TOP ACTIVATIONS
MAX = 6.411

first to hear about Nation Travels destinations , and explore the
first to hear about Nation Travels destinations , and explore the
ce / edd 75 / AUT OC R OP / h
acids for fuel . Inter mitt ent fasting and spending more
ar ( D ish ) owes V oom ( AM C
presidential nominee Hillary Clinton Hillary Diane Rodham Clinton Sanders : '
mix of low - s ulf ur fuel oil and diesel
MORE and Hillary Clinton Hillary Diane Rodham Clinton Sanders : '
mandate . The Bush Administration susp ends the OR I proposal
Los Angeles Times blogger Andrew Malcolm , you flip the script
) is difficult ," Lam orie llo said . " But
would go to cover debts owed the City of Toronto and
this . P ump kin Seed Fl our
Clinton ended w elfare as we know it ,
an alternative to The Ad vertis er , a different voice
MORE and Hillary Clinton Hillary Diane Rodham Clinton Sanders : '
s been made since owes something to Annie Hall .
says NASA Goddard glac iologist Kelly Br unt .
the Supreme Court Orders on Aadhaar The Supreme Court
23 Muslim organisations in Tamil Nadu before its release and before

MIN ACTIVATIONS
MIN = -5.409

! If you need a compound expression , use ng -
in clock speeds . In OC M ODE the core increases
warm and stubborn sonic imp urities , having been encoded in
earlier works like The Cour tyard , where the characters boast
was characterized as having bacterial vag in osis ( B V
lot of sense . Its admittedly high fuel consumption , noise
a Catalan town in a bid to sc upper the referendum
tested the single card in OC mode , but we are
s where the admittedly tiny piece of good news
be explained away as an aber ration of the primitive mind
army and its allies captured turf around the southern edge of
amongst the officers , with crude and disgusting comments ."" Oh
honey comb to mimic the compound eye of a fly .
since March 2009 in a bid to help economic recovery .
in turn results in the dil ution of talent that the
passenger planes . <|endoftext|> An amateur football match in Brazil turned
acquired by reading from an Atomic , as we
rather - than - bre xit - is - the -
smell the scent of burning flesh .
Audio To O & A Bits 2008 01 11 O &

INTERVAL 3.456 - 6.411
CONTAINS 0.043%

Neil Thomson - A Det ailed Review http ://
over the authority is owed more than $ 251 ,
national cultures within the British Isles can claim to be literary
Natural Markets will open new store at Five Corn ers in
Canadian public identify with enough faces around the table . If

INTERVAL 0.501 - 3.456
CONTAINS 22.145%

office secretary who steals $ 40 , 000 from her boss
registration will expire , and the date of that exp iry
give back to them and use that to improve their experience
not impossible that this could happen again . If
price they will want , so factories will close down and

INTERVAL -2.454 - 0.501
CONTAINS 77.232%

formidable Diana Vill iers . She is too much for Jack
and vegetables , keeps honey bees , cultiv ates mushrooms ,
of books that you want to read on the Kindle ,
mind , we do realize that some are more exciting than
, and to continue paying my tit hes to the church

INTERVAL -5.409 - -2.454
CONTAINS 0.580%

aine also did a good job repeatedly pressing on Trump
especially when you consider the Las Vegas case in its larger
pest il ent congregation of vap ors . What
stock was trading when the bid approach was made on 1
a week . Still , there is a right
Token first
Token ID717
Feature activation-4.29e-01

Pos logit contributions
 Nice+0.071
quiet+0.067
zeb+0.066
isexual+0.063
+0.062
Neg logit contributions
 welf-0.104
 weap-0.096
 scrut-0.096
 ingred-0.094
 unden-0.092
Token to
Token ID284
Feature activation+3.34e-01

Pos logit contributions
 Nice+0.226
quiet+0.211
zeb+0.208
isexual+0.197
+0.192
Neg logit contributions
 welf-0.428
 weap-0.400
 scrut-0.400
 ingred-0.395
 unden-0.389
Token hear
Token ID3285
Feature activation-1.09e+00

Pos logit contributions
 welf+0.308
 weap+0.288
 scrut+0.285
 ingred+0.280
 unden+0.275
Neg logit contributions
 Nice-0.198
quiet-0.188
zeb-0.185
isexual-0.176
-0.173
Token about
Token ID546
Feature activation-1.36e-01

Pos logit contributions
 Nice+0.661
quiet+0.625
zeb+0.617
isexual+0.583
+0.573
Neg logit contributions
 welf-1.027
 weap-0.946
 ingred-0.944
 scrut-0.944
 unden-0.940
Token Nation
Token ID8741
Feature activation+6.89e-01

Pos logit contributions
 Nice+0.106
quiet+0.100
zeb+0.099
isexual+0.094
+0.093
Neg logit contributions
 welf-0.105
 scrut-0.096
 ingred-0.095
 weap-0.095
 unden-0.091
Token Travels
Token ID48899
Feature activation+6.41e+00

Pos logit contributions
 welf+0.405
 scrut+0.360
 weap+0.359
 ingred+0.350
 unden+0.335
Neg logit contributions
 Nice-0.645
quiet-0.627
zeb-0.622
isexual-0.604
-0.592
Token destinations
Token ID23982
Feature activation+1.03e+00

Pos logit contributions
 welf+3.944
 weap+3.656
 scrut+3.574
 ingred+3.447
ships+3.441
Neg logit contributions
 Nice-5.577
zeb-5.432
quiet-5.427
isexual-5.240
-5.175
Token,
Token ID11
Feature activation+3.54e-02

Pos logit contributions
 welf+0.882
 weap+0.823
 scrut+0.818
 ingred+0.803
ships+0.783
Neg logit contributions
 Nice-0.675
quiet-0.643
zeb-0.636
isexual-0.613
-0.597
Token and
Token ID290
Feature activation-1.14e-01

Pos logit contributions
 welf+0.033
 weap+0.031
 scrut+0.031
 ingred+0.031
 unden+0.030
Neg logit contributions
 Nice-0.021
quiet-0.020
zeb-0.020
isexual-0.019
-0.019
Token explore
Token ID7301
Feature activation+3.37e-01

Pos logit contributions
 Nice+0.080
quiet+0.077
zeb+0.076
isexual+0.073
+0.072
Neg logit contributions
 welf-0.093
 weap-0.086
 scrut-0.085
 ingred-0.084
 unden-0.081
Token the
Token ID262
Feature activation+1.54e-01

Pos logit contributions
 welf+0.310
 weap+0.290
 scrut+0.289
 ingred+0.286
 unden+0.280
Neg logit contributions
 Nice-0.203
quiet-0.191
zeb-0.189
isexual-0.180
-0.177
Token first
Token ID717
Feature activation+2.81e-02

Pos logit contributions
 welf+0.331
 weap+0.310
 scrut+0.306
 ingred+0.301
ships+0.299
Neg logit contributions
 Nice-0.217
quiet-0.202
zeb-0.197
isexual-0.185
-0.185
Token to
Token ID284
Feature activation+8.76e-01

Pos logit contributions
 welf+0.028
 weap+0.026
 scrut+0.026
 ingred+0.026
 unden+0.025
Neg logit contributions
 Nice-0.015
quiet-0.014
zeb-0.014
isexual-0.013
-0.013
Token hear
Token ID3285
Feature activation-7.33e-01

Pos logit contributions
 welf+0.813
 weap+0.770
 scrut+0.756
 ingred+0.745
ships+0.734
Neg logit contributions
 Nice-0.514
quiet-0.485
zeb-0.475
isexual-0.449
-0.441
Token about
Token ID546
Feature activation+2.82e-01

Pos logit contributions
 Nice+0.429
quiet+0.399
zeb+0.382
isexual+0.363
igue+0.349
Neg logit contributions
 welf-0.694
 weap-0.662
 scrut-0.652
 ingred-0.646
 unden-0.623
Token Nation
Token ID8741
Feature activation+1.48e+00

Pos logit contributions
 welf+0.221
 scrut+0.210
 weap+0.208
 ingred+0.204
ships+0.193
Neg logit contributions
 Nice-0.215
quiet-0.198
zeb-0.193
isexual-0.182
igue-0.179
Token Travels
Token ID48899
Feature activation+6.33e+00

Pos logit contributions
 welf+0.869
 weap+0.786
 scrut+0.778
 ingred+0.774
 unden+0.729
Neg logit contributions
 Nice-1.370
quiet-1.324
zeb-1.311
isexual-1.278
-1.255
Token destinations
Token ID23982
Feature activation+1.10e+00

Pos logit contributions
 welf+3.848
 weap+3.573
 scrut+3.473
ships+3.358
 ingred+3.347
Neg logit contributions
 Nice-5.531
quiet-5.397
zeb-5.397
isexual-5.204
-5.156
Token,
Token ID11
Feature activation+2.16e-01

Pos logit contributions
 welf+0.937
 weap+0.876
 scrut+0.870
 ingred+0.853
ships+0.836
Neg logit contributions
 Nice-0.726
quiet-0.690
zeb-0.683
isexual-0.659
-0.642
Token and
Token ID290
Feature activation+1.86e-01

Pos logit contributions
 welf+0.206
 weap+0.191
 scrut+0.191
 ingred+0.189
 unden+0.188
Neg logit contributions
 Nice-0.126
quiet-0.117
zeb-0.116
isexual-0.107
igue-0.107
Token explore
Token ID7301
Feature activation+5.22e-01

Pos logit contributions
 welf+0.169
 weap+0.152
 ingred+0.152
 scrut+0.152
 unden+0.151
Neg logit contributions
 Nice-0.121
quiet-0.113
zeb-0.111
isexual-0.106
-0.102
Token the
Token ID262
Feature activation+4.43e-01

Pos logit contributions
 welf+0.475
 weap+0.445
 scrut+0.443
 ingred+0.437
 unden+0.425
Neg logit contributions
 Nice-0.319
quiet-0.298
zeb-0.294
isexual-0.281
-0.276
Tokence
Token ID344
Feature activation+1.17e+00

Pos logit contributions
 welf+0.552
 scrut+0.524
 weap+0.524
 ingred+0.502
 unden+0.498
Neg logit contributions
 Nice-0.577
quiet-0.553
zeb-0.548
isexual-0.525
igue-0.519
Token/
Token ID14
Feature activation+1.42e-02

Pos logit contributions
 welf+0.995
 weap+0.928
 scrut+0.921
 ingred+0.902
ships+0.883
Neg logit contributions
 Nice-0.786
quiet-0.746
zeb-0.735
isexual-0.710
-0.693
Tokenedd
Token ID6048
Feature activation+1.01e+00

Pos logit contributions
 welf+0.010
 weap+0.009
 scrut+0.009
 ingred+0.009
 unden+0.009
Neg logit contributions
 Nice-0.011
quiet-0.011
zeb-0.011
isexual-0.010
-0.010
Token75
Token ID2425
Feature activation+3.19e-02

Pos logit contributions
 welf+0.729
 weap+0.671
 scrut+0.668
 ingred+0.650
ships+0.631
Neg logit contributions
 Nice-0.802
quiet-0.773
zeb-0.767
isexual-0.745
-0.728
Token/
Token ID14
Feature activation+1.08e-01

Pos logit contributions
 welf+0.027
 weap+0.025
 scrut+0.025
 ingred+0.025
 unden+0.024
Neg logit contributions
 Nice-0.021
quiet-0.020
zeb-0.020
isexual-0.019
-0.019
TokenAUT
Token ID39371
Feature activation+5.67e+00

Pos logit contributions
 welf+0.093
 scrut+0.088
 weap+0.087
 ingred+0.084
 unden+0.082
Neg logit contributions
 Nice-0.072
quiet-0.070
zeb-0.065
isexual-0.063
-0.063
TokenOC
Token ID4503
Feature activation-1.84e+00

Pos logit contributions
 welf+4.246
 weap+3.935
 scrut+3.897
 ingred+3.801
ships+3.749
Neg logit contributions
 Nice-4.274
quiet-4.093
zeb-4.058
isexual-3.941
-3.846
TokenR
Token ID49
Feature activation-1.72e+00

