir-0.011
athered-0.011
Token
Token ID198
Feature activation-4.08e-02

Pos logit contributions
ranch+0.108
otten+0.098
hammad+0.097
 fir+0.096
athered+0.096
Neg logit contributions
isphere-0.089
ethe-0.089
ITY-0.086
ities-0.084
agraph-0.078
Token
Token ID198
Feature activation-5.70e-02

Pos logit contributions
isphere+0.076
ethe+0.075
ITY+0.073
ities+0.072
agraph+0.066
Neg logit contributions
ranch-0.092
otten-0.083
hammad-0.082
 fir-0.081
athered-0.081
TokenThe
Token ID464
Feature activation-1.44e-03

Pos logit contributions
isphere+0.106
ethe+0.105
ITY+0.101
ities+0.100
oir+0.092
Neg logit contributions
ranch-0.128
otten-0.115
hammad-0.114
athered-0.113
 fir-0.113
Token.
Token ID13
Feature activation-2.61e-02

Pos logit contributions
ranch+0.074
otten+0.068
hammad+0.067
 fir+0.067
ulla+0.066
Neg logit contributions
isphere-0.046
ethe-0.046
ITY-0.044
ities-0.043
oir-0.039
Token
Token ID198
Feature activation+2.39e-02

Pos logit contributions
isphere+0.050
ethe+0.050
ITY+0.049
ities+0.048
oir+0.044
Neg logit contributions
ranch-0.057
otten-0.051
hammad-0.050
 fir-0.050
athered-0.050
Token
Token ID198
Feature activation+1.91e-02

Pos logit contributions
ranch+0.053
otten+0.048
hammad+0.047
 fir+0.047
athered+0.046
Neg logit contributions
isphere-0.045
ethe-0.045
ITY-0.043
ities-0.043
agraph-0.040
TokenS
Token ID50
Feature activation+3.19e-02

Pos logit contributions
ranch+0.043
otten+0.039
hammad+0.038
athered+0.038
 fir+0.038
Neg logit contributions
isphere-0.035
ethe-0.035
ITY-0.034
ities-0.033
agraph-0.031
Tokenovere
Token ID33518
Feature activation+8.21e-02

Pos logit contributions
ranch+0.065
otten+0.058
hammad+0.057
athered+0.056
 fir+0.056
Neg logit contributions
isphere-0.066
ethe-0.066
ITY-0.064
ities-0.063
agraph-0.059
Tokenign
Token ID570
Feature activation-5.31e-01

Pos logit contributions
ranch+0.187
otten+0.169
hammad+0.168
athered+0.167
 fir+0.166
Neg logit contributions
isphere-0.150
ethe-0.149
ITY-0.144
ities-0.141
oir-0.130
Token Lux
Token ID17145
Feature activation-1.62e-01

Pos logit contributions
isphere+1.039
ethe+1.035
ITY+1.005
ities+0.987
oir+0.913
Neg logit contributions
ranch-1.138
otten-1.021
hammad-1.013
 fir-1.003
athered-1.001
Tokenury
Token ID1601
Feature activation+6.11e-01

Pos logit contributions
isphere+0.413
ethe+0.412
ITY+0.402
ities+0.396
oir+0.373
Neg logit contributions
ranch-0.253
otten-0.217
hammad-0.214
 fir-0.211
athered-0.210
Token Travel
Token ID13524
Feature activation-1.91e-01

Pos logit contributions
ranch+1.323
otten+1.180
 fir+1.174
hammad+1.170
athered+1.165
Neg logit contributions
isphere-1.182
ethe-1.179
ITY-1.130
ities-1.102
agraph-1.030
Token (
Token ID357
Feature activation-2.12e-02

Pos logit contributions
isphere+0.363
ethe+0.362
ITY+0.351
ities+0.344
oir+0.318
Neg logit contributions
ranch-0.421
otten-0.379
hammad-0.376
 fir-0.372
athered-0.372
Token08
Token ID2919
Feature activation-5.25e-02

Pos logit contributions
isphere+0.040
ethe+0.039
ITY+0.038
ities+0.038
oir+0.035
Neg logit contributions
ranch-0.048
otten-0.043
hammad-0.042
athered-0.042
 fir-0.042
Token inches
Token ID8331
Feature activation+6.77e-02

Pos logit contributions
ranch+0.091
otten+0.081
hammad+0.080
 fir+0.080
athered+0.079
Neg logit contributions
isphere-0.093
ethe-0.092
ITY-0.090
ities-0.088
oir-0.082
Token,
Token ID11
Feature activation+2.49e-02

Pos logit contributions
ranch+0.165
otten+0.150
 fir+0.149
hammad+0.148
athered+0.148
Neg logit contributions
ethe-0.112
isphere-0.112
ITY-0.108
ities-0.105
agraph-0.097
Token and
Token ID290
Feature activation+8.36e-02

Pos logit contributions
ranch+0.053
otten+0.047
hammad+0.047
ulla+0.047
athered+0.047
Neg logit contributions
isphere-0.049
ethe-0.049
ITY-0.047
ities-0.047
oir-0.043
Token taking
Token ID2263
Feature activation+1.10e-01

Pos logit contributions
ranch+0.183
otten+0.165
hammad+0.163
 fir+0.163
athered+0.162
Neg logit contributions
isphere-0.159
ethe-0.159
ITY-0.154
ities-0.150
oir-0.140
Token splash
Token ID22870
Feature activation+1.69e-01

Pos logit contributions
ranch+0.231
otten+0.208
 fir+0.207
hammad+0.205
athered+0.205
Neg logit contributions
ethe-0.219
isphere-0.219
ITY-0.211
ities-0.206
oir-0.193
Tokeny
Token ID88
Feature activation-5.24e-01

Pos logit contributions
ranch+0.431
otten+0.395
 fir+0.392
hammad+0.389
athered+0.388
Neg logit contributions
isphere-0.267
ethe-0.260
ITY-0.252
ities-0.244
agraph-0.223
Token,
Token ID11
Feature activation+3.29e-02

Pos logit contributions
isphere+1.029
ethe+1.026
ITY+0.996
ities+0.978
oir+0.905
Neg logit contributions
ranch-1.117
otten-1.002
hammad-0.994
 fir-0.984
athered-0.983
Token cash
Token ID5003
Feature activation-1.22e-01

Pos logit contributions
ranch+0.071
otten+0.063
hammad+0.063
 fir+0.062
athered+0.062
Neg logit contributions
isphere-0.064
ethe-0.064
ITY-0.062
ities-0.061
oir-0.057
Tokeny
Token ID88
Feature activation-4.52e-01

Pos logit contributions
isphere+0.210
ethe+0.208
ITY+0.202
ities+0.196
agraph+0.181
Neg logit contributions
ranch-0.292
otten-0.265
hammad-0.263
 fir-0.262
athered-0.262
Token advantage
Token ID4621
Feature activation+1.19e-01

Pos logit contributions
isphere+0.888
ethe+0.885
ITY+0.860
ities+0.846
oir+0.780
Neg logit contributions
ranch-0.966
otten-0.867
hammad-0.860
athered-0.849
 fir-0.849
Token of
Token ID286
Feature activation+4.80e-02

Pos logit contributions
ranch+0.249
otten+0.224
 fir+0.221
hammad+0.221
athered+0.219
Neg logit contributions
isphere-0.239
ethe-0.237
ITY-0.231
ities-0.224
agraph-0.211
Token a
Token ID257
Feature activation+1.90e-02

Pos logit contributions
ranch+0.033
otten+0.029
hammad+0.029
 fir+0.029
athered+0.029
Neg logit contributions
isphere-0.033
ethe-0.033
ITY-0.032
ities-0.031
agraph-0.029
Token new
Token ID649
Feature activation+6.18e-03

Pos logit contributions
ranch+0.037
otten+0.033
hammad+0.033
 fir+0.032
athered+0.032
Neg logit contributions
isphere-0.041
ethe-0.041
ITY-0.039
ities-0.039
agraph-0.036
Token mood
Token ID10038
Feature activation+1.16e-02

Pos logit contributions
ranch+0.013
otten+0.012
hammad+0.012
 fir+0.012
athered+0.012
Neg logit contributions
isphere-0.012
ethe-0.012
ITY-0.012
ities-0.012
oir-0.011
Token of
Token ID286
Feature activation+4.71e-03

Pos logit contributions
ranch+0.024
otten+0.021
 fir+0.021
hammad+0.021
athered+0.021
Neg logit contributions
isphere-0.023
ethe-0.023
ITY-0.023
ities-0.022
agraph-0.021
Token cens
Token ID12428
Feature activation+2.74e-02

Pos logit contributions
ranch+0.009
otten+0.008
hammad+0.008
 fir+0.008
athered+0.008
Neg logit contributions
isphere-0.010
ethe-0.010
ITY-0.010
ities-0.010
agraph-0.009
Tokenorious
Token ID9982
Feature activation-5.22e-01

Pos logit contributions
ranch+0.057
otten+0.051
hammad+0.050
 fir+0.050
athered+0.049
Neg logit contributions
isphere-0.056
ethe-0.056
ITY-0.054
ities-0.053
agraph-0.049
Token political
Token ID1964
Feature activation-1.42e-03

Pos logit contributions
isphere+1.050
ethe+1.049
ITY+1.022
ities+1.011
oir+0.930
Neg logit contributions
ranch-1.087
otten-0.974
hammad-0.966
athered-0.951
ulla-0.949
Token correctness
Token ID29409
Feature activation-1.79e-01

Pos logit contributions
isphere+0.003
ethe+0.003
ITY+0.003
ities+0.003
agraph+0.003
Neg logit contributions
ranch-0.003
otten-0.003
hammad-0.002
 fir-0.002
athered-0.002
Token sweeping
Token ID18404
Feature activation+6.84e-02