Pos logit contributions
 Nice+0.884
quiet+0.832
zeb+0.811
isexual+0.763
+0.759
Neg logit contributions
 welf-1.900
 scrut-1.815
 weap-1.809
 ingred-1.766
 unden-1.733
TokenOP
Token ID3185
Feature activation+9.29e-02

Pos logit contributions
 Nice+1.164
quiet+1.103
zeb+1.078
isexual+1.052
igue+1.025
Neg logit contributions
 welf-1.444
 weap-1.341
 ingred-1.330
 scrut-1.325
ships-1.290
Token/
Token ID14
Feature activation+3.18e-01

Pos logit contributions
 welf+0.078
 weap+0.073
 scrut+0.073
 ingred+0.071
 unden+0.069
Neg logit contributions
 Nice-0.062
quiet-0.059
zeb-0.058
isexual-0.057
-0.055
Tokenh
Token ID71
Feature activation+3.74e-01

Pos logit contributions
 welf+0.212
 scrut+0.201
 weap+0.195
 ingred+0.195
 unden+0.188
Neg logit contributions
 Nice-0.273
quiet-0.272
zeb-0.255
-0.253
isexual-0.247
Token acids
Token ID17045
Feature activation-1.42e+00

Pos logit contributions
 welf+0.465
 weap+0.424
 scrut+0.423
 ingred+0.409
ships+0.399
Neg logit contributions
 Nice-0.571
quiet-0.545
zeb-0.544
isexual-0.528
-0.516
Token for
Token ID329
Feature activation-8.28e-02

Pos logit contributions
 Nice+0.908
quiet+0.857
zeb+0.854
isexual+0.817
+0.802
Neg logit contributions
 welf-1.235
 weap-1.148
 scrut-1.145
 ingred-1.116
ships-1.098
Token fuel
Token ID5252
Feature activation-1.90e+00

Pos logit contributions
 Nice+0.058
quiet+0.055
zeb+0.055
isexual+0.053
+0.052
Neg logit contributions
 welf-0.067
 weap-0.062
 scrut-0.062
 ingred-0.060
ships-0.060
Token.
Token ID13
Feature activation-3.65e-01

Pos logit contributions
 Nice+1.377
quiet+1.310
zeb+1.307
isexual+1.254
+1.238
Neg logit contributions
 welf-1.486
 scrut-1.374
 weap-1.372
 ingred-1.331
ships-1.300
Token Inter
Token ID4225
Feature activation-9.29e-01

Pos logit contributions
 Nice+0.251
quiet+0.231
zeb+0.228
isexual+0.219
+0.218
Neg logit contributions
 welf-0.310
 scrut-0.290
 weap-0.289
 ingred-0.286
 unden-0.276
Tokenmitt
Token ID20124
Feature activation+4.96e+00

Pos logit contributions
 Nice+0.960
quiet+0.929
zeb+0.924
isexual+0.905
+0.889
Neg logit contributions
 welf-0.437
 weap-0.386
 scrut-0.381
 ingred-0.366
ships-0.357
Tokenent
Token ID298
Feature activation+2.16e-02

Pos logit contributions
 welf+4.080
 weap+3.881
 scrut+3.854
ships+3.804
 ingred+3.767
Neg logit contributions
 Nice-3.127
zeb-2.935
quiet-2.898
isexual-2.799
-2.751
Token fasting
Token ID24845
Feature activation+2.23e+00

Pos logit contributions
 welf+0.017
 weap+0.016
 scrut+0.016
 ingred+0.015
ships+0.015
Neg logit contributions
 Nice-0.015
quiet-0.015
zeb-0.015
isexual-0.014
-0.014
Token and
Token ID290
Feature activation-2.96e-01

Pos logit contributions
 welf+1.804
 weap+1.681
 scrut+1.667
 ingred+1.631
ships+1.603
Neg logit contributions
 Nice-1.551
quiet-1.481
zeb-1.466
isexual-1.415
-1.385
Token spending
Token ID4581
Feature activation-1.40e-01

Pos logit contributions
 Nice+0.203
quiet+0.192
zeb+0.189
isexual+0.184
+0.179
Neg logit contributions
 welf-0.242
 weap-0.226
 scrut-0.225
 ingred-0.219
ships-0.218
Token more
Token ID517
Feature activation-1.09e-01

Pos logit contributions
 Nice+0.090
quiet+0.085
zeb+0.084
isexual+0.081
+0.079
Neg logit contributions
 welf-0.121
 weap-0.113
 scrut-0.113
 ingred-0.110
ships-0.109
Tokenar
Token ID283
Feature activation-2.67e-01

Pos logit contributions
 welf+0.189
 weap+0.177
 scrut+0.176
 ingred+0.174
 unden+0.171
Neg logit contributions
 Nice-0.106
quiet-0.101
zeb-0.100
isexual-0.095
-0.092
Token (
Token ID357
Feature activation+3.85e-02

Pos logit contributions
 Nice+0.193
quiet+0.183
zeb+0.182
isexual+0.175
+0.173
Neg logit contributions
 welf-0.212
 weap-0.195
 scrut-0.193
 ingred-0.190
ships-0.186
TokenD
Token ID35
Feature activation+2.47e-01

Pos logit contributions
 welf+0.036
 weap+0.034
 scrut+0.034
 ingred+0.033
ships+0.032
Neg logit contributions
 Nice-0.022
quiet-0.021
zeb-0.020
isexual-0.020
-0.019
Tokenish
Token ID680
Feature activation+2.86e-01

Pos logit contributions
 welf+0.248
 weap+0.234
 scrut+0.233
 ingred+0.229
ships+0.226
Neg logit contributions
 Nice-0.124
zeb-0.116
quiet-0.116
isexual-0.110
-0.105
Token)
Token ID8
Feature activation-9.09e-01

Pos logit contributions
 welf+0.236
 weap+0.220
 scrut+0.218
 ingred+0.214
ships+0.210
Neg logit contributions
 Nice-0.194
quiet-0.185
zeb-0.183
isexual-0.177
-0.173
Token owes
Token ID29264
Feature activation+4.87e+00

Pos logit contributions
 Nice+0.652
quiet+0.616
zeb+0.615
isexual+0.590
+0.580
Neg logit contributions
 welf-0.724
 weap-0.667
 scrut-0.661
 ingred-0.652
ships-0.636
Token V
Token ID569
Feature activation-4.40e-01

Pos logit contributions
 welf+3.899
 weap+3.639
 scrut+3.608
 ingred+3.537
ships+3.478
Neg logit contributions
 Nice-3.376
quiet-3.249
zeb-3.210
isexual-3.113
-3.024
Tokenoom
Token ID4207
Feature activation-2.41e-01

Pos logit contributions
 Nice+0.308
quiet+0.295
zeb+0.294
isexual+0.283
+0.275
Neg logit contributions
 welf-0.366
 scrut-0.340
 weap-0.335
 ingred-0.332
 unden-0.326
Token (
Token ID357
Feature activation+2.38e-02

Pos logit contributions
 Nice+0.168
quiet+0.157
zeb+0.157
isexual+0.152
+0.150
Neg logit contributions
 welf-0.196
 weap-0.182
 scrut-0.181
 ingred-0.176
ships-0.173
TokenAM
Token ID2390
Feature activation+4.91e-01

Pos logit contributions
 welf+0.022
 weap+0.020
 scrut+0.020
 ingred+0.020
 unden+0.019
Neg logit contributions
 Nice-0.014
quiet-0.014
zeb-0.013
isexual-0.013
-0.013
TokenC
Token ID34
Feature activation+5.85e-01

Pos logit contributions
 welf+0.320
 weap+0.294
 scrut+0.290
 ingred+0.283
ships+0.277
Neg logit contributions
 Nice-0.419
quiet-0.403
zeb-0.400
isexual-0.389
-0.382
Token presidential
Token ID4787
Feature activation-9.53e-01

Pos logit contributions
 welf+1.456
 weap+1.367
 scrut+1.356
 ingred+1.333
ships+1.315
Neg logit contributions
 Nice-0.996
quiet-0.940
zeb-0.928
isexual-0.896
-0.867
Token nominee
Token ID10429
Feature activation-5.24e-01

Pos logit contributions
 Nice+0.539
quiet+0.500
zeb+0.490
isexual+0.472
+0.455
Neg logit contributions
 welf-0.895
 weap-0.843
 scrut-0.824
 ingred-0.823
ships-0.819
Token Hillary
Token ID5073
Feature activation+1.07e+00

Pos logit contributions
 Nice+0.244
quiet+0.222
zeb+0.215
isexual+0.202
+0.195
Neg logit contributions
 welf-0.551
 weap-0.523
 scrut-0.516
 ingred-0.511
ships-0.507
Token Clinton
Token ID2605
Feature activation+1.25e+00

Pos logit contributions
 welf+1.023
 weap+0.960
 scrut+0.953
 ingred+0.941
 unden+0.923
Neg logit contributions
 Nice-0.603
quiet-0.557
zeb-0.551
isexual-0.525
igue-0.510
Token Hillary
Token ID5073
Feature activation+1.34e+00

Pos logit contributions
 welf+0.987
 weap+0.919
 scrut+0.909
 ingred+0.891
ships+0.876
Neg logit contributions
 Nice-0.888
quiet-0.848
zeb-0.840
isexual-0.812
-0.793
Token Diane
Token ID26542
Feature activation+4.68e+00

Pos logit contributions
 welf+1.024
 weap+0.936
 scrut+0.931
 ingred+0.917
 unden+0.909
Neg logit contributions
 Nice-1.039
quiet-0.973
zeb-0.951
isexual-0.927
igue-0.920
Token Rodham
Token ID41848
Feature activation+1.39e+00

Pos logit contributions
 welf+2.653
 scrut+2.385
 weap+2.384
 ingred+2.279
ships+2.244
Neg logit contributions
 Nice-4.279
quiet-4.157
zeb-4.137
isexual-4.059
-3.987
Token Clinton
Token ID2605
Feature activation+1.17e+00

Pos logit contributions
 welf+1.301
 weap+1.227
 scrut+1.218
 ingred+1.194
ships+1.173
Neg logit contributions
 Nice-0.798
quiet-0.750
zeb-0.735
isexual-0.703
-0.686
TokenSanders
Token ID26747
Feature activation+8.23e-01

Pos logit contributions
 welf+0.815
 weap+0.750
 scrut+0.742
 ingred+0.721
ships+0.703
Neg logit contributions
 Nice-0.959
quiet-0.925
zeb-0.911
isexual-0.887
-0.870
Token:
Token ID25
Feature activation+1.28e+00

Pos logit contributions
 welf+0.525
 weap+0.474
 scrut+0.462
 ingred+0.448
 unden+0.447
Neg logit contributions
 Nice-0.739
quiet-0.698
zeb-0.687
isexual-0.668
igue-0.658
Token '
Token ID705
Feature activation-7.31e-01

Pos logit contributions
 welf+0.959
 weap+0.887
 scrut+0.879
 ingred+0.860
ships+0.852
Neg logit contributions
 Nice-0.946
quiet-0.918
zeb-0.910
isexual-0.877
-0.865
Token mix
Token ID5022
Feature activation-5.88e-01

Pos logit contributions
 welf+0.216
 weap+0.201
 scrut+0.199
 ingred+0.196
ships+0.192
Neg logit contributions
 Nice-0.197
quiet-0.188
zeb-0.186
isexual-0.180
-0.176
Token of
Token ID286
Feature activation+1.39e-01

Pos logit contributions
 Nice+0.427
quiet+0.407
zeb+0.403
isexual+0.391
+0.383
Neg logit contributions
 welf-0.460
 weap-0.428
 scrut-0.423
 ingred-0.414
ships-0.405
Token low
Token ID1877
Feature activation+6.11e-01

Pos logit contributions
 welf+0.118
 weap+0.111
 scrut+0.110
 ingred+0.107
ships+0.106
Neg logit contributions
 Nice-0.091
quiet-0.085
zeb-0.084
isexual-0.082
-0.079
Token-
Token ID12
Feature activation+4.66e-01

Pos logit contributions
 welf+0.472
 weap+0.438
 scrut+0.434
 ingred+0.424
ships+0.417
Neg logit contributions
 Nice-0.449
quiet-0.429
zeb-0.424
isexual-0.412
-0.403
Tokens
Token ID82
Feature activation-9.69e-02

Pos logit contributions
 welf+0.348
 weap+0.323
 scrut+0.320
 ingred+0.312
ships+0.308
Neg logit contributions
 Nice-0.352
quiet-0.337
zeb-0.334
isexual-0.324
-0.316
Tokenulf
Token ID4754
Feature activation+4.64e+00

Pos logit contributions
 Nice+0.103
quiet+0.100
zeb+0.099
isexual+0.097
+0.096
Neg logit contributions
 welf-0.043
 weap-0.038
 scrut-0.037
 ingred-0.035
ships-0.034
Tokenur
Token ID333
Feature activation-6.99e-01

Pos logit contributions
 welf+4.010
 weap+3.799
 scrut+3.796
ships+3.762
 ingred+3.716
Neg logit contributions
 Nice-2.703
quiet-2.549
zeb-2.496
isexual-2.399
-2.353
Token fuel
Token ID5252
Feature activation-1.24e+00

Pos logit contributions
 Nice+0.478
quiet+0.450
zeb+0.445
isexual+0.434
+0.420
Neg logit contributions
 welf-0.578
 weap-0.539
 scrut-0.536
 ingred-0.522
ships-0.512
Token oil
Token ID3056
Feature activation-2.49e-02

Pos logit contributions
 Nice+0.840
quiet+0.789
zeb+0.787
isexual+0.760
+0.740
Neg logit contributions
 welf-1.031
 weap-0.961
 scrut-0.957
 ingred-0.935
ships-0.914
Token and
Token ID290
Feature activation+1.22e-01

Pos logit contributions
 Nice+0.018
quiet+0.017
zeb+0.017
isexual+0.016
+0.016
Neg logit contributions
 welf-0.020
 weap-0.018
 scrut-0.018
 ingred-0.018
ships-0.017
Token diesel
Token ID21866
Feature activation-1.18e+00

Pos logit contributions
 welf+0.102
 weap+0.095
 scrut+0.094
 ingred+0.092
ships+0.091
Neg logit contributions
 Nice-0.082
quiet-0.077
zeb-0.076
isexual-0.074
-0.072
Token MORE
Token ID12011
Feature activation-1.33e+00

Pos logit contributions
 welf+0.268
 weap+0.250
 scrut+0.249
 ingred+0.242
ships+0.241
Neg logit contributions
 Nice-0.234
zeb-0.224
quiet-0.224
isexual-0.217
-0.211
Token and
Token ID290
Feature activation-7.58e-01

Pos logit contributions
 Nice+0.860
quiet+0.818
zeb+0.806
isexual+0.780
+0.758
Neg logit contributions
 welf-1.141
 weap-1.068
 scrut-1.058
 ingred-1.037
ships-1.023
Token Hillary
Token ID5073
Feature activation+3.53e-01

Pos logit contributions
 Nice+0.419
quiet+0.388
zeb+0.378
isexual+0.361
+0.353
Neg logit contributions
 welf-0.731
 weap-0.685
 scrut-0.676
 ingred-0.671
ships-0.664
Token Clinton
Token ID2605
Feature activation+7.62e-01

Pos logit contributions
 welf+0.344
 weap+0.322
 scrut+0.320
 ingred+0.317
 unden+0.311
Neg logit contributions
 Nice-0.198
quiet-0.183
zeb-0.180
isexual-0.171
-0.167
Token Hillary
Token ID5073
Feature activation+7.92e-01

Pos logit contributions
 welf+0.792
 weap+0.750
 scrut+0.743
 ingred+0.734
ships+0.723
Neg logit contributions
 Nice-0.360
quiet-0.336
zeb-0.330
isexual-0.309
-0.300
Token Diane
Token ID26542
Feature activation+4.61e+00

Pos logit contributions
 welf+0.595
 weap+0.543
 scrut+0.539
 ingred+0.532
 unden+0.524
Neg logit contributions
 Nice-0.624
quiet-0.584
zeb-0.575
isexual-0.556
igue-0.553
Token Rodham
Token ID41848
Feature activation+1.47e+00

Pos logit contributions
 welf+2.408
 scrut+2.179
 weap+2.159
 ingred+2.042
ships+2.031
Neg logit contributions
 Nice-4.327
quiet-4.244
zeb-4.232
isexual-4.186
-4.109
Token Clinton
Token ID2605
Feature activation+1.17e+00

Pos logit contributions
 welf+1.385
 weap+1.307
 scrut+1.297
 ingred+1.273
ships+1.250
Neg logit contributions
 Nice-0.847
quiet-0.796
zeb-0.777
isexual-0.745
-0.728
TokenSanders
Token ID26747
Feature activation+6.99e-01

Pos logit contributions
 welf+0.803
 weap+0.739
 scrut+0.729
 ingred+0.707
ships+0.690
Neg logit contributions
 Nice-0.970
quiet-0.939
zeb-0.923
isexual-0.898
-0.882
Token:
Token ID25
Feature activation+1.46e+00

Pos logit contributions
 welf+0.443
 weap+0.401
 scrut+0.389
 ingred+0.379
 unden+0.379
Neg logit contributions
 Nice-0.630
quiet-0.595
zeb-0.586
isexual-0.570
igue-0.562
Token '
Token ID705
Feature activation-7.37e-02

Pos logit contributions
 welf+1.073
 weap+0.989
 scrut+0.982
 ingred+0.953
ships+0.952
Neg logit contributions
 Nice-1.094
quiet-1.070
zeb-1.062
isexual-1.018
-1.010
Token mandate
Token ID14598
Feature activation-9.83e-01

Pos logit contributions
 welf+0.439
 weap+0.409
 scrut+0.407
 ingred+0.399
ships+0.395
Neg logit contributions
 Nice-0.364
quiet-0.344
zeb-0.343
isexual-0.327
-0.322
Token.
Token ID13
Feature activation-7.95e-02

Pos logit contributions
 Nice+0.694
quiet+0.659
zeb+0.656
isexual+0.631
+0.617
Neg logit contributions
 welf-0.785
 weap-0.731
 scrut-0.727
 ingred-0.712
ships-0.697
Token The
Token ID383
Feature activation+4.83e-02

Pos logit contributions
 Nice+0.055
quiet+0.052
zeb+0.052
isexual+0.050
+0.049
Neg logit contributions
 welf-0.065
 weap-0.060
 scrut-0.060
 ingred-0.059
ships-0.058
Token Bush
Token ID5511
Feature activation-5.25e-01

Pos logit contributions
 welf+0.038
 weap+0.036
 scrut+0.035
 ingred+0.034
ships+0.034
Neg logit contributions
 Nice-0.035
quiet-0.033
zeb-0.032
isexual-0.031
-0.031
Token Administration
Token ID8694
Feature activation+1.33e+00

Pos logit contributions
 Nice+0.366
quiet+0.347
zeb+0.343
isexual+0.329
+0.322
Neg logit contributions
 welf-0.424
 weap-0.398
 scrut-0.395
 ingred-0.386
ships-0.382
Token susp
Token ID4012
Feature activation+4.60e+00

Pos logit contributions
 welf+1.018
 weap+0.947
 scrut+0.936
 ingred+0.917
ships+0.898
Neg logit contributions
 Nice-0.990
quiet-0.948
zeb-0.937
isexual-0.906
-0.884
Tokenends
Token ID2412
Feature activation+7.19e-01

Pos logit contributions
 welf+2.137
 weap+1.884
 scrut+1.873
ships+1.799
 ingred+1.768
Neg logit contributions
 Nice-4.696
quiet-4.528
zeb-4.514
isexual-4.415
-4.331
Token the
Token ID262
Feature activation+3.02e-01

Pos logit contributions
 welf+0.603
 weap+0.565
 scrut+0.560
 ingred+0.550
ships+0.543
Neg logit contributions
 Nice-0.479
quiet-0.453
zeb-0.447
isexual-0.433
-0.421
Token OR
Token ID6375
Feature activation+5.96e-01

Pos logit contributions
 welf+0.240
 weap+0.224
 scrut+0.223
 ingred+0.218
ships+0.215
Neg logit contributions
 Nice-0.215
quiet-0.203
zeb-0.200
isexual-0.194
-0.189
TokenI
Token ID40
Feature activation-2.65e-01

Pos logit contributions
 welf+0.438
 weap+0.404
 scrut+0.401
 ingred+0.393
 unden+0.380
Neg logit contributions
 Nice-0.465
quiet-0.445
zeb-0.440
isexual-0.429
-0.419
Token proposal
Token ID6961
Feature activation-6.97e-01

Pos logit contributions
 Nice+0.196
quiet+0.186
zeb+0.184
isexual+0.178
+0.174
Neg logit contributions
 welf-0.204
 weap-0.190
 scrut-0.188
 ingred-0.184
ships-0.181
Token Los
Token ID5401
Feature activation-1.49e+00

Pos logit contributions
 Nice+0.404
quiet+0.377
zeb+0.371
isexual+0.357
+0.346
Neg logit contributions
 welf-0.576
 weap-0.542
 scrut-0.538
 ingred-0.528
ships-0.524
Token Angeles
Token ID5652
Feature activation+3.75e-01

Pos logit contributions
 Nice+0.813
quiet+0.759
zeb+0.754
isexual+0.716
+0.690
Neg logit contributions
 welf-1.436
 weap-1.354
 scrut-1.344
 ingred-1.324
ships-1.299
Token Times
Token ID3782
Feature activation+2.86e-02

Pos logit contributions
 welf+0.367
 weap+0.346
 scrut+0.343
 ingred+0.337
ships+0.332
Neg logit contributions
 Nice-0.197
quiet-0.186
zeb-0.183
isexual-0.176
-0.170
Token blogger
Token ID23530
Feature activation+1.79e+00

Pos logit contributions
 welf+0.022
 weap+0.021
 scrut+0.021
 ingred+0.020
ships+0.020
Neg logit contributions
 Nice-0.021
quiet-0.020
zeb-0.020
isexual-0.019
-0.018
Token Andrew
Token ID6858
Feature activation+1.46e+00

Pos logit contributions
 welf+1.651
 weap+1.553
 scrut+1.543
 ingred+1.512
ships+1.494
Neg logit contributions
 Nice-1.025
quiet-0.975
zeb-0.964
isexual-0.928
-0.898
Token Malcolm
Token ID20002
Feature activation+4.46e+00

Pos logit contributions
 welf+1.270
 weap+1.192
 scrut+1.183
 ingred+1.154
ships+1.142
Neg logit contributions
 Nice-0.917
quiet-0.882
zeb-0.867
isexual-0.842
-0.814
Token,
Token ID11
Feature activation+2.89e-01

Pos logit contributions
 welf+3.595
 weap+3.344
 scrut+3.339
 ingred+3.244
ships+3.203
Neg logit contributions
 Nice-2.968
quiet-2.878
zeb-2.817
isexual-2.782
-2.667
Token you
Token ID345
Feature activation-5.13e-01

Pos logit contributions
 welf+0.235
 weap+0.219
 scrut+0.217
 ingred+0.213
ships+0.210
Neg logit contributions
 Nice-0.202
quiet-0.192
zeb-0.188
isexual-0.182
-0.178
Token flip
Token ID14283
Feature activation+1.81e+00

Pos logit contributions
 Nice+0.344
quiet+0.330
zeb+0.323
isexual+0.311
+0.305
Neg logit contributions
 welf-0.431
 weap-0.402
 scrut-0.397
 ingred-0.395
ships-0.383
Token the
Token ID262
Feature activation+1.85e-01

Pos logit contributions
 welf+1.507
 weap+1.408
 scrut+1.397
 ingred+1.367
ships+1.347
Neg logit contributions
 Nice-1.213
quiet-1.157
zeb-1.145
isexual-1.107
-1.077
Token script
Token ID4226
Feature activation-5.90e-01

Pos logit contributions
 welf+0.159
 weap+0.149
 scrut+0.147
 ingred+0.144
ships+0.143
Neg logit contributions
 Nice-0.119
quiet-0.113
zeb-0.112
isexual-0.108
-0.105
Token)
Token ID8
Feature activation-6.59e-01