Pos logit contributions
isphere+0.329
ethe+0.328
ITY+0.317
ities+0.310
agraph+0.286
Neg logit contributions
ranch-0.405
otten-0.366
hammad-0.363
 fir-0.362
athered-0.360
Token university
Token ID6403
Feature activation-2.47e-02

Pos logit contributions
ranch+0.143
otten+0.128
hammad+0.127
 fir+0.126
athered+0.125
Neg logit contributions
isphere-0.138
ethe-0.137
ITY-0.133
ities-0.131
oir-0.121
Token campuses
Token ID23003
Feature activation-3.27e-02

Pos logit contributions
isphere+0.058
ethe+0.058
ITY+0.056
ities+0.056
oir+0.052
Neg logit contributions
ranch-0.043
otten-0.038
hammad-0.038
 fir-0.037
athered-0.037
Token W
Token ID370
Feature activation-9.52e-02

Pos logit contributions
ethe+0.148
isphere+0.147
ITY+0.143
ities+0.140
oir+0.128
Neg logit contributions
ranch-0.201
otten-0.182
hammad-0.181
 fir-0.179
athered-0.179
Tokenalth
Token ID1094
Feature activation-4.16e-02

Pos logit contributions
ethe+0.210
isphere+0.209
ITY+0.205
ities+0.202
oir+0.189
Neg logit contributions
ranch-0.179
otten-0.159
hammad-0.157
 fir-0.156
athered-0.155
Tokenam
Token ID321
Feature activation-5.34e-02

Pos logit contributions
isphere+0.086
ethe+0.086
ITY+0.084
ities+0.082
oir+0.076
Neg logit contributions
ranch-0.085
otten-0.076
hammad-0.075
 fir-0.074
athered-0.074
Token and
Token ID290
Feature activation-1.13e-01

Pos logit contributions
isphere+0.109
ethe+0.109
ITY+0.106
ities+0.104
oir+0.097
Neg logit contributions
ranch-0.110
otten-0.098
hammad-0.097
 fir-0.096
athered-0.096
Token Som
Token ID9995
Feature activation-1.09e-01

Pos logit contributions
isphere+0.248
ethe+0.247
ITY+0.241
ities+0.237
oir+0.221
Neg logit contributions
ranch-0.215
otten-0.190
hammad-0.188
 fir-0.186
athered-0.186
Tokenerville
Token ID33487
Feature activation-5.15e-01

Pos logit contributions
isphere+0.190
ethe+0.188
ITY+0.183
ities+0.179
agraph+0.165
Neg logit contributions
ranch-0.256
otten-0.231
hammad-0.230
athered-0.228
ulla-0.227
Token's
Token ID338
Feature activation-8.77e-02

Pos logit contributions
isphere+0.795
ethe+0.795
ITY+0.766
ities+0.751
oir+0.677
Neg logit contributions
ranch-1.314
otten-1.201
hammad-1.193
athered-1.183
 fir-1.181
Token Union
Token ID4479
Feature activation-8.85e-02

Pos logit contributions
isphere+0.155
ethe+0.155
ITY+0.150
ities+0.147
oir+0.134
Neg logit contributions
ranch-0.205
otten-0.185
hammad-0.184
 fir-0.182
athered-0.182
Token Square
Token ID9276
Feature activation+2.21e-02

Pos logit contributions
isphere+0.149
ethe+0.147
ITY+0.142
ities+0.139
oir+0.127
Neg logit contributions
ranch-0.215
otten-0.195
hammad-0.194
 fir-0.192
athered-0.192
Token.
Token ID13
Feature activation-5.71e-02

Pos logit contributions
ranch+0.063
otten+0.058
hammad+0.057
 fir+0.057
athered+0.057
Neg logit contributions
isphere-0.028
ethe-0.028
ITY-0.027
ities-0.026
agraph-0.023
Token
Token ID198
Feature activation-8.40e-02

Pos logit contributions
isphere+0.098
ethe+0.098
ITY+0.094
ities+0.092
oir+0.084
Neg logit contributions
ranch-0.136
otten-0.124
hammad-0.123
athered-0.122
 fir-0.122
Token of
Token ID286
Feature activation+2.22e-02

Pos logit contributions
ranch+0.125
otten+0.112
hammad+0.111
 fir+0.111
athered+0.110
Neg logit contributions
isphere-0.119
ethe-0.118
ITY-0.114
ities-0.112
agraph-0.105
Token Cl
Token ID1012
Feature activation-5.02e-02

Pos logit contributions
ranch+0.058
otten+0.053
hammad+0.052
 fir+0.052
athered+0.052
Neg logit contributions
isphere-0.033
ethe-0.033
ITY-0.032
ities-0.031
oir-0.028
Tokenarity
Token ID6806
Feature activation+6.01e-01

Pos logit contributions
isphere+0.130
ethe+0.130
ITY+0.127
ities+0.125
oir+0.118
Neg logit contributions
ranch-0.076
otten-0.065
hammad-0.064
 fir-0.063
athered-0.063
Token Gaming
Token ID14426
Feature activation+5.83e-02

Pos logit contributions
ranch+1.348
 fir+1.226
otten+1.220
hammad+1.208
ulla+1.189
Neg logit contributions
isphere-1.112
ethe-1.097
ITY-1.054
ities-1.025
oir-0.968
Token Cl
Token ID1012
Feature activation-1.98e-02

Pos logit contributions
ranch+0.139
otten+0.126
hammad+0.125
 fir+0.124
athered+0.123
Neg logit contributions
isphere-0.100
ethe-0.100
ITY-0.097
ities-0.095
oir-0.087
Tokenarity
Token ID6806
Feature activation+6.05e-01

Pos logit contributions
isphere+0.051
ethe+0.051
ITY+0.050
ities+0.049
oir+0.047
Neg logit contributions
ranch-0.030
otten-0.025
hammad-0.025
athered-0.025
 fir-0.025
Token Gaming
Token ID14426
Feature activation+1.02e-01

Pos logit contributions
ranch+1.354
 fir+1.230
otten+1.225
hammad+1.214
athered+1.197
Neg logit contributions
isphere-1.113
ethe-1.104
ITY-1.061
ities-1.032
oir-0.976
Token will
Token ID481
Feature activation-1.54e-02

Pos logit contributions
ranch+0.223
otten+0.201
hammad+0.199
 fir+0.198
athered+0.197
Neg logit contributions
isphere-0.196
ethe-0.195
ITY-0.190
ities-0.186
agraph-0.172
Token also
Token ID635
Feature activation+2.76e-02

Pos logit contributions
isphere+0.025
ethe+0.024
ITY+0.024
ities+0.023
agraph+0.021
Neg logit contributions
ranch-0.039
otten-0.035
hammad-0.035
 fir-0.035
athered-0.035
Token be
Token ID307
Feature activation-5.74e-02

Pos logit contributions
ranch+0.052
otten+0.046
hammad+0.045
 fir+0.045
athered+0.045
Neg logit contributions
isphere-0.061
ethe-0.061
ITY-0.059
ities-0.058
agraph-0.055
Token releasing
Token ID13011
Feature activation+9.09e-02

Pos logit contributions
isphere+0.126
ethe+0.125
ITY+0.122
ities+0.119
agraph+0.112
Neg logit contributions
ranch-0.110
otten-0.097
hammad-0.096
 fir-0.096
athered-0.095
Tokenе
Token ID16843
Feature activation+1.97e-01

Pos logit contributions
ranch+0.504
otten+0.454
hammad+0.448
 fir+0.444
athered+0.440
Neg logit contributions
isphere-0.510
ethe-0.503
ITY-0.487
ities-0.481
agraph-0.448
Tokenр
Token ID21169
Feature activation+8.67e-02

Pos logit contributions
ranch+0.444
otten+0.402
hammad+0.398
 fir+0.395
athered+0.393
Neg logit contributions
isphere-0.366
ethe-0.362
ITY-0.352
ities-0.345
agraph-0.317
Tokenд
Token ID43666
Feature activation+2.20e-01

Pos logit contributions
ranch+0.219
otten+0.202
hammad+0.199
 fir+0.198
ulla+0.197
Neg logit contributions
isphere-0.136
ethe-0.134
ITY-0.129
ities-0.127
agraph-0.115
Tokenи
Token ID18849
Feature activation+3.36e-01

Pos logit contributions
ranch+0.493
otten+0.448
hammad+0.444
 fir+0.441
ulla+0.437
Neg logit contributions
isphere-0.408
ethe-0.403
ITY-0.391
ities-0.384
agraph-0.355
Tokenт
Token ID20375
Feature activation+4.81e-02

Pos logit contributions
ranch+0.842
otten+0.776
hammad+0.766
 fir+0.763
ulla+0.757
Neg logit contributions
isphere-0.535
ethe-0.530
ITY-0.509
ities-0.499
agraph-0.453
Tokenь
Token ID45367
Feature activation+4.96e-01

Pos logit contributions
ranch+0.112
otten+0.102
hammad+0.101
 fir+0.101
ulla+0.100
Neg logit contributions
isphere-0.085
ethe-0.084
ITY-0.082
ities-0.080
agraph-0.073
Token
Token ID12466
Feature activation+2.64e-02

Pos logit contributions
ranch+1.353
otten+1.259
 fir+1.253
hammad+1.247
ulla+1.232
Neg logit contributions
isphere-0.670
ethe-0.658
ITY-0.623
ities-0.605
agraph-0.543
Token
Token ID111
Feature activation+1.54e-01

Pos logit contributions
ranch+0.054
otten+0.048
hammad+0.048
 fir+0.047
athered+0.047
Neg logit contributions
isphere-0.054
ethe-0.054
ITY-0.052
ities-0.052
oir-0.048
Tokenи
Token ID18849
Feature activation+3.34e-01