Pos logit contributions
 Nice+0.130
quiet+0.124
zeb+0.121
isexual+0.117
+0.115
Neg logit contributions
 welf-0.159
 weap-0.149
 scrut-0.147
 ingred-0.145
ships-0.141
Token is
Token ID318
Feature activation+4.02e-01

Pos logit contributions
 Nice+0.460
quiet+0.439
zeb+0.433
isexual+0.417
+0.409
Neg logit contributions
 welf-0.532
 weap-0.497
 scrut-0.492
 ingred-0.484
 unden-0.469
Token difficult
Token ID2408
Feature activation+2.49e-01

Pos logit contributions
 welf+0.335
 weap+0.313
 scrut+0.310
 ingred+0.305
ships+0.298
Neg logit contributions
 Nice-0.272
quiet-0.258
zeb-0.254
isexual-0.245
-0.239
Token,"
Token ID553
Feature activation+1.00e+00

Pos logit contributions
 welf+0.219
 weap+0.205
 scrut+0.204
 ingred+0.200
ships+0.196
Neg logit contributions
 Nice-0.156
quiet-0.148
zeb-0.146
isexual-0.141
-0.137
Token Lam
Token ID10923
Feature activation+7.21e-01

Pos logit contributions
 welf+0.841
 weap+0.784
 scrut+0.779
 ingred+0.762
ships+0.750
Neg logit contributions
 Nice-0.674
quiet-0.642
zeb-0.632
isexual-0.611
-0.595
Tokenorie
Token ID19257
Feature activation+4.44e+00

Pos logit contributions
 welf+0.675
 weap+0.634
 scrut+0.630
 ingred+0.618
ships+0.606
Neg logit contributions
 Nice-0.415
quiet-0.393
zeb-0.387
isexual-0.371
-0.361
Tokenllo
Token ID18798
Feature activation+1.03e-01

Pos logit contributions
 welf+1.038
 weap+0.801
 scrut+0.769
 ingred+0.694
ships+0.677
Neg logit contributions
 Nice-5.586
quiet-5.437
zeb-5.419
isexual-5.341
-5.243
Token said
Token ID531
Feature activation-6.51e-01

Pos logit contributions
 welf+0.077
 weap+0.072
 scrut+0.071
 ingred+0.070
ships+0.069
Neg logit contributions
 Nice-0.077
quiet-0.074
zeb-0.073
isexual-0.071
-0.069
Token.
Token ID13
Feature activation+6.15e-01

Pos logit contributions
 Nice+0.491
quiet+0.471
zeb+0.466
isexual+0.453
+0.442
Neg logit contributions
 welf-0.488
 weap-0.452
 scrut-0.448
 ingred-0.438
ships-0.430
Token "
Token ID366
Feature activation+6.93e-02

Pos logit contributions
 welf+0.487
 weap+0.453
 scrut+0.449
 ingred+0.439
ships+0.432
Neg logit contributions
 Nice-0.439
quiet-0.419
zeb-0.415
isexual-0.403
-0.392
TokenBut
Token ID1537
Feature activation+4.35e-01

Pos logit contributions
 welf+0.055
 weap+0.051
 scrut+0.051
 ingred+0.050
 unden+0.048
Neg logit contributions
 Nice-0.051
quiet-0.049
zeb-0.048
isexual-0.046
-0.046
Token would
Token ID561
Feature activation+1.02e-02

Pos logit contributions
 welf+0.154
 weap+0.143
 scrut+0.142
 ingred+0.140
ships+0.137
Neg logit contributions
 Nice-0.122
quiet-0.116
zeb-0.114
isexual-0.110
-0.107
Token go
Token ID467
Feature activation+1.34e-01

Pos logit contributions
 welf+0.008
 weap+0.007
 scrut+0.007
 ingred+0.007
ships+0.007
Neg logit contributions
 Nice-0.007
quiet-0.007
zeb-0.007
isexual-0.007
-0.007
Token to
Token ID284
Feature activation+2.51e-01

Pos logit contributions
 welf+0.122
 weap+0.115
 scrut+0.114
 ingred+0.112
ships+0.109
Neg logit contributions
 Nice-0.081
quiet-0.077
zeb-0.075
isexual-0.072
-0.070
Token cover
Token ID3002
Feature activation+7.37e-01

Pos logit contributions
 welf+0.208
 weap+0.194
 scrut+0.192
 ingred+0.189
ships+0.185
Neg logit contributions
 Nice-0.172
quiet-0.163
zeb-0.160
isexual-0.154
-0.151
Token debts
Token ID20250
Feature activation+2.18e+00

Pos logit contributions
 welf+0.597
 weap+0.555
 scrut+0.549
 ingred+0.541
ships+0.531
Neg logit contributions
 Nice-0.514
quiet-0.488
zeb-0.482
isexual-0.464
-0.456
Token owed
Token ID21057
Feature activation+4.42e+00

Pos logit contributions
 welf+1.749
 weap+1.631
 scrut+1.620
 ingred+1.578
ships+1.559
Neg logit contributions
 Nice-1.524
quiet-1.461
zeb-1.449
isexual-1.409
-1.364
Token the
Token ID262
Feature activation+7.54e-01

Pos logit contributions
 welf+3.763
 weap+3.540
 scrut+3.515
ships+3.438
 ingred+3.406
Neg logit contributions
 Nice-2.779
quiet-2.673
zeb-2.659
isexual-2.596
-2.485
Token City
Token ID2254
Feature activation-1.21e-01

Pos logit contributions
 welf+0.660
 weap+0.618
 scrut+0.614
 ingred+0.603
ships+0.592
Neg logit contributions
 Nice-0.476
quiet-0.450
zeb-0.445
isexual-0.428
-0.416
Token of
Token ID286
Feature activation+7.55e-01

Pos logit contributions
 Nice+0.083
quiet+0.079
zeb+0.079
isexual+0.075
+0.074
Neg logit contributions
 welf-0.100
 weap-0.093
 scrut-0.092
 ingred-0.091
 unden-0.088
Token Toronto
Token ID6586
Feature activation+7.14e-01

Pos logit contributions
 welf+0.678
 weap+0.636
 scrut+0.631
 ingred+0.620
ships+0.610
Neg logit contributions
 Nice-0.459
quiet-0.434
zeb-0.429
isexual-0.413
-0.401
Token and
Token ID290
Feature activation+3.91e-01

Pos logit contributions
 welf+0.609
 weap+0.567
 scrut+0.563
 ingred+0.557
ships+0.540
Neg logit contributions
 Nice-0.470
quiet-0.446
zeb-0.440
isexual-0.422
-0.414
Token this
Token ID428
Feature activation-2.26e-02

Pos logit contributions
 Nice+0.045
quiet+0.042
zeb+0.042
isexual+0.040
+0.039
Neg logit contributions
 welf-0.056
 weap-0.052
 scrut-0.052
 ingred-0.050
ships-0.050
Token.
Token ID13
Feature activation+2.75e-01

Pos logit contributions
 Nice+0.015
quiet+0.014
zeb+0.014
isexual+0.013
+0.013
Neg logit contributions
 welf-0.019
 scrut-0.018
 weap-0.018
 ingred-0.017
ships-0.017
Token
Token ID198
Feature activation+2.14e-01

Pos logit contributions
 welf+0.228
 weap+0.213
 scrut+0.212
 ingred+0.207
ships+0.202
Neg logit contributions
 Nice-0.191
quiet-0.178
zeb-0.177
isexual-0.171
-0.167
Token
Token ID198
Feature activation+2.83e-01

Pos logit contributions
 welf+0.188
 weap+0.174
 scrut+0.173
 ingred+0.173
 unden+0.170
Neg logit contributions
 Nice-0.142
quiet-0.135
zeb-0.133
isexual-0.127
-0.125
TokenP
Token ID47
Feature activation+1.91e+00

Pos logit contributions
 welf+0.223
 weap+0.207
 scrut+0.205
 ingred+0.200
 unden+0.195
Neg logit contributions
 Nice-0.208
quiet-0.200
zeb-0.197
isexual-0.191
-0.188
Tokenump
Token ID931
Feature activation+4.41e+00

Pos logit contributions
 welf+1.536
 weap+1.431
 scrut+1.419
 ingred+1.388
ships+1.365
Neg logit contributions
 Nice-1.333
quiet-1.273
zeb-1.261
isexual-1.221
-1.189
Tokenkin
Token ID5116
Feature activation+1.90e-01

Pos logit contributions
 welf+3.717
 weap+3.476
 scrut+3.466
 ingred+3.404
ships+3.347
Neg logit contributions
 Nice-2.856
quiet-2.730
zeb-2.701
isexual-2.598
-2.527
Token Seed
Token ID23262
Feature activation-3.17e-02

Pos logit contributions
 welf+0.159
 weap+0.148
 scrut+0.147
 ingred+0.144
ships+0.141
Neg logit contributions
 Nice-0.129
quiet-0.122
zeb-0.121
isexual-0.117
-0.114
Token Fl
Token ID1610
Feature activation+1.39e+00

Pos logit contributions
 Nice+0.022
quiet+0.021
zeb+0.021
isexual+0.020
+0.020
Neg logit contributions
 welf-0.026
 weap-0.024
 scrut-0.024
 ingred-0.023
ships-0.023
Tokenour
Token ID454
Feature activation+2.12e-01

Pos logit contributions
 welf+1.422
 weap+1.343
 scrut+1.335
 ingred+1.316
 unden+1.286
Neg logit contributions
 Nice-0.682
quiet-0.644
zeb-0.631
isexual-0.601
-0.583
Token
Token ID960
Feature activation+5.91e-01

Pos logit contributions
 welf+0.122
 weap+0.110
 scrut+0.109
 ingred+0.106
ships+0.103
Neg logit contributions
 Nice-0.197
quiet-0.191
zeb-0.189
isexual-0.185
-0.181
Token Clinton
Token ID2605
Feature activation+8.41e-01

Pos logit contributions
 Nice+0.527
quiet+0.494
zeb+0.492
isexual+0.469
+0.463
Neg logit contributions
 welf-0.754
 weap-0.710
 scrut-0.706
 ingred-0.693
ships-0.677
Token ended
Token ID4444
Feature activation+1.13e+00

Pos logit contributions
 welf+0.667
 weap+0.621
 scrut+0.614
 ingred+0.602
ships+0.591
Neg logit contributions
 Nice-0.600
quiet-0.574
zeb-0.569
isexual-0.548
-0.539
Token
Token ID564
Feature activation-1.73e-01

Pos logit contributions
 welf+0.956
 weap+0.898
 scrut+0.891
 ingred+0.876
ships+0.862
Neg logit contributions
 Nice-0.739
quiet-0.699
zeb-0.692
isexual-0.667
-0.651
Token
Token ID250
Feature activation-1.08e-01

Pos logit contributions
 Nice+0.115
quiet+0.110
zeb+0.109
isexual+0.105
+0.102
Neg logit contributions
 welf-0.144
 weap-0.135
 scrut-0.134
 ingred-0.131
ships-0.129
Tokenw
Token ID86
Feature activation+1.31e+00

Pos logit contributions
 Nice+0.078
quiet+0.075
zeb+0.074
isexual+0.071
+0.070
Neg logit contributions
 welf-0.085
 weap-0.079
 scrut-0.079
 ingred-0.077
ships-0.075
Tokenelfare
Token ID27122
Feature activation+4.40e+00

Pos logit contributions
 welf+0.993
 weap+0.922
 scrut+0.916
 ingred+0.895
ships+0.878
Neg logit contributions
 Nice-0.975
quiet-0.933
zeb-0.925
isexual-0.898
-0.878
Token as
Token ID355
Feature activation-6.40e-02

Pos logit contributions
 welf+3.750
 weap+3.498
 scrut+3.460
 ingred+3.393
ships+3.347
Neg logit contributions
 Nice-2.857
quiet-2.722
zeb-2.686
isexual-2.618
-2.532
Token we
Token ID356
Feature activation-1.34e+00

Pos logit contributions
 Nice+0.043
quiet+0.041
zeb+0.041
isexual+0.039
+0.039
Neg logit contributions
 welf-0.052
 scrut-0.049
 weap-0.049
 ingred-0.048
ships-0.048
Token know
Token ID760
Feature activation+5.20e-01

Pos logit contributions
 Nice+1.136
quiet+1.106
zeb+1.100
+1.052
isexual+1.050
Neg logit contributions
 welf-0.863
 weap-0.797
 scrut-0.786
 ingred-0.781
ships-0.759
Token it
Token ID340
Feature activation+1.96e-02

Pos logit contributions
 welf+0.421
 weap+0.393
 scrut+0.391
 ingred+0.382
ships+0.376
Neg logit contributions
 Nice-0.361
quiet-0.344
zeb-0.341
isexual-0.329
-0.322
Token,
Token ID11
Feature activation-1.93e-02

Pos logit contributions
 welf+0.014
 weap+0.013
 scrut+0.013
 ingred+0.013
ships+0.013
Neg logit contributions
 Nice-0.015
quiet-0.014
zeb-0.014
isexual-0.014
-0.014
Token an
Token ID281
Feature activation-4.88e-01

Pos logit contributions
 welf+0.649
 weap+0.607
 scrut+0.592
 ingred+0.587
 unden+0.573
Neg logit contributions
 Nice-0.591
zeb-0.557
quiet-0.552
isexual-0.529
-0.519
Token alternative
Token ID5559
Feature activation-1.02e+00

Pos logit contributions
 Nice+0.379
zeb+0.360
quiet+0.359
isexual+0.347
+0.340
Neg logit contributions
 welf-0.359
 weap-0.334
 scrut-0.325
 ingred-0.318
ships-0.315
Token to
Token ID284
Feature activation-1.76e-01

Pos logit contributions
 Nice+0.499
zeb+0.464
quiet+0.460
isexual+0.427
+0.416
Neg logit contributions
 welf-1.050
 weap-0.987
 ingred-0.984
 scrut-0.968
ships-0.960
Token The
Token ID383
Feature activation-8.89e-01

Pos logit contributions
 Nice+0.104
zeb+0.095
quiet+0.091
 Knox+0.086
igue+0.086
Neg logit contributions
 welf-0.165
 weap-0.156
 scrut-0.156
 ingred-0.155
 unden-0.154
Token Ad
Token ID1215
Feature activation+5.66e-01

Pos logit contributions
 Nice+0.542
zeb+0.507
quiet+0.502
isexual+0.481
+0.466
Neg logit contributions
 welf-0.807
 weap-0.755
 scrut-0.747
 ingred-0.740
ships-0.721
Tokenvertis
Token ID3346
Feature activation+4.40e+00

Pos logit contributions
 welf+0.305
 weap+0.273
 scrut+0.269
 ingred+0.261
ships+0.254
Neg logit contributions
 Nice-0.548
quiet-0.531
zeb-0.527
isexual-0.514
-0.505
Tokener
Token ID263
Feature activation+6.48e-02

Pos logit contributions
 welf+4.011
 weap+3.803
 scrut+3.767
ships+3.689
 ingred+3.674
Neg logit contributions
 Nice-2.508
quiet-2.369
zeb-2.341
isexual-2.289
-2.198
Token,
Token ID11
Feature activation-6.20e-02

Pos logit contributions
 welf+0.060
 weap+0.056
 ingred+0.056
 scrut+0.056
 unden+0.053
Neg logit contributions
 Nice-0.039
zeb-0.037
quiet-0.037
isexual-0.035
-0.034
Token a
Token ID257
Feature activation+3.27e-01

Pos logit contributions
 Nice+0.041
zeb+0.036
quiet+0.035
igue+0.034
+0.034
Neg logit contributions
 welf-0.056
 ingred-0.052
 weap-0.052
 scrut-0.051
 unden-0.051
Token different
Token ID1180
Feature activation+4.75e-01

Pos logit contributions
 welf+0.278
 weap+0.261
 ingred+0.256
 scrut+0.256
ships+0.253
Neg logit contributions
 Nice-0.223
quiet-0.208
zeb-0.207
isexual-0.194
-0.192
Token voice
Token ID3809
Feature activation+2.27e+00

Pos logit contributions
 welf+0.364
 weap+0.333
 ingred+0.333
 scrut+0.328
ships+0.323
Neg logit contributions
 Nice-0.360
zeb-0.340
quiet-0.336
-0.319
isexual-0.318
Token MORE
Token ID12011
Feature activation-1.23e+00

Pos logit contributions
 Nice+0.552
quiet+0.524
zeb+0.519
isexual+0.501
+0.487
Neg logit contributions
 welf-0.685
 weap-0.641
 scrut-0.635
 ingred-0.622
ships-0.612
Token and
Token ID290
Feature activation-8.64e-01

Pos logit contributions
 Nice+0.819
quiet+0.781
zeb+0.772
isexual+0.746
+0.726
Neg logit contributions
 welf-1.031
 weap-0.963
 scrut-0.955
 ingred-0.935
ships-0.920
Token Hillary
Token ID5073
Feature activation+8.36e-02

Pos logit contributions
 Nice+0.560
quiet+0.525
zeb+0.522
isexual+0.501
+0.486
Neg logit contributions
 welf-0.747
 weap-0.699
 scrut-0.694
 ingred-0.678
ships-0.673
Token Clinton
Token ID2605
Feature activation+1.43e-01

Pos logit contributions
 welf+0.077
 weap+0.072
 scrut+0.072
 ingred+0.070
ships+0.069
Neg logit contributions
 Nice-0.049
quiet-0.046
zeb-0.046
isexual-0.044
-0.043
Token Hillary
Token ID5073
Feature activation+5.88e-01

Pos logit contributions
 welf+0.146
 weap+0.138
 scrut+0.137
 ingred+0.135
ships+0.133
Neg logit contributions
 Nice-0.070
quiet-0.066
zeb-0.065
isexual-0.062
-0.059
Token Diane
Token ID26542
Feature activation+4.36e+00

Pos logit contributions
 welf+0.445
 weap+0.407
 scrut+0.405
 ingred+0.398
 unden+0.395
Neg logit contributions
 Nice-0.460
quiet-0.429
zeb-0.423
isexual-0.410
igue-0.406
Token Rodham
Token ID41848
Feature activation+1.10e+00

Pos logit contributions
 welf+2.361
 scrut+2.115
 weap+2.113
ships+1.999
 ingred+1.995
Neg logit contributions
 Nice-4.058
quiet-3.962
zeb-3.935
isexual-3.890
-3.820
Token Clinton
Token ID2605
Feature activation+6.18e-01

Pos logit contributions
 welf+1.041
 weap+0.983
 scrut+0.975
 ingred+0.958
ships+0.939
Neg logit contributions
 Nice-0.631
quiet-0.592
zeb-0.577
isexual-0.552
-0.541
TokenSanders
Token ID26747
Feature activation+5.08e-01

Pos logit contributions
 welf+0.426
 weap+0.392
 scrut+0.387
 ingred+0.375
ships+0.367
Neg logit contributions
 Nice-0.508
quiet-0.491
zeb-0.482
isexual-0.470
-0.462
Token:
Token ID25
Feature activation+1.32e+00

Pos logit contributions
 welf+0.313
 weap+0.283
 scrut+0.275
 ingred+0.266
 unden+0.266
Neg logit contributions
 Nice-0.465
quiet-0.441
zeb-0.435
isexual-0.422
igue-0.417
Token '
Token ID705
Feature activation-2.31e-01

Pos logit contributions
 welf+0.971
 weap+0.897
 scrut+0.886
 ingred+0.865
ships+0.864
Neg logit contributions
 Nice-0.983
quiet-0.962
zeb-0.954
isexual-0.915
-0.907
Token
Token ID247
Feature activation-1.25e-02

Pos logit contributions
 Nice+0.253
quiet+0.243
zeb+0.240
+0.230
isexual+0.230
Neg logit contributions
 welf-0.381
 weap-0.355
 scrut-0.351
 ingred-0.340
 unden-0.336
Tokens
Token ID82
Feature activation-7.51e-01

Pos logit contributions
 Nice+0.010
quiet+0.009
zeb+0.009
isexual+0.009
+0.009
Neg logit contributions
 welf-0.009
 weap-0.008
 scrut-0.008
 ingred-0.008
 unden-0.008
Token been
Token ID587
Feature activation-3.35e-01

Pos logit contributions
 Nice+0.492
quiet+0.466
zeb+0.462
isexual+0.446
+0.433
Neg logit contributions
 welf-0.641
 weap-0.600
 scrut-0.593
 ingred-0.582
ships-0.573
Token made
Token ID925
Feature activation+3.99e-02

Pos logit contributions
 Nice+0.222
quiet+0.211
zeb+0.209
isexual+0.202
+0.196
Neg logit contributions
 welf-0.283
 weap-0.265
 scrut-0.262
 ingred-0.257
ships-0.253
Token since
Token ID1201
Feature activation-2.06e+00

Pos logit contributions
 welf+0.034
 weap+0.032
 scrut+0.032
 ingred+0.031
ships+0.030
Neg logit contributions
 Nice-0.026
quiet-0.025
zeb-0.024
isexual-0.024
-0.023
Token owes
Token ID29264
Feature activation+4.31e+00

Pos logit contributions
 Nice+1.324
quiet+1.232
zeb+1.218
isexual+1.158
+1.137
Neg logit contributions
 welf-1.802
 weap-1.694
 scrut-1.673
 ingred-1.641
ships-1.617
Token something
Token ID1223
Feature activation-1.33e+00

Pos logit contributions
 welf+3.452
 weap+3.221
 scrut+3.191
 ingred+3.127
ships+3.085
Neg logit contributions
 Nice-2.982
quiet-2.867
zeb-2.838
isexual-2.751
-2.671
Token to
Token ID284
Feature activation-7.72e-01

Pos logit contributions
 Nice+0.721
quiet+0.666
zeb+0.647
isexual+0.629
+0.614
Neg logit contributions
 welf-1.283
 weap-1.215
 scrut-1.199
 ingred-1.175
ships-1.161
Token Annie
Token ID25860
Feature activation+7.43e-02

Pos logit contributions
 Nice+0.492
quiet+0.462
zeb+0.456
isexual+0.441
+0.427
Neg logit contributions
 welf-0.673
 weap-0.634
 scrut-0.628
 ingred-0.615
ships-0.604
Token Hall
Token ID4789
Feature activation+7.26e-01

Pos logit contributions
 welf+0.058
 weap+0.054
 scrut+0.053
 ingred+0.052
ships+0.051
Neg logit contributions
 Nice-0.054
quiet-0.052
zeb-0.051
isexual-0.050
-0.049
Token.
Token ID13
Feature activation+3.25e-01

Pos logit contributions
 welf+0.521
 weap+0.481
 scrut+0.477
 ingred+0.464
ships+0.455
Neg logit contributions
 Nice-0.573
quiet-0.550
zeb-0.546
isexual-0.529
-0.519
Token
Token ID447
Feature activation+6.03e-01

Pos logit contributions
 welf+0.492
 weap+0.460
 scrut+0.458
 ingred+0.449
ships+0.440
Neg logit contributions
 Nice-0.360
quiet-0.340
zeb-0.335
isexual-0.323
-0.316
Token
Token ID251
Feature activation-2.60e-01

Pos logit contributions
 welf+0.520
 weap+0.483
 scrut+0.479
 ingred+0.468
 unden+0.456
Neg logit contributions
 Nice-0.396
quiet-0.380
zeb-0.374
isexual-0.359
-0.354
Token says
Token ID1139
Feature activation+8.76e-02

Pos logit contributions
 Nice+0.172
quiet+0.165
zeb+0.161
isexual+0.155
+0.152
Neg logit contributions
 welf-0.222
 weap-0.207
 scrut-0.205
 ingred-0.201
ships-0.195
Token NASA
Token ID8884
Feature activation+7.42e-01

Pos logit contributions
 welf+0.079
 weap+0.074
 scrut+0.073
 ingred+0.072
ships+0.071
Neg logit contributions
 Nice-0.053
quiet-0.050
zeb-0.050
isexual-0.048
-0.047
Token Goddard
Token ID47386
Feature activation-7.18e-01