Pos logit contributions
ranch+0.393
otten+0.362
hammad+0.359
 fir+0.357
ulla+0.355
Neg logit contributions
isphere-0.235
ethe-0.231
ITY-0.224
ities-0.218
agraph-0.197
Token
Token ID140
Feature activation+1.40e-01

Pos logit contributions
ranch+0.850
otten+0.784
hammad+0.776
 fir+0.773
athered+0.765
Neg logit contributions
isphere-0.519
ethe-0.510
ITY-0.490
ities-0.481
agraph-0.434
Token
Token ID109
Feature activation+7.73e-03

Pos logit contributions
ranch+0.357
otten+0.326
hammad+0.324
 fir+0.321
athered+0.321
Neg logit contributions
isphere-0.217
ethe-0.216
ITY-0.208
ities-0.203
oir-0.184
Tokenb
Token ID65
Feature activation-1.08e-02

Pos logit contributions
isphere+0.201
ethe+0.200
ITY+0.195
ities+0.189
oir+0.174
Neg logit contributions
ranch-0.274
otten-0.247
hammad-0.246
athered-0.243
 fir-0.243
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
isphere+0.017
ethe+0.017
ITY+0.016
ities+0.016
oir+0.015
Neg logit contributions
ranch-0.027
otten-0.025
hammad-0.025
 fir-0.025
ulla-0.025
Tokensh
Token ID1477
Feature activation-1.07e-01

Pos logit contributions
ethe+0.041
isphere+0.041
ITY+0.040
ities+0.039
oir+0.036
Neg logit contributions
ranch-0.046
otten-0.041
hammad-0.040
athered-0.040
 fir-0.040
Tokenorter
Token ID4337
Feature activation-1.93e-01

Pos logit contributions
isphere+0.134
ethe+0.133
ITY+0.127
ities+0.123
oir+0.108
Neg logit contributions
ranch-0.303
otten-0.280
hammad-0.278
 fir-0.276
athered-0.276
TokenAx
Token ID31554
Feature activation-6.73e-02

Pos logit contributions
isphere+0.309
ethe+0.308
ITY+0.295
ities+0.288
agraph+0.264
Neg logit contributions
ranch-0.484
otten-0.440
hammad-0.436
 fir-0.434
athered-0.433
Tokenis
Token ID271
Feature activation+5.64e-01

Pos logit contributions
ethe+0.120
isphere+0.119
ITY+0.116
ities+0.112
oir+0.105
Neg logit contributions
ranch-0.155
otten-0.140
hammad-0.139
 fir-0.138
ucket-0.137
Token,
Token ID11
Feature activation+4.22e-02

Pos logit contributions
ranch+1.444
otten+1.319
 fir+1.307
hammad+1.293
athered+1.292
Neg logit contributions
isphere-0.866
ethe-0.858
ITY-0.812
ities-0.792
agraph-0.741
Token space
Token ID2272
Feature activation-4.19e-02

Pos logit contributions
ranch+0.089
otten+0.079
hammad+0.078
 fir+0.078
athered+0.078
Neg logit contributions
isphere-0.084
ethe-0.084
ITY-0.081
ities-0.080
oir-0.074
Token );
Token ID5619
Feature activation+1.01e-01

Pos logit contributions
isphere+0.065
ethe+0.065
ITY+0.061
ities+0.060
agraph+0.055
Neg logit contributions
ranch-0.107
otten-0.098
 fir-0.097
hammad-0.096
athered-0.096
Token //
Token ID3373
Feature activation-3.91e-03

Pos logit contributions
ranch+0.216
otten+0.194
hammad+0.192
 fir+0.191
athered+0.190
Neg logit contributions
isphere-0.200
ethe-0.199
ITY-0.193
ities-0.189
agraph-0.176
Token 3
Token ID513
Feature activation+3.05e-02

Pos logit contributions
isphere+0.008
ethe+0.008
ITY+0.007
ities+0.007
oir+0.007
Neg logit contributions
ranch-0.008
otten-0.008
hammad-0.007
 fir-0.007
athered-0.007
Tokenojure
Token ID32511
Feature activation+3.71e-02

Pos logit contributions
ranch+0.214
otten+0.182
hammad+0.179
athered+0.175
 fir+0.175
Neg logit contributions
isphere-0.399
ethe-0.397
ITY-0.390
ities-0.383
agraph-0.363
Token /
Token ID1220
Feature activation+2.16e-02

Pos logit contributions
ranch+0.099
otten+0.091
hammad+0.090
athered+0.090
 fir+0.090
Neg logit contributions
isphere-0.053
ethe-0.053
ITY-0.051
ities-0.049
oir-0.044
Token math
Token ID10688
Feature activation+2.11e-01

Pos logit contributions
ranch+0.042
otten+0.037
hammad+0.036
athered+0.036
ulla+0.036
Neg logit contributions
isphere-0.047
ethe-0.047
ITY-0.046
ities-0.045
oir-0.042
Token.
Token ID764
Feature activation-9.67e-03

Pos logit contributions
ranch+0.497
otten+0.451
hammad+0.448
athered+0.443
 fir+0.442
Neg logit contributions
isphere-0.367
ethe-0.367
ITY-0.355
ities-0.348
oir-0.319
Token comb
Token ID1974
Feature activation+2.10e-01

Pos logit contributions
isphere+0.021
ethe+0.020
ITY+0.020
ities+0.020
agraph+0.018
Neg logit contributions
ranch-0.019
otten-0.017
hammad-0.017
athered-0.017
ulla-0.017
Tokeninator
Token ID20900
Feature activation+4.91e-01

Pos logit contributions
ranch+0.443
otten+0.396
hammad+0.393
 fir+0.389
athered+0.388
Neg logit contributions
isphere-0.417
ethe-0.415
ITY-0.404
ities-0.396
oir-0.367
Tokenics
Token ID873
Feature activation+6.82e-04

Pos logit contributions
ranch+1.132
otten+1.027
hammad+1.021
 fir+1.014
ulla+1.008
Neg logit contributions
isphere-0.874
ethe-0.866
ITY-0.837
ities-0.819
agraph-0.758
Token |
Token ID930
Feature activation+1.07e-01

Pos logit contributions
ranch+0.002
otten+0.001
hammad+0.001
athered+0.001
 fir+0.001
Neg logit contributions
isphere-0.001
ethe-0.001
ITY-0.001
ities-0.001
oir-0.001
Token 372
Token ID46633
Feature activation+1.57e-01

Pos logit contributions
ranch+0.229
otten+0.205
hammad+0.203
 fir+0.202
athered+0.201
Neg logit contributions
isphere-0.211
ethe-0.209
ITY-0.202
ities-0.198
agraph-0.185
Token |
Token ID930
Feature activation+1.11e-01

Pos logit contributions
ranch+0.371
otten+0.336
hammad+0.333
 fir+0.331
athered+0.330
Neg logit contributions
isphere-0.274
ethe-0.273
ITY-0.263
ities-0.258
agraph-0.237
Token |
Token ID930
Feature activation+1.17e-01

Pos logit contributions
ranch+0.267
otten+0.243
hammad+0.241
 fir+0.239
athered+0.239
Neg logit contributions
isphere-0.189
ethe-0.188
ITY-0.183
ities-0.178
oir-0.163
Token
Token ID198
Feature activation+1.91e-02

Pos logit contributions
ranch+0.053
otten+0.048
hammad+0.047
 fir+0.047
athered+0.046
Neg logit contributions
isphere-0.045
ethe-0.045
ITY-0.043
ities-0.043
agraph-0.040
TokenS
Token ID50
Feature activation+3.19e-02

Pos logit contributions
ranch+0.043
otten+0.039
hammad+0.038
athered+0.038
 fir+0.038
Neg logit contributions
isphere-0.035
ethe-0.035
ITY-0.034
ities-0.033
agraph-0.031
Tokenovere
Token ID33518
Feature activation+8.21e-02

Pos logit contributions
ranch+0.065
otten+0.058
hammad+0.057
athered+0.056
 fir+0.056
Neg logit contributions
isphere-0.066
ethe-0.066
ITY-0.064
ities-0.063
agraph-0.059
Tokenign
Token ID570
Feature activation-5.31e-01

Pos logit contributions
ranch+0.187
otten+0.169
hammad+0.168
athered+0.167
 fir+0.166
Neg logit contributions
isphere-0.150
ethe-0.149
ITY-0.144
ities-0.141
oir-0.130
Token Lux
Token ID17145
Feature activation-1.62e-01

Pos logit contributions
isphere+1.039
ethe+1.035
ITY+1.005
ities+0.987
oir+0.913
Neg logit contributions
ranch-1.138
otten-1.021
hammad-1.013
 fir-1.003
athered-1.001
Tokenury
Token ID1601
Feature activation+6.11e-01

Pos logit contributions
isphere+0.413
ethe+0.412
ITY+0.402
ities+0.396
oir+0.373
Neg logit contributions
ranch-0.253
otten-0.217
hammad-0.214
 fir-0.211
athered-0.210
Token Travel
Token ID13524
Feature activation-1.91e-01

Pos logit contributions
ranch+1.323
otten+1.180
 fir+1.174
hammad+1.170
athered+1.165
Neg logit contributions
isphere-1.182
ethe-1.179
ITY-1.130
ities-1.102
agraph-1.030
Token (
Token ID357
Feature activation-2.12e-02

Pos logit contributions
isphere+0.363
ethe+0.362
ITY+0.351
ities+0.344
oir+0.318
Neg logit contributions
ranch-0.421
otten-0.379
hammad-0.376
 fir-0.372
athered-0.372
Token08
Token ID2919
Feature activation-5.25e-02

Pos logit contributions
isphere+0.040
ethe+0.039
ITY+0.038
ities+0.038
oir+0.035
Neg logit contributions
ranch-0.048
otten-0.043
hammad-0.042
athered-0.042
 fir-0.042
Token44
Token ID2598
Feature activation+4.31e-02

Pos logit contributions
isphere+0.097
ethe+0.096
ITY+0.093
ities+0.091
agraph+0.084
Neg logit contributions
ranch-0.118
otten-0.107
hammad-0.106
 fir-0.105
athered-0.105
Token 415
Token ID40643
Feature activation+9.52e-02

Pos logit contributions
ranch+0.097
otten+0.088
hammad+0.087
 fir+0.087
athered+0.086
Neg logit contributions
isphere-0.080
ethe-0.079
ITY-0.076
ities-0.075
agraph-0.069
Token his
Token ID465
Feature activation+9.10e-02

Pos logit contributions
ranch+0.048
otten+0.043
hammad+0.042
 fir+0.042
athered+0.042
Neg logit contributions
isphere-0.046
ethe-0.045
ITY-0.044
ities-0.043
oir-0.040
Token political
Token ID1964
Feature activation-2.64e-02

Pos logit contributions
ranch+0.188
otten+0.167
hammad+0.166
 fir+0.165
athered+0.165
Neg logit contributions
isphere-0.186
ethe-0.183
ITY-0.178
ities-0.175
agraph-0.163
Token career
Token ID3451
Feature activation+2.19e-01

Pos logit contributions
isphere+0.057
ethe+0.057
ITY+0.056
ities+0.054
agraph+0.051
Neg logit contributions
ranch-0.051
otten-0.045
hammad-0.044
 fir-0.044
athered-0.044
Token,
Token ID11
Feature activation+1.75e-02

Pos logit contributions
ranch+0.591
otten+0.543
hammad+0.542
 fir+0.536
athered+0.536
Neg logit contributions
isphere-0.308
ethe-0.300
ITY-0.288
ities-0.280
agraph-0.254
Token Bernie
Token ID10477
Feature activation-3.43e-02

Pos logit contributions
ranch+0.039
otten+0.035
hammad+0.035
 fir+0.035
athered+0.035
Neg logit contributions
isphere-0.032
ethe-0.032
ITY-0.031
ities-0.031
oir-0.028
Token
Token ID447
Feature activation+6.71e-02

Pos logit contributions
isphere+0.067
ethe+0.066
ITY+0.064
ities+0.063
agraph+0.058
Neg logit contributions
ranch-0.074
otten-0.067
hammad-0.066
 fir-0.065
athered-0.065
Token
Token ID247
Feature activation+5.37e-02

Pos logit contributions
ranch+0.142
otten+0.127
hammad+0.125
 fir+0.125
athered+0.124
Neg logit contributions
isphere-0.134
ethe-0.134
ITY-0.129
ities-0.127
oir-0.117
Tokens
Token ID82
Feature activation+4.39e-02

Pos logit contributions
ranch+0.122
otten+0.110
hammad+0.109
 fir+0.108
athered+0.108
Neg logit contributions
isphere-0.099
ethe-0.098
ITY-0.095
ities-0.093
agraph-0.086
Token current
Token ID1459
Feature activation-2.56e-02

Pos logit contributions
ranch+0.091
otten+0.081
hammad+0.081
 fir+0.080
athered+0.080
Neg logit contributions
isphere-0.089
ethe-0.089
ITY-0.086
ities-0.085
agraph-0.079
Token Millenn
Token ID19007
Feature activation-3.08e-02

Pos logit contributions
isphere+0.054
ethe+0.053
ITY+0.052
ities+0.051
agraph+0.048
Neg logit contributions
ranch-0.051
otten-0.045
hammad-0.045
 fir-0.045
athered-0.045
Tokenial
Token ID498
Feature activation+1.91e-01

Pos logit contributions
ethe+0.058
isphere+0.058
ITY+0.056
ities+0.055
agraph+0.051
Neg logit contributions
ranch-0.068
otten-0.062
hammad-0.061
athered-0.060
ulla-0.060
TokenThe
Token ID464
Feature activation+2.37e-02

Pos logit contributions
isphere+0.068
ethe+0.068
ITY+0.065
ities+0.064
agraph+0.060
Neg logit contributions
ranch-0.079
otten-0.071
hammad-0.071
 fir-0.070
athered-0.070
Token victim
Token ID3117
Feature activation+1.38e-02

Pos logit contributions
ranch+0.050
otten+0.045
hammad+0.044
 fir+0.044
athered+0.044
Neg logit contributions
isphere-0.047
ethe-0.047
ITY-0.046
ities-0.045
oir-0.042
Token was
Token ID373
Feature activation-5.70e-02

Pos logit contributions
ranch+0.029
otten+0.026
hammad+0.026
 fir+0.026
athered+0.026
Neg logit contributions
isphere-0.027
ethe-0.027
ITY-0.026
ities-0.025
agraph-0.024
Token able
Token ID1498
Feature activation-7.15e-03

Pos logit contributions
isphere+0.118
ethe+0.117
ITY+0.114
ities+0.112
oir+0.104
Neg logit contributions
ranch-0.116
otten-0.103
hammad-0.102
 fir-0.101
athered-0.101
Token to
Token ID284
Feature activation-1.61e-02

Pos logit contributions
isphere+0.014
ethe+0.014
ITY+0.013
ities+0.013
oir+0.012
Neg logit contributions
ranch-0.016
otten-0.014
hammad-0.014
 fir-0.014
athered-0.014
Token put
Token ID1234
Feature activation+9.54e-02

Pos logit contributions
isphere+0.037
ethe+0.037
ITY+0.036
ities+0.035
oir+0.033
Neg logit contributions
ranch-0.029
otten-0.026
 fir-0.025
hammad-0.025
athered-0.025
Token out
Token ID503
Feature activation-8.25e-02

Pos logit contributions
ranch+0.208
otten+0.187
hammad+0.186
 fir+0.185
athered+0.184
Neg logit contributions
isphere-0.183
ethe-0.182
ITY-0.177
ities-0.173
oir-0.160
Token the
Token ID262
Feature activation-4.05e-02

Pos logit contributions
isphere+0.153
ethe+0.153
ITY+0.148
ities+0.146
agraph+0.134
Neg logit contributions
ranch-0.186
otten-0.167
hammad-0.166
athered-0.164
ulla-0.164
Token fire
Token ID2046
Feature activation+1.56e-01

Pos logit contributions
isphere+0.114
ethe+0.113
ITY+0.111
ities+0.110
oir+0.104
Neg logit contributions
ranch-0.053
otten-0.044
hammad-0.043
athered-0.042
 fir-0.042
Token and
Token ID290
Feature activation-2.90e-02

Pos logit contributions
ranch+0.362
otten+0.328
hammad+0.326
 fir+0.325
ulla+0.322
Neg logit contributions
isphere-0.276
ethe-0.275
ITY-0.266
ities-0.259
oir-0.237
Token called
Token ID1444
Feature activation-1.41e-01

Pos logit contributions
isphere+0.063
ethe+0.063
ITY+0.061
ities+0.060
agraph+0.056
Neg logit contributions
ranch-0.056
otten-0.049
hammad-0.049
 fir-0.049
athered-0.049
Tokener
Token ID263
Feature activation+1.40e-01

Pos logit contributions
isphere+0.094
ethe+0.094
ITY+0.091
ities+0.090
oir+0.084
Neg logit contributions
ranch-0.090
otten-0.080
hammad-0.079
athered-0.078
 fir-0.078
Token found
Token ID1043
Feature activation+6.34e-02

Pos logit contributions
ranch+0.276
otten+0.246
 fir+0.243
hammad+0.243
athered+0.241
Neg logit contributions
ethe-0.298
isphere-0.297
ITY-0.289
ities-0.283
oir-0.264
Token out
Token ID503
Feature activation-8.62e-02

Pos logit contributions
ranch+0.141
otten+0.127
 fir+0.126
hammad+0.125
athered+0.125
Neg logit contributions
isphere-0.120
ethe-0.118
ITY-0.115
ities-0.112
oir-0.104
Token about
Token ID546
Feature activation-6.11e-02

Pos logit contributions
isphere+0.146
ethe+0.145
ITY+0.140
ities+0.137
agraph+0.125
Neg logit contributions
ranch-0.207
otten-0.190
 fir-0.188
hammad-0.187
athered-0.185
Token Josh
Token ID8518
Feature activation+9.42e-02

Pos logit contributions
isphere+0.112
ethe+0.111
ITY+0.108
ities+0.105
oir+0.097
Neg logit contributions
ranch-0.139
otten-0.126
hammad-0.124
 fir-0.124
athered-0.123
Token
Token ID447
Feature activation+8.45e-02

Pos logit contributions
ranch+0.235
otten+0.214
hammad+0.212
 fir+0.212
athered+0.210
Neg logit contributions
isphere-0.153
ethe-0.151
ITY-0.145
ities-0.142
agraph-0.129
Token
Token ID247
Feature activation+7.87e-02

Pos logit contributions
ranch+0.174
otten+0.155
hammad+0.153
 fir+0.152
ulla+0.152
Neg logit contributions
isphere-0.173
ethe-0.173
ITY-0.167
ities-0.164
oir-0.153
Tokens
Token ID82
Feature activation+2.33e-02

Pos logit contributions
ranch+0.180
otten+0.163
hammad+0.162
 fir+0.160
athered+0.160
Neg logit contributions
isphere-0.142
ethe-0.142
ITY-0.137
ities-0.135
oir-0.124
Token history
Token ID2106
Feature activation-4.17e-02

Pos logit contributions
ranch+0.044
otten+0.040
 fir+0.039
hammad+0.039
athered+0.039
Neg logit contributions
isphere-0.051
ethe-0.051
ITY-0.049
ities-0.048
agraph-0.045
Token,
Token ID11
Feature activation-1.23e-02