Pos logit contributions
 welf+0.522
 weap+0.479
 scrut+0.476
 ingred+0.464
ships+0.455
Neg logit contributions
 Nice-0.596
quiet-0.573
zeb-0.567
isexual-0.549
-0.539
Token glac
Token ID25169
Feature activation+4.30e+00

Pos logit contributions
 Nice+0.489
quiet+0.461
zeb+0.451
isexual+0.437
igue+0.430
Neg logit contributions
 welf-0.597
 scrut-0.552
 weap-0.552
 ingred-0.540
 unden-0.530
Tokeniologist
Token ID31599
Feature activation+9.66e-01

Pos logit contributions
 welf+3.298
 weap+3.134
 scrut+3.048
ships+2.961
 ingred+2.957
Neg logit contributions
 Nice-3.110
quiet-2.955
zeb-2.919
isexual-2.825
-2.755
Token Kelly
Token ID9077
Feature activation-2.37e-01

Pos logit contributions
 welf+0.912
 weap+0.859
 scrut+0.853
 ingred+0.838
ships+0.827
Neg logit contributions
 Nice-0.540
quiet-0.510
zeb-0.503
isexual-0.483
-0.467
Token Br
Token ID1709
Feature activation-1.48e+00

Pos logit contributions
 Nice+0.153
quiet+0.144
zeb+0.143
isexual+0.137
+0.134
Neg logit contributions
 welf-0.205
 weap-0.192
 scrut-0.191
 ingred-0.187
ships-0.184
Tokenunt
Token ID2797
Feature activation-1.99e+00

Pos logit contributions
 Nice+1.031
quiet+0.986
zeb+0.978
isexual+0.945
+0.922
Neg logit contributions
 welf-1.207
 weap-1.123
 scrut-1.114
 ingred-1.091
ships-1.070
Token.
Token ID13
Feature activation+1.57e-02

Pos logit contributions
 Nice+1.392
quiet+1.334
zeb+1.329
isexual+1.256
+1.254
Neg logit contributions
 welf-1.606
 weap-1.494
 scrut-1.479
 ingred-1.459
 unden-1.418
Token the
Token ID262
Feature activation+2.19e-02

Pos logit contributions
 welf+0.135
 weap+0.127
 scrut+0.126
 ingred+0.123
ships+0.122
Neg logit contributions
 Nice-0.105
quiet-0.098
zeb-0.098
isexual-0.094
-0.092
Token Supreme
Token ID5617
Feature activation+2.24e+00

Pos logit contributions
 welf+0.018
 weap+0.017
 scrut+0.017
 ingred+0.017
ships+0.017
Neg logit contributions
 Nice-0.015
quiet-0.014
zeb-0.014
isexual-0.013
-0.013
Token Court
Token ID3078
Feature activation+7.34e-01

Pos logit contributions
 welf+1.765
 weap+1.646
 scrut+1.628
 ingred+1.603
ships+1.561
Neg logit contributions
 Nice-1.637
quiet-1.551
zeb-1.535
isexual-1.481
-1.459
Token Orders
Token ID30689
Feature activation+1.37e+00

Pos logit contributions
 welf+0.559
 weap+0.521
 scrut+0.514
 ingred+0.503
ships+0.495
Neg logit contributions
 Nice-0.547
quiet-0.522
zeb-0.517
isexual-0.500
-0.490
Token on
Token ID319
Feature activation+6.73e-01

Pos logit contributions
 welf+1.136
 weap+1.061
 scrut+1.053
 ingred+1.030
ships+1.015
Neg logit contributions
 Nice-0.928
quiet-0.885
zeb-0.876
isexual-0.847
-0.824
Token Aadhaar
Token ID47727
Feature activation+4.30e+00

Pos logit contributions
 welf+0.574
 weap+0.538
 scrut+0.533
 ingred+0.523
ships+0.515
Neg logit contributions
 Nice-0.440
quiet-0.417
zeb-0.412
isexual-0.398
-0.387
Token
Token ID198
Feature activation+6.58e-01

Pos logit contributions
 welf+3.471
 weap+3.222
 scrut+3.215
 ingred+3.131
ships+3.085
Neg logit contributions
 Nice-2.966
quiet-2.849
zeb-2.821
isexual-2.749
-2.660
Token
Token ID198
Feature activation+4.54e-01

Pos logit contributions
 welf+0.532
 weap+0.496
 scrut+0.492
 ingred+0.482
ships+0.472
Neg logit contributions
 Nice-0.460
quiet-0.439
zeb-0.434
isexual-0.420
-0.410
TokenThe
Token ID464
Feature activation+4.01e-02

Pos logit contributions
 welf+0.342
 weap+0.319
 scrut+0.314
 ingred+0.308
 unden+0.299
Neg logit contributions
 Nice-0.344
quiet-0.333
zeb-0.327
isexual-0.316
-0.312
Token Supreme
Token ID5617
Feature activation+2.17e+00

Pos logit contributions
 welf+0.031
 weap+0.029
 scrut+0.029
 ingred+0.028
ships+0.028
Neg logit contributions
 Nice-0.029
quiet-0.028
zeb-0.027
isexual-0.026
-0.026
Token Court
Token ID3078
Feature activation+7.20e-01

Pos logit contributions
 welf+1.702
 weap+1.585
 scrut+1.566
 ingred+1.540
ships+1.503
Neg logit contributions
 Nice-1.588
quiet-1.510
zeb-1.494
isexual-1.443
-1.413
Token 23
Token ID2242
Feature activation-2.01e-01

Pos logit contributions
 welf+0.106
 weap+0.100
 scrut+0.099
 ingred+0.098
ships+0.096
Neg logit contributions
 Nice-0.081
quiet-0.075
zeb-0.075
isexual-0.072
-0.069
Token Muslim
Token ID3765
Feature activation+2.62e+00

Pos logit contributions
 Nice+0.139
quiet+0.132
zeb+0.131
isexual+0.127
+0.123
Neg logit contributions
 welf-0.164
 weap-0.154
 scrut-0.151
 ingred-0.149
ships-0.146
Token organisations
Token ID16435
Feature activation+2.72e-01

Pos logit contributions
 welf+2.088
 weap+1.940
 scrut+1.935
 ingred+1.882
ships+1.851
Neg logit contributions
 Nice-1.830
quiet-1.763
zeb-1.742
isexual-1.691
-1.653
Token in
Token ID287
Feature activation+3.30e-01

Pos logit contributions
 welf+0.229
 weap+0.214
 scrut+0.211
 ingred+0.208
ships+0.204
Neg logit contributions
 Nice-0.181
quiet-0.172
zeb-0.171
isexual-0.164
-0.160
Token Tamil
Token ID32519
Feature activation+3.50e+00

Pos logit contributions
 welf+0.273
 weap+0.259
 scrut+0.254
 ingred+0.252
ships+0.247
Neg logit contributions
 Nice-0.227
quiet-0.211
zeb-0.209
isexual-0.202
-0.196
Token Nadu
Token ID46917
Feature activation+4.30e+00

Pos logit contributions
 welf+1.138
 weap+0.935
 scrut+0.910
 ingred+0.843
ships+0.837
Neg logit contributions
 Nice-4.104
quiet-4.009
zeb-3.973
isexual-3.911
-3.858
Token before
Token ID878
Feature activation+6.46e-02

Pos logit contributions
 welf+3.367
 weap+3.125
 scrut+3.116
 ingred+3.016
ships+3.015
Neg logit contributions
 Nice-3.018
quiet-2.899
zeb-2.864
isexual-2.800
-2.694
Token its
Token ID663
Feature activation-6.89e-01

Pos logit contributions
 welf+0.055
 weap+0.051
 scrut+0.051
 ingred+0.050
ships+0.049
Neg logit contributions
 Nice-0.043
quiet-0.040
zeb-0.040
isexual-0.038
-0.037
Token release
Token ID2650
Feature activation+1.21e+00

Pos logit contributions
 Nice+0.526
quiet+0.491
zeb+0.491
isexual+0.472
+0.458
Neg logit contributions
 welf-0.514
 weap-0.481
 scrut-0.471
 ingred-0.469
ships-0.461
Token and
Token ID290
Feature activation+1.10e-01

Pos logit contributions
 welf+1.020
 weap+0.954
 scrut+0.946
 ingred+0.926
ships+0.912
Neg logit contributions
 Nice-0.803
quiet-0.765
zeb-0.757
isexual-0.731
-0.711
Token before
Token ID878
Feature activation+2.30e-01

Pos logit contributions
 welf+0.092
 weap+0.086
 scrut+0.085
 ingred+0.084
ships+0.083
Neg logit contributions
 Nice-0.075
quiet-0.070
zeb-0.070
isexual-0.067
-0.065
Token!
Token ID0
Feature activation-7.90e-01

Pos logit contributions
 Nice+2.017
quiet+1.870
zeb+1.826
+1.766
isexual+1.758
Neg logit contributions
 welf-2.353
 weap-2.233
 scrut-2.150
ships-2.146
 ingred-2.143
Token If
Token ID1002
Feature activation+1.33e+00

Pos logit contributions
 Nice+0.543
quiet+0.505
zeb+0.497
isexual+0.479
+0.470
Neg logit contributions
 welf-0.661
 weap-0.618
 scrut-0.612
 ingred-0.603
ships-0.588
Token you
Token ID345
Feature activation-1.69e+00

Pos logit contributions
 welf+1.046
 weap+0.972
 scrut+0.963
 ingred+0.943
ships+0.927
Neg logit contributions
 Nice-0.956
quiet-0.912
zeb-0.903
isexual-0.875
-0.854
Token need
Token ID761
Feature activation+1.91e-01

Pos logit contributions
 Nice+1.138
quiet+1.074
zeb+1.053
isexual+1.007
+0.997
Neg logit contributions
 welf-1.419
 weap-1.306
 scrut-1.293
 ingred-1.286
CLASSIFIED-1.274
Token a
Token ID257
Feature activation-3.65e-01

Pos logit contributions
 welf+0.170
 weap+0.160
 scrut+0.158
 ingred+0.155
ships+0.153
Neg logit contributions
 Nice-0.117
quiet-0.111
zeb-0.110
isexual-0.106
-0.102
Token compound
Token ID13061
Feature activation-5.41e+00

Pos logit contributions
 Nice+0.255
quiet+0.239
zeb+0.237
isexual+0.228
+0.223
Neg logit contributions
 welf-0.297
 weap-0.277
 scrut-0.274
 ingred-0.270
ships-0.268
Token expression
Token ID5408
Feature activation-1.49e+00

Pos logit contributions
 Nice+3.939
quiet+3.581
zeb+3.517
+3.437
igue+3.369
Neg logit contributions
 welf-4.228
 weap-3.916
ships-3.893
 scrut-3.770
 ingred-3.758
Token,
Token ID11
Feature activation-3.49e-01

Pos logit contributions
 Nice+0.948
quiet+0.884
zeb+0.865
isexual+0.827
+0.820
Neg logit contributions
 welf-1.311
 weap-1.226
 scrut-1.203
 ingred-1.196
ships-1.179
Token use
Token ID779
Feature activation+6.00e-01

Pos logit contributions
 Nice+0.254
quiet+0.238
zeb+0.235
isexual+0.226
+0.222
Neg logit contributions
 welf-0.277
 weap-0.256
 scrut-0.253
 ingred-0.249
ships-0.248
Token ng
Token ID23370
Feature activation-9.18e-01

Pos logit contributions
 welf+0.495
 weap+0.462
 scrut+0.457
 ingred+0.449
ships+0.443
Neg logit contributions
 Nice-0.409
quiet-0.389
zeb-0.384
isexual-0.371
-0.362
Token-
Token ID12
Feature activation+4.43e-02

Pos logit contributions
 Nice+0.679
quiet+0.648
zeb+0.640
isexual+0.618
+0.605
Neg logit contributions
 welf-0.705
 weap-0.654
 scrut-0.647
 ingred-0.634
ships-0.627
Token in
Token ID287
Feature activation-2.08e-01