Pos logit contributions
isphere+0.069
ethe+0.069
ITY+0.066
ities+0.065
agraph+0.059
Neg logit contributions
ranch-0.102
otten-0.093
hammad-0.092
 fir-0.092
athered-0.091
Token leading
Token ID3756
Feature activation+4.90e-02

Pos logit contributions
isphere+0.024
ethe+0.024
ITY+0.023
ities+0.023
agraph+0.021
Neg logit contributions
ranch-0.026
otten-0.024
hammad-0.024
athered-0.023
 fir-0.023
Token F
Token ID376
Feature activation+3.10e-02

Pos logit contributions
isphere+0.038
ethe+0.038
ITY+0.037
ities+0.036
oir+0.033
Neg logit contributions
ranch-0.036
otten-0.032
hammad-0.032
 fir-0.031
ulla-0.031
Tokenocal
Token ID4374
Feature activation-1.59e-02

Pos logit contributions
ranch+0.061
otten+0.054
hammad+0.054
athered+0.053
ulla+0.053
Neg logit contributions
isphere-0.066
ethe-0.066
ITY-0.064
ities-0.063
agraph-0.059
Token ac
Token ID936
Feature activation+1.21e-01

Pos logit contributions
isphere+0.030
ethe+0.030
ITY+0.029
ities+0.029
oir+0.027
Neg logit contributions
ranch-0.035
otten-0.031
hammad-0.031
 fir-0.031
athered-0.031
Tokenral
Token ID1373
Feature activation+8.33e-02

Pos logit contributions
ranch+0.231
otten+0.204
hammad+0.202
ulla+0.200
athered+0.200
Neg logit contributions
isphere-0.264
ethe-0.263
ITY-0.258
ities-0.251
oir-0.236
Token hyper
Token ID8718
Feature activation+4.86e-02

Pos logit contributions
ranch+0.183
otten+0.165
 fir+0.162
hammad+0.162
ulla+0.161
Neg logit contributions
isphere-0.159
ethe-0.158
ITY-0.153
ities-0.149
oir-0.139
Tokenker
Token ID6122
Feature activation+1.75e-01

Pos logit contributions
ranch+0.094
otten+0.084
hammad+0.083
 fir+0.082
athered+0.082
Neg logit contributions
isphere-0.105
ethe-0.104
ITY-0.102
ities-0.100
oir-0.093
Tokenat
Token ID265
Feature activation-1.05e-01

Pos logit contributions
ranch+0.408
otten+0.368
hammad+0.365
athered+0.362
ulla+0.361
Neg logit contributions
isphere-0.310
ethe-0.308
ITY-0.301
ities-0.290
oir-0.269
Tokenosis
Token ID5958
Feature activation-5.00e-03

Pos logit contributions
isphere+0.269
ethe+0.269
ITY+0.264
ities+0.258
oir+0.245
Neg logit contributions
ranch-0.159
otten-0.136
hammad-0.134
ulla-0.132
athered-0.132
Token (
Token ID357
Feature activation-2.70e-02

Pos logit contributions
ethe+0.009
isphere+0.009
ITY+0.008
ities+0.008
oir+0.008
Neg logit contributions
ranch-0.012
otten-0.011
hammad-0.011
 fir-0.011
ulla-0.010
Tokenalso
Token ID14508
Feature activation-2.53e-02

Pos logit contributions
isphere+0.050
ethe+0.050
ITY+0.048
ities+0.047
oir+0.044
Neg logit contributions
ranch-0.061
otten-0.055
hammad-0.054
 fir-0.054
athered-0.054
Token known
Token ID1900
Feature activation-6.91e-02

Pos logit contributions
isphere+0.049
ethe+0.049
ITY+0.048
ities+0.047
oir+0.043
Neg logit contributions
ranch-0.054
otten-0.049
hammad-0.048
 fir-0.048
athered-0.048
Token based
Token ID1912
Feature activation+9.81e-02

Pos logit contributions
ranch+0.179
otten+0.162
hammad+0.160
ulla+0.159
athered+0.158
Neg logit contributions
isphere-0.152
ethe-0.152
ITY-0.147
ities-0.144
agraph-0.133
Token in
Token ID287
Feature activation+1.08e-01

Pos logit contributions
ranch+0.221
otten+0.200
hammad+0.198
 fir+0.196
athered+0.196
Neg logit contributions
isphere-0.181
ethe-0.180
ITY-0.175
ities-0.172
agraph-0.158
Token New
Token ID968
Feature activation-1.92e-02

Pos logit contributions
ranch+0.220
otten+0.197
hammad+0.195
athered+0.192
 fir+0.192
Neg logit contributions
isphere-0.222
ethe-0.222
ITY-0.216
ities-0.213
oir-0.197
Token Jersey
Token ID8221
Feature activation+1.80e-01

Pos logit contributions
isphere+0.039
ethe+0.039
ITY+0.038
ities+0.037
oir+0.035
Neg logit contributions
ranch-0.040
otten-0.035
hammad-0.035
 fir-0.035
athered-0.035
Token,
Token ID11
Feature activation+7.90e-02

Pos logit contributions
ranch+0.494
otten+0.455
hammad+0.451
 fir+0.450
ulla+0.449
Neg logit contributions
isphere-0.242
ethe-0.240
ITY-0.229
ities-0.223
oir-0.198
Token said
Token ID531
Feature activation+7.43e-02

Pos logit contributions
ranch+0.172
otten+0.155
hammad+0.154
 fir+0.152
athered+0.152
Neg logit contributions
isphere-0.152
ethe-0.151
ITY-0.147
ities-0.144
agraph-0.133
Token on
Token ID319
Feature activation+6.30e-02

Pos logit contributions
ranch+0.170
otten+0.153
 fir+0.152
hammad+0.152
athered+0.151
Neg logit contributions
isphere-0.135
ethe-0.134
ITY-0.130
ities-0.127
oir-0.117
Token Thursday
Token ID3635
Feature activation+4.02e-03

Pos logit contributions
ranch+0.136
otten+0.123
hammad+0.122
 fir+0.121
athered+0.120
Neg logit contributions
isphere-0.122
ethe-0.121
ITY-0.118
ities-0.115
oir-0.107
Token that
Token ID326
Feature activation+1.67e-02

Pos logit contributions
ranch+0.010
otten+0.009
hammad+0.009
 fir+0.009
athered+0.009
Neg logit contributions
isphere-0.007
ethe-0.007
ITY-0.007
ities-0.006
oir-0.006
Token the
Token ID262
Feature activation+3.70e-02

Pos logit contributions
ranch+0.038
otten+0.035
 fir+0.035
hammad+0.034
athered+0.034
Neg logit contributions
isphere-0.030
ethe-0.030
ITY-0.029
ities-0.028
oir-0.026
Token Food
Token ID7318
Feature activation-1.08e-01

Pos logit contributions
ranch+0.078
otten+0.070
 fir+0.069
hammad+0.069
athered+0.069
Neg logit contributions
isphere-0.074
ethe-0.073
ITY-0.071
ities-0.070
oir-0.065
Tokengallery
Token ID24460
Feature activation+8.02e-02

Pos logit contributions
isphere+0.221
ethe+0.220
ITY+0.213
ities+0.209
oir+0.192
Neg logit contributions
ranch-0.280
otten-0.253
hammad-0.251
 fir-0.249
athered-0.249
Token id
Token ID4686
Feature activation-5.48e-02

Pos logit contributions
ranch+0.142
otten+0.124
hammad+0.123
 fir+0.122
athered+0.122
Neg logit contributions
ethe-0.187
isphere-0.187
ITY-0.181
ities-0.179
oir-0.168
Token=
Token ID28
Feature activation+1.88e-01

Pos logit contributions
isphere+0.096
ethe+0.095
ITY+0.092
ities+0.090
agraph+0.083
Neg logit contributions
ranch-0.129
otten-0.116
hammad-0.116
athered-0.115
 fir-0.114
Token159
Token ID19707
Feature activation+4.07e-02

Pos logit contributions
ranch+0.417
otten+0.376
hammad+0.373
athered+0.369
 fir+0.368
Neg logit contributions
isphere-0.355
ethe-0.352
ITY-0.341
ities-0.335
agraph-0.310
Token]
Token ID60
Feature activation-3.09e-02

Pos logit contributions
ranch+0.086
otten+0.077
hammad+0.077
 fir+0.076
athered+0.076
Neg logit contributions
isphere-0.080
ethe-0.080
ITY-0.078
ities-0.076
agraph-0.071
Token
Token ID198
Feature activation+2.66e-02

Pos logit contributions
isphere+0.059
ethe+0.058
ITY+0.057
ities+0.056
oir+0.051
Neg logit contributions
ranch-0.068
otten-0.061
hammad-0.061
 fir-0.060
athered-0.060
Token
Token ID198
Feature activation+1.04e-02

Pos logit contributions
ranch+0.059
otten+0.053
hammad+0.053
 fir+0.052
athered+0.052
Neg logit contributions
isphere-0.050
ethe-0.050
ITY-0.048
ities-0.047
agraph-0.044
TokenThe
Token ID464
Feature activation+6.73e-02

Pos logit contributions
ranch+0.023
otten+0.021
hammad+0.021
athered+0.020
 fir+0.020
Neg logit contributions
isphere-0.020
ethe-0.019
ITY-0.019
ities-0.018
oir-0.017
Token unfortunate
Token ID14855
Feature activation-4.16e-02

Pos logit contributions
ranch+0.142
otten+0.128
 fir+0.126
hammad+0.126
athered+0.125
Neg logit contributions
isphere-0.134
ethe-0.133
ITY-0.129
ities-0.127
oir-0.118
Token bulk
Token ID11963
Feature activation+1.12e-01

Pos logit contributions
isphere+0.090
ethe+0.089
ITY+0.086
ities+0.084
oir+0.080
Neg logit contributions
ranch-0.081
otten-0.071
 fir-0.071
hammad-0.071
athered-0.070
Token of
Token ID286
Feature activation-7.24e-02

Pos logit contributions
ranch+0.242
otten+0.218
hammad+0.216
 fir+0.214
athered+0.213
Neg logit contributions
isphere-0.216
ethe-0.215
ITY-0.209
ities-0.205
oir-0.190
Tokens
Token ID82
Feature activation-7.72e-03

Pos logit contributions
isphere+0.049
ethe+0.049
ITY+0.048
ities+0.046
oir+0.043
Neg logit contributions
ranch-0.059
otten-0.053
hammad-0.053
 fir-0.052
athered-0.052
Token our
Token ID674
Feature activation-5.80e-02

Pos logit contributions
isphere+0.015
ethe+0.015
ITY+0.014
ities+0.014
oir+0.013
Neg logit contributions
ranch-0.017
otten-0.015
hammad-0.015
 fir-0.015
athered-0.015
Token job
Token ID1693
Feature activation+3.24e-03

Pos logit contributions
isphere+0.130
ethe+0.129
ITY+0.126
ities+0.123
agraph+0.116
Neg logit contributions
ranch-0.109
otten-0.096
hammad-0.095
 fir-0.094
athered-0.094
Token,
Token ID11
Feature activation+1.72e-02

Pos logit contributions
ranch+0.008
otten+0.007
hammad+0.007
 fir+0.007
athered+0.007
Neg logit contributions
isphere-0.006
ethe-0.006
ITY-0.005
ities-0.005
agraph-0.005
Token not
Token ID407
Feature activation-9.93e-03

Pos logit contributions
ranch+0.045
otten+0.041
hammad+0.041
 fir+0.040
athered+0.040
Neg logit contributions
isphere-0.026
ethe-0.025
ITY-0.025
ities-0.024
oir-0.022
Token theirs
Token ID22021
Feature activation-2.31e-01

Pos logit contributions
isphere+0.019
ethe+0.019
ITY+0.018
ities+0.018
oir+0.016
Neg logit contributions
ranch-0.022
otten-0.020
hammad-0.020
 fir-0.020
athered-0.020
Token.
Token ID13
Feature activation+6.12e-03

Pos logit contributions
isphere+0.319
ethe+0.314
ITY+0.304
ities+0.293
agraph+0.263
Neg logit contributions
ranch-0.629
otten-0.578
hammad-0.574
 fir-0.571
athered-0.570
Token
Token ID447
Feature activation+6.66e-03

Pos logit contributions
ranch+0.015
otten+0.014
hammad+0.014
 fir+0.014
ulla+0.014
Neg logit contributions
isphere-0.010
ethe-0.010
ITY-0.009
ities-0.009
agraph-0.008
Token
Token ID251
Feature activation-1.21e-02

Pos logit contributions
ranch+0.014
otten+0.013
hammad+0.013
 fir+0.012
athered+0.012
Neg logit contributions
isphere-0.013
ethe-0.013
ITY-0.013
ities-0.013
oir-0.012
Token
Token ID198
Feature activation-4.29e-02

Pos logit contributions
isphere+0.023
ethe+0.023
ITY+0.022
ities+0.022
agraph+0.020
Neg logit contributions
ranch-0.026
otten-0.024
hammad-0.023
 fir-0.023
ulla-0.023
Token
Token ID198
Feature activation-5.95e-02

Pos logit contributions
isphere+0.080
ethe+0.079
ITY+0.077
ities+0.075
agraph+0.069
Neg logit contributions
ranch-0.096
otten-0.087
hammad-0.086
 fir-0.085
athered-0.085
Token is
Token ID318
Feature activation+3.10e-02

Pos logit contributions
isphere+0.076
ethe+0.074
ITY+0.071
ities+0.069
agraph+0.065
Neg logit contributions
ranch-0.105
otten-0.096
hammad-0.095
 fir-0.095
athered-0.094
Token job
Token ID1693
Feature activation-7.83e-03

Pos logit contributions
ranch+0.066
otten+0.060
 fir+0.059
hammad+0.059
athered+0.059
Neg logit contributions
isphere-0.061
ethe-0.060
ITY-0.059
ities-0.057
agraph-0.053
Token one
Token ID530
Feature activation-2.01e-02

Pos logit contributions
isphere+0.015
ethe+0.015
ITY+0.015
ities+0.014
agraph+0.013
Neg logit contributions
ranch-0.017
otten-0.015
hammad-0.015
 fir-0.015
athered-0.015
Token.
Token ID13
Feature activation+4.08e-02

Pos logit contributions
isphere+0.034
ethe+0.034
ITY+0.032
ities+0.032
agraph+0.029
Neg logit contributions
ranch-0.049
otten-0.044
hammad-0.044
 fir-0.044
athered-0.044
Token Lots
Token ID25024
Feature activation+4.71e-02

Pos logit contributions
ranch+0.084
otten+0.075
hammad+0.075
 fir+0.074
athered+0.074
Neg logit contributions
isphere-0.083
ethe-0.083
ITY-0.080
ities-0.079
agraph-0.073
Token of
Token ID286
Feature activation+1.80e-02

Pos logit contributions
ranch+0.103
otten+0.093
hammad+0.092
athered+0.091
 fir+0.091
Neg logit contributions
isphere-0.090
ethe-0.090
ITY-0.087
ities-0.086
oir-0.079
Token systems
Token ID3341
Feature activation+8.40e-02

Pos logit contributions
ranch+0.039
otten+0.035
hammad+0.035
 fir+0.035
athered+0.034
Neg logit contributions
isphere-0.035
ethe-0.035
ITY-0.034
ities-0.033
agraph-0.030
Token in
Token ID287
Feature activation-3.21e-03

Pos logit contributions
ranch+0.170
otten+0.152
 fir+0.150
hammad+0.150
athered+0.150
Neg logit contributions
isphere-0.174
ethe-0.173
ITY-0.168
ities-0.164
oir-0.154
Token place
Token ID1295
Feature activation-2.36e-02

Pos logit contributions
isphere+0.006
ethe+0.006
ITY+0.006
ities+0.006
agraph+0.006
Neg logit contributions
ranch-0.007
otten-0.006
hammad-0.006
 fir-0.006
athered-0.006
Token to
Token ID284
Feature activation-2.59e-02

Pos logit contributions
isphere+0.046
ethe+0.046
ITY+0.045
ities+0.044
oir+0.041
Neg logit contributions
ranch-0.050
otten-0.045
hammad-0.045
 fir-0.045
athered-0.044
Token check
Token ID2198
Feature activation-8.51e-02

Pos logit contributions
isphere+0.057
ethe+0.057
ITY+0.056
ities+0.055
agraph+0.051
Neg logit contributions
ranch-0.049
otten-0.043
hammad-0.043
 fir-0.042
athered-0.042
Token however
Token ID2158
Feature activation-8.14e-02

Pos logit contributions
ranch+0.117
otten+0.106
hammad+0.105
 fir+0.104
athered+0.104
Neg logit contributions
isphere-0.094
ethe-0.094
ITY-0.091
ities-0.089
agraph-0.082
Token,
Token ID11
Feature activation+1.24e-02

Pos logit contributions
isphere+0.106
ethe+0.106
ITY+0.101
ities+0.098
oir+0.087
Neg logit contributions
ranch-0.227
otten-0.210
hammad-0.208
 fir-0.207
athered-0.207
Token is
Token ID318
Feature activation-4.79e-03

Pos logit contributions
ranch+0.028
otten+0.025
hammad+0.025
 fir+0.024
athered+0.024
Neg logit contributions
isphere-0.023
ethe-0.023
ITY-0.023
ities-0.022
agraph-0.020
Token allowed
Token ID3142
Feature activation+1.00e-01

Pos logit contributions
isphere+0.010
ethe+0.010
ITY+0.010
ities+0.010
oir+0.009
Neg logit contributions
ranch-0.009
otten-0.008
hammad-0.008
 fir-0.008
athered-0.008
Token to
Token ID284
Feature activation+3.51e-02

Pos logit contributions
ranch+0.221
otten+0.199
hammad+0.197
 fir+0.195
athered+0.195
Neg logit contributions
isphere-0.189
ethe-0.189
ITY-0.183
ities-0.179
oir-0.166
Token do
Token ID466
Feature activation+1.52e-03

Pos logit contributions
ranch+0.064
otten+0.057
hammad+0.056
 fir+0.056
athered+0.056
Neg logit contributions
isphere-0.080
ethe-0.079
ITY-0.077
ities-0.076
oir-0.071
Token so
Token ID523
Feature activation+5.69e-02

Pos logit contributions
ranch+0.003
otten+0.003
hammad+0.003
 fir+0.003
athered+0.003
Neg logit contributions
isphere-0.003
ethe-0.003
ITY-0.003
ities-0.003
oir-0.003
Token.
Token ID13
Feature activation+2.62e-02

Pos logit contributions
ranch+0.148
otten+0.136
 fir+0.135
athered+0.135
hammad+0.134
Neg logit contributions
isphere-0.085
ethe-0.084
ITY-0.081
ities-0.078
oir-0.071
Token
Token ID198
Feature activation+2.17e-02

Pos logit contributions
ranch+0.056
otten+0.051
hammad+0.050
 fir+0.050
athered+0.050
Neg logit contributions
isphere-0.051
ethe-0.051
ITY-0.050
ities-0.049
agraph-0.045
Token
Token ID198
Feature activation+1.72e-02

Pos logit contributions
ranch+0.049
otten+0.044
hammad+0.043
 fir+0.043
athered+0.043
Neg logit contributions
isphere-0.041
ethe-0.040
ITY-0.039
ities-0.038
agraph-0.035
TokenMc
Token ID9742
Feature activation+1.13e-01