Pos logit contributions
 Nice+1.454
quiet+1.371
zeb+1.351
isexual+1.298
+1.259
Neg logit contributions
 welf-2.345
 weap-2.200
 scrut-2.190
 ingred-2.147
ships-2.113
Token clock
Token ID8801
Feature activation-2.59e+00

Pos logit contributions
 Nice+0.133
quiet+0.127
zeb+0.125
isexual+0.121
+0.117
Neg logit contributions
 welf-0.180
 weap-0.169
 scrut-0.167
 ingred-0.164
ships-0.162
Token speeds
Token ID12055
Feature activation+3.46e-01

Pos logit contributions
 Nice+1.828
quiet+1.744
zeb+1.727
isexual+1.640
+1.628
Neg logit contributions
 welf-2.076
 weap-1.927
 scrut-1.907
 ingred-1.880
ships-1.837
Token.
Token ID13
Feature activation+3.02e-01

Pos logit contributions
 welf+0.277
 weap+0.258
 scrut+0.256
 ingred+0.251
ships+0.246
Neg logit contributions
 Nice-0.245
quiet-0.233
zeb-0.231
isexual-0.222
-0.218
Token In
Token ID554
Feature activation+6.87e-01

Pos logit contributions
 welf+0.253
 weap+0.236
 scrut+0.234
 ingred+0.231
ships+0.225
Neg logit contributions
 Nice-0.207
quiet-0.195
zeb-0.192
isexual-0.185
-0.181
Token OC
Token ID24775
Feature activation-5.07e+00

Pos logit contributions
 welf+0.558
 weap+0.520
 scrut+0.514
 ingred+0.506
ships+0.498
Neg logit contributions
 Nice-0.479
quiet-0.456
zeb-0.449
isexual-0.435
-0.424
Token M
Token ID337
Feature activation-9.23e-01

Pos logit contributions
 Nice+1.897
quiet+1.737
zeb+1.638
isexual+1.509
+1.456
Neg logit contributions
 welf-5.760
 weap-5.443
 scrut-5.395
 ingred-5.363
 unden-5.248
TokenODE
Token ID16820
Feature activation-1.31e+00

Pos logit contributions
 Nice+0.643
quiet+0.613
zeb+0.609
isexual+0.588
+0.573
Neg logit contributions
 welf-0.750
 weap-0.699
 scrut-0.698
 ingred-0.680
ships-0.666
Token the
Token ID262
Feature activation-2.67e-01

Pos logit contributions
 Nice+0.757
quiet+0.712
zeb+0.694
isexual+0.664
+0.648
Neg logit contributions
 welf-1.228
 weap-1.152
 scrut-1.143
 ingred-1.125
ships-1.108
Token core
Token ID4755
Feature activation-1.52e-01

Pos logit contributions
 Nice+0.187
quiet+0.177
zeb+0.175
isexual+0.168
+0.165
Neg logit contributions
 welf-0.216
 weap-0.201
 scrut-0.199
 ingred-0.195
ships-0.193
Token increases
Token ID5732
Feature activation-2.03e+00

Pos logit contributions
 Nice+0.111
quiet+0.106
zeb+0.105
isexual+0.102
+0.099
Neg logit contributions
 welf-0.118
 weap-0.109
 scrut-0.108
 ingred-0.106
ships-0.104
Token warm
Token ID5814
Feature activation+1.92e-01

Pos logit contributions
 welf+0.784
 weap+0.731
 scrut+0.725
 ingred+0.709
ships+0.698
Neg logit contributions
 Nice-0.682
quiet-0.651
zeb-0.645
isexual-0.625
-0.608
Token and
Token ID290
Feature activation-4.49e-01

Pos logit contributions
 welf+0.154
 weap+0.143
 scrut+0.142
 ingred+0.139
ships+0.136
Neg logit contributions
 Nice-0.135
quiet-0.129
zeb-0.128
isexual-0.124
-0.121
Token stubborn
Token ID24444
Feature activation+7.40e-01

Pos logit contributions
 Nice+0.285
quiet+0.271
zeb+0.267
isexual+0.257
+0.250
Neg logit contributions
 welf-0.392
 weap-0.367
 scrut-0.363
 ingred-0.357
ships-0.352
Token sonic
Token ID36220
Feature activation+1.09e-01

Pos logit contributions
 welf+0.560
 weap+0.519
 scrut+0.514
 ingred+0.502
ships+0.493
Neg logit contributions
 Nice-0.554
quiet-0.530
zeb-0.524
isexual-0.508
-0.497
Token imp
Token ID848
Feature activation+7.54e-01

Pos logit contributions
 welf+0.080
 weap+0.074
 scrut+0.073
 ingred+0.071
ships+0.070
Neg logit contributions
 Nice-0.084
quiet-0.080
zeb-0.080
isexual-0.077
-0.075
Tokenurities
Token ID10886
Feature activation-4.95e+00

Pos logit contributions
 welf+0.602
 weap+0.560
 scrut+0.555
 ingred+0.543
ships+0.533
Neg logit contributions
 Nice-0.534
quiet-0.511
zeb-0.505
isexual-0.489
-0.477
Token,
Token ID11
Feature activation-4.25e-01

Pos logit contributions
 Nice+3.264
quiet+3.140
zeb+3.071
+2.973
isexual+2.954
Neg logit contributions
 welf-4.126
 weap-3.798
 ingred-3.723
 scrut-3.698
CLASSIFIED-3.655
Token having
Token ID1719
Feature activation-1.56e+00

Pos logit contributions
 Nice+0.280
quiet+0.266
zeb+0.263
isexual+0.254
+0.248
Neg logit contributions
 welf-0.359
 weap-0.336
 scrut-0.333
 ingred-0.326
ships-0.321
Token been
Token ID587
Feature activation-2.27e-01

Pos logit contributions
 Nice+1.031
quiet+0.983
zeb+0.970
isexual+0.938
+0.917
Neg logit contributions
 welf-1.318
 weap-1.232
 scrut-1.215
 ingred-1.196
ships-1.175
Token encoded
Token ID30240
Feature activation-1.17e+00

Pos logit contributions
 Nice+0.155
quiet+0.148
zeb+0.147
isexual+0.141
+0.139
Neg logit contributions
 welf-0.186
 weap-0.174
 scrut-0.172
 ingred-0.169
ships-0.166
Token in
Token ID287
Feature activation-3.72e-01

Pos logit contributions
 Nice+0.736
quiet+0.704
zeb+0.691
isexual+0.667
+0.656
Neg logit contributions
 welf-1.027
 weap-0.953
 scrut-0.949
 ingred-0.929
ships-0.917
Token earlier
Token ID2961
Feature activation-6.24e-01

Pos logit contributions
 welf+0.232
 weap+0.217
 scrut+0.216
 ingred+0.213
ships+0.208
Neg logit contributions
 Nice-0.182
quiet-0.173
zeb-0.170
isexual-0.164
-0.161
Token works
Token ID2499
Feature activation+1.35e-01

Pos logit contributions
 Nice+0.484
quiet+0.462
zeb+0.454
isexual+0.441
+0.431
Neg logit contributions
 welf-0.458
 weap-0.425
 scrut-0.424
 ingred-0.413
ships-0.401
Token like
Token ID588
Feature activation-5.38e-01

Pos logit contributions
 welf+0.110
 weap+0.102
 scrut+0.101
 ingred+0.100
ships+0.098
Neg logit contributions
 Nice-0.094
quiet-0.090
zeb-0.089
isexual-0.086
-0.084
Token The
Token ID383
Feature activation-6.91e-01

Pos logit contributions
 Nice+0.353
quiet+0.332
zeb+0.329
isexual+0.316
+0.309
Neg logit contributions
 welf-0.462
 weap-0.432
 scrut-0.429
 ingred-0.422
ships-0.413
Token Cour
Token ID2734
Feature activation-1.35e+00

Pos logit contributions
 Nice+0.460
quiet+0.436
zeb+0.430
isexual+0.415
+0.405
Neg logit contributions
 welf-0.584
 weap-0.545
 scrut-0.541
 ingred-0.531
ships-0.520
Tokentyard
Token ID30308
Feature activation-4.90e+00

Pos logit contributions
 Nice+0.694
quiet+0.654
zeb+0.645
isexual+0.611
+0.595
Neg logit contributions
 welf-1.343
 weap-1.268
 scrut-1.260
 ingred-1.236
 unden-1.208
Token,
Token ID11
Feature activation+2.03e-01

Pos logit contributions
 Nice+3.260
quiet+3.020
zeb+2.995
+2.855
isexual+2.830
Neg logit contributions
 welf-4.126
 weap-3.839
 scrut-3.833
 ingred-3.812
 unden-3.664
Token where
Token ID810
Feature activation-2.96e-01

Pos logit contributions
 welf+0.174
 weap+0.163
 scrut+0.161
 ingred+0.159
ships+0.156
Neg logit contributions
 Nice-0.132
quiet-0.125
zeb-0.124
isexual-0.119
-0.117
Token the
Token ID262
Feature activation+2.56e-01

Pos logit contributions
 Nice+0.187
quiet+0.175
zeb+0.173
isexual+0.167
+0.163
Neg logit contributions
 welf-0.260
 weap-0.243
 scrut-0.242
 ingred-0.238
ships-0.234
Token characters
Token ID3435
Feature activation+5.41e-01

Pos logit contributions
 welf+0.203
 weap+0.188
 scrut+0.187
 ingred+0.183
ships+0.180
Neg logit contributions
 Nice-0.183
quiet-0.174
zeb-0.172
isexual-0.166
-0.163
Token boast
Token ID28020
Feature activation-2.77e-01

Pos logit contributions
 welf+0.442
 weap+0.411
 scrut+0.407
 ingred+0.401
ships+0.393
Neg logit contributions
 Nice-0.374
quiet-0.357
zeb-0.353
isexual-0.341
-0.334
Token was
Token ID373
Feature activation-7.03e-02

Pos logit contributions
 welf+0.208
 weap+0.194
 scrut+0.192
 ingred+0.188
ships+0.185
Neg logit contributions
 Nice-0.179
quiet-0.170
zeb-0.169
isexual-0.163
-0.160
Token characterized
Token ID16264
Feature activation+2.19e-01

Pos logit contributions
 Nice+0.045
quiet+0.042
zeb+0.042
isexual+0.040
+0.039
Neg logit contributions
 welf-0.061
 weap-0.057
 scrut-0.057
 ingred-0.056
ships-0.055
Token as
Token ID355
Feature activation-9.02e-01

Pos logit contributions
 welf+0.185
 weap+0.173
 scrut+0.171
 ingred+0.168
ships+0.165
Neg logit contributions
 Nice-0.146
quiet-0.138
zeb-0.137
isexual-0.132
-0.129
Token having
Token ID1719
Feature activation-2.13e+00

Pos logit contributions
 Nice+0.604
quiet+0.566
zeb+0.555
isexual+0.545
+0.528
Neg logit contributions
 welf-0.760
 weap-0.712
 scrut-0.702
 ingred-0.690
ships-0.683
Token bacterial
Token ID23462
Feature activation-2.54e+00

Pos logit contributions
 Nice+1.438
quiet+1.334
zeb+1.301
isexual+1.299
+1.249
Neg logit contributions
 welf-1.777
 weap-1.669
 scrut-1.622
 ingred-1.611
ships-1.585
Token vag
Token ID14334
Feature activation-4.75e+00

Pos logit contributions
 Nice+1.812
quiet+1.706
zeb+1.688
isexual+1.687
+1.591
Neg logit contributions
 welf-1.992
 weap-1.873
 scrut-1.828
 ingred-1.800
ships-1.785
Tokenin
Token ID259
Feature activation-4.70e-02

Pos logit contributions
 Nice+2.009
quiet+1.903
zeb+1.823
isexual+1.773
igue+1.640
Neg logit contributions
 welf-5.151
 weap-4.870
 scrut-4.806
 ingred-4.789
 unden-4.713
Tokenosis
Token ID5958
Feature activation-1.93e+00

Pos logit contributions
 Nice+0.032
quiet+0.031
zeb+0.030
isexual+0.030
+0.029
Neg logit contributions
 welf-0.039
 weap-0.036
 scrut-0.036
 ingred-0.035
ships-0.034
Token (
Token ID357
Feature activation-3.76e-01