Pos logit contributions
ranch+0.039
otten+0.035
hammad+0.035
athered+0.035
 fir+0.034
Neg logit contributions
isphere-0.032
ethe-0.031
ITY-0.030
ities-0.030
agraph-0.027
Token
Token ID198
Feature activation-3.93e-02

Pos logit contributions
ranch+0.006
otten+0.005
hammad+0.005
 fir+0.005
athered+0.005
Neg logit contributions
isphere-0.005
ethe-0.005
ITY-0.005
ities-0.005
agraph-0.005
Token
Token ID198
Feature activation-5.32e-02

Pos logit contributions
isphere+0.074
ethe+0.073
ITY+0.071
ities+0.069
agraph+0.064
Neg logit contributions
ranch-0.088
otten-0.079
hammad-0.078
 fir-0.078
athered-0.078
TokenOver
Token ID5886
Feature activation+1.22e-01

Pos logit contributions
isphere+0.102
ethe+0.101
ITY+0.098
ities+0.096
agraph+0.089
Neg logit contributions
ranch-0.117
otten-0.105
hammad-0.104
athered-0.103
 fir-0.103
Token the
Token ID262
Feature activation-2.68e-02

Pos logit contributions
ranch+0.271
otten+0.245
hammad+0.243
 fir+0.241
athered+0.241
Neg logit contributions
isphere-0.228
ethe-0.227
ITY-0.221
ities-0.216
oir-0.200
Token past
Token ID1613
Feature activation-7.71e-02

Pos logit contributions
isphere+0.063
ethe+0.062
ITY+0.061
ities+0.060
agraph+0.056
Neg logit contributions
ranch-0.047
otten-0.041
hammad-0.041
athered-0.040
ulla-0.040
Token few
Token ID1178
Feature activation-3.54e-02

Pos logit contributions
isphere+0.165
ethe+0.164
ITY+0.160
ities+0.157
oir+0.146
Neg logit contributions
ranch-0.151
otten-0.135
hammad-0.133
 fir-0.132
athered-0.132
Token months
Token ID1933
Feature activation-6.33e-02

Pos logit contributions
isphere+0.080
ethe+0.080
ITY+0.078
ities+0.076
oir+0.072
Neg logit contributions
ranch-0.065
otten-0.057
 fir-0.056
hammad-0.056
athered-0.056
Token we
Token ID356
Feature activation-3.23e-02

Pos logit contributions
isphere+0.098
ethe+0.098
ITY+0.094
ities+0.091
agraph+0.083
Neg logit contributions
ranch-0.161
otten-0.148
hammad-0.146
 fir-0.146
athered-0.145
Token have
Token ID423
Feature activation+8.05e-03

Pos logit contributions
isphere+0.061
ethe+0.061
ITY+0.059
ities+0.058
oir+0.054
Neg logit contributions
ranch-0.071
otten-0.064
athered-0.064
hammad-0.063
 fir-0.063
Token been
Token ID587
Feature activation+3.28e-02

Pos logit contributions
ranch+0.014
otten+0.013
hammad+0.013
 fir+0.012
athered+0.012
Neg logit contributions
isphere-0.019
ethe-0.019
ITY-0.018
ities-0.018
agraph-0.017
Token hearing
Token ID4854
Feature activation+4.19e-03

Pos logit contributions
ranch+0.066
otten+0.059
 fir+0.059
athered+0.058
hammad+0.058
Neg logit contributions
isphere-0.068
ethe-0.068
ITY-0.066
ities-0.065
oir-0.061
Token these
Token ID777
Feature activation+1.74e-02

Pos logit contributions
isphere+0.002
ethe+0.002
ITY+0.002
ities+0.002
agraph+0.001
Neg logit contributions
ranch-0.002
otten-0.002
 fir-0.002
hammad-0.002
athered-0.002
Token tasty
Token ID25103
Feature activation+1.89e-02

Pos logit contributions
ranch+0.037
otten+0.034
hammad+0.033
 fir+0.033
athered+0.033
Neg logit contributions
isphere-0.034
ethe-0.034
ITY-0.033
ities-0.032
oir-0.030
Token,
Token ID11
Feature activation-3.32e-02

Pos logit contributions
ranch+0.041
otten+0.037
hammad+0.036
 fir+0.036
athered+0.036
Neg logit contributions
isphere-0.037
ethe-0.037
ITY-0.036
ities-0.035
oir-0.032
Token super
Token ID2208
Feature activation+1.52e-01

Pos logit contributions
isphere+0.064
ethe+0.064
ITY+0.062
ities+0.060
oir+0.056
Neg logit contributions
ranch-0.072
otten-0.065
hammad-0.065
 fir-0.064
athered-0.064
Token-
Token ID12
Feature activation+6.04e-02

Pos logit contributions
ranch+0.363
otten+0.329
hammad+0.325
 fir+0.324
athered+0.324
Neg logit contributions
isphere-0.264
ethe-0.261
ITY-0.253
ities-0.247
agraph-0.227
Tokennut
Token ID14930
Feature activation-3.60e-01

Pos logit contributions
ranch+0.132
otten+0.118
hammad+0.117
athered+0.116
 fir+0.115
Neg logit contributions
isphere-0.117
ethe-0.116
ITY-0.113
ities-0.110
agraph-0.102
Tokenrit
Token ID799
Feature activation+5.91e-02

Pos logit contributions
isphere+0.823
ethe+0.821
ITY+0.800
ities+0.789
oir+0.740
Neg logit contributions
ranch-0.649
otten-0.570
hammad-0.566
 fir-0.559
athered-0.557
Tokenious
Token ID699
Feature activation+6.04e-02

Pos logit contributions
ranch+0.202
otten+0.190
hammad+0.187
athered+0.187
 fir+0.187
Neg logit contributions
isphere-0.041
ethe-0.040
ITY-0.038
ities-0.035
agraph-0.027
Token wild
Token ID4295
Feature activation+7.95e-02

Pos logit contributions
ranch+0.132
otten+0.119
hammad+0.118
 fir+0.118
athered+0.117
Neg logit contributions
isphere-0.116
ethe-0.115
ITY-0.112
ities-0.109
agraph-0.101
Token plants
Token ID6134
Feature activation+4.81e-02

Pos logit contributions
ranch+0.167
otten+0.149
hammad+0.148
 fir+0.147
athered+0.146
Neg logit contributions
isphere-0.159
ethe-0.159
ITY-0.154
ities-0.150
agraph-0.140
Token assuming
Token ID13148
Feature activation-8.97e-02

Pos logit contributions
ranch+0.108
otten+0.099
 fir+0.099
hammad+0.098
athered+0.097
Neg logit contributions
isphere-0.088
ethe-0.087
ITY-0.084
ities-0.081
agraph-0.076
Token declines
Token ID24459
Feature activation-1.32e-01

Pos logit contributions
isphere+0.180
ethe+0.178
ITY+0.172
ities+0.168
agraph+0.155
Neg logit contributions
ranch-0.236
otten-0.214
hammad-0.212
 fir-0.211
athered-0.211
Token to
Token ID284
Feature activation-1.17e-02

Pos logit contributions
ethe+0.248
isphere+0.248
ITY+0.240
ities+0.236
agraph+0.217
Neg logit contributions
ranch-0.292
otten-0.263
hammad-0.261
 fir-0.258
athered-0.258
Token disclose
Token ID15771
Feature activation+4.95e-02

Pos logit contributions
isphere+0.024
ethe+0.024
ITY+0.024
ities+0.023
oir+0.022
Neg logit contributions
ranch-0.024
otten-0.021
hammad-0.021
 fir-0.021
athered-0.021
Token his
Token ID465
Feature activation+8.61e-02

Pos logit contributions
ranch+0.109
otten+0.098
 fir+0.097
hammad+0.097
athered+0.096
Neg logit contributions
isphere-0.095
ethe-0.094
ITY-0.091
ities-0.089
oir-0.083
Token tax
Token ID1687
Feature activation-1.30e-02

Pos logit contributions
ranch+0.160
otten+0.141
 fir+0.139
hammad+0.139
athered+0.138
Neg logit contributions
isphere-0.194
ethe-0.192
ITY-0.187
ities-0.183
agraph-0.173
Token rate
Token ID2494
Feature activation-3.57e-01

Pos logit contributions
isphere+0.024
ethe+0.023
ITY+0.023
ities+0.022
agraph+0.020
Neg logit contributions
ranch-0.030
otten-0.027
hammad-0.027
 fir-0.027
athered-0.027
Token,
Token ID11
Feature activation-4.13e-02

Pos logit contributions
isphere+0.592
ethe+0.589
ITY+0.569
ities+0.554
agraph+0.507
Neg logit contributions
ranch-0.872
otten-0.795
hammad-0.789
 fir-0.783
athered-0.781
Token stating
Token ID12316
Feature activation-1.12e-02

Pos logit contributions
isphere+0.081
ethe+0.081
ITY+0.078
ities+0.077
agraph+0.071
Neg logit contributions
ranch-0.089
otten-0.080
hammad-0.079
ulla-0.078
athered-0.078
Token in
Token ID287
Feature activation-4.13e-02

Pos logit contributions
isphere+0.021
ethe+0.020
ITY+0.020
ities+0.019
oir+0.018
Neg logit contributions
ranch-0.026
otten-0.023
hammad-0.023
athered-0.023
 fir-0.023
Token an
Token ID281
Feature activation-4.85e-02

Pos logit contributions
isphere+0.082
ethe+0.081
ITY+0.079
ities+0.077
oir+0.072
Neg logit contributions
ranch-0.088
otten-0.079
hammad-0.078
 fir-0.078
athered-0.077
Token ABC
Token ID9738
Feature activation-8.31e-02

Pos logit contributions
isphere+0.091
ethe+0.090
ITY+0.088
ities+0.086
oir+0.079
Neg logit contributions
ranch-0.108
otten-0.097
hammad-0.097
 fir-0.096
athered-0.096
Token Se
Token ID1001
Feature activation-4.27e-02

Pos logit contributions
isphere+0.156
ethe+0.155
ITY+0.151
ities+0.148
agraph+0.137
Neg logit contributions
ranch-0.175
otten-0.157
hammad-0.155
 fir-0.154
athered-0.154
Tokeneker
Token ID28233
Feature activation-1.53e-01

Pos logit contributions
isphere+0.076
ethe+0.074
ITY+0.074
ities+0.071
agraph+0.066
Neg logit contributions
ranch-0.099
otten-0.090
hammad-0.089
athered-0.089
ulla-0.088
Token
Token ID198
Feature activation-5.63e-02

Pos logit contributions
isphere+0.280
ethe+0.279
ITY+0.271
ities+0.266
oir+0.245
Neg logit contributions
ranch-0.345
otten-0.311
hammad-0.309
 fir-0.306
athered-0.306
Token
Token ID198
Feature activation-7.04e-02

Pos logit contributions
isphere+0.105
ethe+0.105
ITY+0.101
ities+0.099
agraph+0.092
Neg logit contributions
ranch-0.126
otten-0.113
hammad-0.112
 fir-0.111
athered-0.111
TokenPh
Token ID2725
Feature activation-4.41e-02

Pos logit contributions
isphere+0.137
ethe+0.137
ITY+0.132
ities+0.130
agraph+0.121
Neg logit contributions
ranch-0.151
otten-0.136
hammad-0.135
athered-0.133
 fir-0.133
Tokenyt
Token ID20760
Feature activation-4.45e-01

Pos logit contributions
isphere+0.067
ethe+0.067
ITY+0.065
ities+0.063
agraph+0.057
Neg logit contributions
ranch-0.114
otten-0.104
hammad-0.103
athered-0.103
ulla-0.102
Tokenot
Token ID313
Feature activation+8.46e-03

Pos logit contributions
isphere+0.865
ethe+0.862
ITY+0.832
ities+0.819
agraph+0.760
Neg logit contributions
ranch-0.960
otten-0.860
hammad-0.858
 fir-0.849
athered-0.847
Tokenitan
Token ID18642
Feature activation-7.18e-02

Pos logit contributions
ranch+0.015
otten+0.013
hammad+0.013
 fir+0.013
athered+0.013
Neg logit contributions
isphere-0.020
ethe-0.020
ITY-0.019
ities-0.019
agraph-0.018
Token vs
Token ID3691
Feature activation+1.48e-02

Pos logit contributions
isphere+0.133
ethe+0.132
ITY+0.129
ities+0.126
agraph+0.116
Neg logit contributions
ranch-0.161
otten-0.146
hammad-0.144
 fir-0.143
athered-0.143
Token Torch
Token ID34868
Feature activation-1.67e-01

Pos logit contributions
ranch+0.031
otten+0.028
hammad+0.028
 fir+0.027
athered+0.027
Neg logit contributions
isphere-0.029
ethe-0.029
ITY-0.028
ities-0.028
agraph-0.026
Tokenling
Token ID1359
Feature activation+1.99e-02

Pos logit contributions
isphere+0.330
ethe+0.329
ITY+0.319
ities+0.313
oir+0.290
Neg logit contributions
ranch-0.355
otten-0.319
hammad-0.316
 fir-0.313
athered-0.312
Token to
Token ID284
Feature activation-3.62e-02

Pos logit contributions
isphere+0.131
ethe+0.130
ITY+0.127
ities+0.124
agraph+0.116
Neg logit contributions
ranch-0.144
otten-0.130
hammad-0.129
 fir-0.128
athered-0.127
Token practice
Token ID3357
Feature activation-1.68e-01

Pos logit contributions
isphere+0.081
ethe+0.080
ITY+0.078
ities+0.076
agraph+0.072
Neg logit contributions
ranch-0.068
otten-0.059
 fir-0.059
athered-0.059
hammad-0.058
Token Lac
Token ID23115
Feature activation+1.19e-01

Pos logit contributions
isphere+0.275
ethe+0.272
ITY+0.263
ities+0.257
agraph+0.235
Neg logit contributions
ranch-0.413
otten-0.376
hammad-0.374
 fir-0.372
athered-0.370
Tokenanian
Token ID38336
Feature activation+3.79e-01

Pos logit contributions
ranch+0.237
otten+0.211
hammad+0.209
ulla+0.207
 fir+0.206
Neg logit contributions
isphere-0.251
ethe-0.248
ITY-0.243
ities-0.237
agraph-0.221
Token psycho
Token ID30731
Feature activation+1.57e-01

Pos logit contributions
ranch+0.887
otten+0.806
 fir+0.800
hammad+0.799
ulla+0.791
Neg logit contributions
isphere-0.661
ethe-0.648
ITY-0.628
ities-0.608
agraph-0.570
Tokenanalysis
Token ID20930
Feature activation-4.54e-01

Pos logit contributions
ranch+0.387
otten+0.352
hammad+0.350
athered+0.347
 fir+0.347
Neg logit contributions
isphere-0.258
ethe-0.253
ITY-0.247
ities-0.239
oir-0.220
Token.
Token ID13
Feature activation-4.27e-03

Pos logit contributions
isphere+0.637
ethe+0.632
ITY+0.607
ities+0.590
agraph+0.529
Neg logit contributions
ranch-1.225
otten-1.125
hammad-1.118
 fir-1.111
athered-1.108
Token This
Token ID770
Feature activation+5.50e-03

Pos logit contributions
isphere+0.009
ethe+0.009
ITY+0.009
ities+0.008
agraph+0.008
Neg logit contributions
ranch-0.009
otten-0.008
hammad-0.008
 fir-0.008
ulla-0.007
Token is
Token ID318
Feature activation-2.55e-03

Pos logit contributions
ranch+0.012
otten+0.011
hammad+0.011
 fir+0.011
athered+0.011
Neg logit contributions
isphere-0.010
ethe-0.010
ITY-0.010
ities-0.010
oir-0.009
Token bullshit
Token ID20041
Feature activation+1.83e-02

Pos logit contributions
isphere+0.005
ethe+0.005
ITY+0.005
ities+0.005
agraph+0.004
Neg logit contributions
ranch-0.006
otten-0.005
 fir-0.005
hammad-0.005
athered-0.005
Token.
Token ID13
Feature activation+4.92e-02

Pos logit contributions
ranch+0.050
otten+0.046
hammad+0.046
 fir+0.045
athered+0.045
Neg logit contributions
isphere-0.025
ethe-0.025
ITY-0.024
ities-0.023
agraph-0.021
Token in
Token ID287
Feature activation-7.52e-03

Pos logit contributions
isphere+0.069
ethe+0.069
ITY+0.067
ities+0.065
agraph+0.061
Neg logit contributions
ranch-0.082
otten-0.074
 fir-0.074
hammad-0.073
athered-0.073
Token the
Token ID262
Feature activation-7.29e-03

Pos logit contributions
isphere+0.014
ethe+0.014
ITY+0.013
ities+0.013
agraph+0.012
Neg logit contributions
ranch-0.017
otten-0.015
hammad-0.015
 fir-0.015
athered-0.015
Token city
Token ID1748
Feature activation-3.11e-02

Pos logit contributions
isphere+0.014
ethe+0.014
ITY+0.014
ities+0.013
agraph+0.012
Neg logit contributions
ranch-0.016
otten-0.014
hammad-0.014
 fir-0.014
athered-0.014
Token of
Token ID286
Feature activation+1.77e-02

Pos logit contributions
isphere+0.056
ethe+0.056
ITY+0.054
ities+0.053
agraph+0.049
Neg logit contributions
ranch-0.071
otten-0.064
hammad-0.064
 fir-0.063
athered-0.063
Token Daytona
Token ID47299
Feature activation-1.26e-01

Pos logit contributions
ranch+0.036
otten+0.032
hammad+0.032
 fir+0.032
athered+0.032
Neg logit contributions
isphere-0.036
ethe-0.036
ITY-0.035
ities-0.034
oir-0.032
Token Beach
Token ID8511
Feature activation-3.71e-01

Pos logit contributions
isphere+0.228
ethe+0.227
ITY+0.220
ities+0.216
oir+0.198
Neg logit contributions
ranch-0.289
otten-0.261
hammad-0.259
 fir-0.257
athered-0.257
Token where
Token ID810
Feature activation+2.50e-02

Pos logit contributions
isphere+0.639
ethe+0.637
ITY+0.616
ities+0.603
agraph+0.552
Neg logit contributions
ranch-0.881
otten-0.799
hammad-0.793
 fir-0.787
athered-0.786
Token Whites
Token ID29290
Feature activation+7.53e-02

Pos logit contributions
ranch+0.056
otten+0.051
hammad+0.050
 fir+0.050
athered+0.050
Neg logit contributions
isphere-0.046
ethe-0.046
ITY-0.045
ities-0.044
agraph-0.041
Token and
Token ID290
Feature activation-2.51e-02

Pos logit contributions
ranch+0.149
otten+0.132
hammad+0.131
 fir+0.130
athered+0.130
Neg logit contributions
isphere-0.160
ethe-0.159
ITY-0.155
ities-0.152
agraph-0.142
Token Blacks
Token ID27875
Feature activation-1.30e-01

Pos logit contributions
isphere+0.047
ethe+0.047
ITY+0.045
ities+0.044
agraph+0.041
Neg logit contributions
ranch-0.056
otten-0.050
hammad-0.050
 fir-0.050
athered-0.050
Token could
Token ID714
Feature activation+1.06e-02

Pos logit contributions
isphere+0.284
ethe+0.283
ITY+0.275
ities+0.271
agraph+0.253
Neg logit contributions
ranch-0.251
otten-0.222
hammad-0.220
 fir-0.218
athered-0.218