Pos logit contributions
 Nice+1.323
quiet+1.248
zeb+1.233
isexual+1.209
+1.174
Neg logit contributions
 welf-1.588
 weap-1.486
 scrut-1.454
 ingred-1.436
ships-1.407
TokenB
Token ID33
Feature activation+2.34e-01

Pos logit contributions
 Nice+0.270
quiet+0.259
zeb+0.255
isexual+0.249
+0.242
Neg logit contributions
 welf-0.298
 weap-0.277
 scrut-0.273
 ingred-0.268
ships-0.260
TokenV
Token ID53
Feature activation-1.75e+00

Pos logit contributions
 welf+0.179
 weap+0.166
 scrut+0.163
 ingred+0.160
ships+0.156
Neg logit contributions
 Nice-0.174
quiet-0.167
zeb-0.165
isexual-0.163
-0.159
Token lot
Token ID1256
Feature activation+7.60e-01

Pos logit contributions
 welf+0.112
 weap+0.104
 scrut+0.103
 ingred+0.102
ships+0.100
Neg logit contributions
 Nice-0.096
quiet-0.091
zeb-0.090
isexual-0.087
-0.084
Token of
Token ID286
Feature activation-8.76e-02

Pos logit contributions
 welf+0.577
 weap+0.536
 scrut+0.532
 ingred+0.516
ships+0.510
Neg logit contributions
 Nice-0.563
quiet-0.540
zeb-0.538
isexual-0.521
-0.509
Token sense
Token ID2565
Feature activation+1.31e+00

Pos logit contributions
 Nice+0.044
quiet+0.041
zeb+0.039
isexual+0.037
+0.036
Neg logit contributions
 welf-0.089
 weap-0.084
 scrut-0.083
 ingred-0.082
ships-0.081
Token.
Token ID13
Feature activation-1.34e-01

Pos logit contributions
 welf+0.985
 weap+0.916
 scrut+0.906
 ingred+0.883
ships+0.872
Neg logit contributions
 Nice-0.982
quiet-0.942
zeb-0.937
isexual-0.909
-0.887
Token Its
Token ID6363
Feature activation-7.95e-01

Pos logit contributions
 Nice+0.093
quiet+0.086
zeb+0.085
isexual+0.081
+0.080
Neg logit contributions
 welf-0.112
 scrut-0.105
 weap-0.104
 ingred-0.104
 unden-0.100
Token admittedly
Token ID33603
Feature activation-4.74e+00

Pos logit contributions
 Nice+0.554
quiet+0.525
zeb+0.514
isexual+0.493
+0.484
Neg logit contributions
 welf-0.642
 weap-0.598
 scrut-0.592
 ingred-0.585
ships-0.579
Token high
Token ID1029
Feature activation+7.10e-02

Pos logit contributions
 Nice+2.980
quiet+2.793
zeb+2.687
isexual+2.572
+2.524
Neg logit contributions
 welf-4.065
 weap-3.811
 ingred-3.779
CLASSIFIED-3.736
 scrut-3.735
Token fuel
Token ID5252
Feature activation-2.15e+00

Pos logit contributions
 welf+0.055
 weap+0.051
 scrut+0.051
 ingred+0.050
ships+0.049
Neg logit contributions
 Nice-0.052
quiet-0.049
zeb-0.049
isexual-0.047
-0.046
Token consumption
Token ID7327
Feature activation+2.94e-01

Pos logit contributions
 Nice+1.592
quiet+1.522
zeb+1.503
isexual+1.447
igue+1.435
Neg logit contributions
 welf-1.628
 weap-1.507
 scrut-1.488
 ingred-1.452
ships-1.435
Token,
Token ID11
Feature activation-4.03e-01

Pos logit contributions
 welf+0.243
 weap+0.227
 scrut+0.225
 ingred+0.220
ships+0.217
Neg logit contributions
 Nice-0.200
quiet-0.190
zeb-0.187
isexual-0.180
-0.176
Token noise
Token ID7838
Feature activation-1.71e+00

Pos logit contributions
 Nice+0.272
quiet+0.258
zeb+0.253
isexual+0.245
+0.239
Neg logit contributions
 welf-0.334
 weap-0.312
 scrut-0.310
 ingred-0.305
ships-0.300
Token a
Token ID257
Feature activation-4.78e-01

Pos logit contributions
 Nice+0.022
quiet+0.020
zeb+0.020
isexual+0.019
+0.019
Neg logit contributions
 welf-0.027
 weap-0.026
 scrut-0.025
 ingred-0.025
ships-0.025
Token Catalan
Token ID31066
Feature activation-5.39e-02

Pos logit contributions
 Nice+0.322
quiet+0.303
zeb+0.296
isexual+0.287
+0.282
Neg logit contributions
 welf-0.402
 weap-0.377
 scrut-0.369
 ingred-0.367
ships-0.360
Token town
Token ID3240
Feature activation-2.16e+00

Pos logit contributions
 Nice+0.036
quiet+0.034
zeb+0.033
isexual+0.032
+0.032
Neg logit contributions
 welf-0.045
 weap-0.043
 scrut-0.042
 ingred-0.041
ships-0.041
Token in
Token ID287
Feature activation-3.71e-01

Pos logit contributions
 Nice+1.390
quiet+1.319
zeb+1.291
isexual+1.244
+1.219
Neg logit contributions
 welf-1.870
 weap-1.752
 scrut-1.726
 ingred-1.706
 unden-1.655
Token a
Token ID257
Feature activation-7.44e-01

Pos logit contributions
 Nice+0.244
quiet+0.229
zeb+0.223
isexual+0.216
+0.213
Neg logit contributions
 welf-0.319
 weap-0.300
 scrut-0.295
 ingred-0.293
ships-0.286
Token bid
Token ID8406
Feature activation-4.68e+00

Pos logit contributions
 Nice+0.482
quiet+0.454
zeb+0.445
isexual+0.428
+0.420
Neg logit contributions
 welf-0.643
 weap-0.604
 scrut-0.593
 ingred-0.587
ships-0.576
Token to
Token ID284
Feature activation-5.91e-01

Pos logit contributions
 Nice+2.128
quiet+2.015
zeb+1.917
isexual+1.780
+1.775
Neg logit contributions
 welf-4.932
 weap-4.597
 ingred-4.551
 scrut-4.549
 unden-4.545
Token sc
Token ID629
Feature activation+1.01e-01

Pos logit contributions
 Nice+0.376
quiet+0.357
zeb+0.348
isexual+0.337
+0.330
Neg logit contributions
 welf-0.518
 weap-0.484
 scrut-0.474
 ingred-0.471
ships-0.466
Tokenupper
Token ID45828
Feature activation-2.17e-01

Pos logit contributions
 welf+0.088
 weap+0.082
 scrut+0.082
 ingred+0.080
ships+0.079
Neg logit contributions
 Nice-0.064
quiet-0.061
zeb-0.060
isexual-0.058
-0.057
Token the
Token ID262
Feature activation-4.50e-01

Pos logit contributions
 Nice+0.143
quiet+0.135
zeb+0.132
isexual+0.128
+0.126
Neg logit contributions
 welf-0.184
 weap-0.173
 scrut-0.170
 ingred-0.168
ships-0.165
Token referendum
Token ID11467
Feature activation-1.74e+00

Pos logit contributions
 Nice+0.322
quiet+0.304
zeb+0.297
isexual+0.289
+0.284
Neg logit contributions
 welf-0.359
 weap-0.335
 scrut-0.329
 ingred-0.325
ships-0.319
Token tested
Token ID6789
Feature activation+8.43e-02

Pos logit contributions
 Nice+0.222
quiet+0.213
zeb+0.210
isexual+0.203
+0.198
Neg logit contributions
 welf-0.269
 weap-0.248
 ingred-0.244
 scrut-0.244
ships-0.237
Token the
Token ID262
Feature activation+1.42e-01

Pos logit contributions
 welf+0.074
 weap+0.069
 scrut+0.068
 ingred+0.067
ships+0.066
Neg logit contributions
 Nice-0.054
quiet-0.051
zeb-0.050
isexual-0.048
-0.047
Token single
Token ID2060
Feature activation-4.15e-01

Pos logit contributions
 welf+0.122
 weap+0.114
 scrut+0.113
 ingred+0.110
ships+0.109
Neg logit contributions
 Nice-0.094
quiet-0.089
zeb-0.087
isexual-0.083
-0.082
Token card
Token ID2657
Feature activation-3.07e+00

Pos logit contributions
 Nice+0.294
quiet+0.281
zeb+0.277
isexual+0.269
+0.263
Neg logit contributions
 welf-0.330
 weap-0.307
 scrut-0.304
 ingred-0.298
ships-0.294
Token in
Token ID287
Feature activation+3.26e-01

Pos logit contributions
 Nice+1.947
quiet+1.834
zeb+1.794
isexual+1.695
+1.669
Neg logit contributions
 welf-2.707
 weap-2.516
 scrut-2.490
 ingred-2.470
ships-2.428
Token OC
Token ID24775
Feature activation-4.56e+00

Pos logit contributions
 welf+0.281
 weap+0.263
 scrut+0.259
 ingred+0.257
ships+0.253
Neg logit contributions
 Nice-0.212
quiet-0.202
zeb-0.197
isexual-0.191
-0.186
Token mode
Token ID4235
Feature activation-2.02e+00

Pos logit contributions
 Nice+2.021
quiet+1.884
zeb+1.809
isexual+1.658
+1.622
Neg logit contributions
 welf-4.860
 weap-4.593
 ingred-4.532
 scrut-4.528
ships-4.450
Token,
Token ID11
Feature activation+2.33e-02

Pos logit contributions
 Nice+1.270
quiet+1.197
zeb+1.166
isexual+1.103
+1.099
Neg logit contributions
 welf-1.800
 weap-1.681
 scrut-1.655
 ingred-1.639
ships-1.612
Token but
Token ID475
Feature activation+5.23e-01

Pos logit contributions
 welf+0.021
 weap+0.019
 scrut+0.019
 ingred+0.019
ships+0.019
Neg logit contributions
 Nice-0.015
quiet-0.014
zeb-0.014
isexual-0.013
-0.013
Token we
Token ID356
Feature activation-4.22e-01

Pos logit contributions
 welf+0.444
 weap+0.413
 scrut+0.407
 ingred+0.404
ships+0.398
Neg logit contributions
 Nice-0.350
quiet-0.332
zeb-0.325
isexual-0.310
-0.306
Token are
Token ID389
Feature activation-2.32e-01

Pos logit contributions
 Nice+0.290
quiet+0.278
zeb+0.274
isexual+0.263
+0.258
Neg logit contributions
 welf-0.349
 weap-0.322
 ingred-0.318
 scrut-0.316
CLASSIFIED-0.309
Token
Token ID447
Feature activation-4.43e-01

Pos logit contributions
 Nice+0.385
quiet+0.369
zeb+0.363
isexual+0.348
+0.346
Neg logit contributions
 welf-0.453
 weap-0.421
 scrut-0.417
 ingred-0.408
ships-0.400
Token
Token ID247
Feature activation-1.54e-01

Pos logit contributions
 Nice+0.277
quiet+0.266
zeb+0.263
isexual+0.250
+0.250
Neg logit contributions
 welf-0.395
 weap-0.368
 scrut-0.365
 ingred-0.355
 unden-0.350
Tokens
Token ID82
Feature activation-1.06e-01

Pos logit contributions
 Nice+0.118
quiet+0.114
zeb+0.112
isexual+0.108
+0.107
Neg logit contributions
 welf-0.114
 weap-0.106
 scrut-0.104
 ingred-0.102
ships-0.099
Token where
Token ID810
Feature activation-7.88e-01

Pos logit contributions
 Nice+0.076
quiet+0.072
zeb+0.071
isexual+0.068
+0.067
Neg logit contributions
 welf-0.085
 weap-0.079
 scrut-0.078
 ingred-0.076
ships-0.075
Token the
Token ID262
Feature activation+6.80e-02

Pos logit contributions
 Nice+0.529
quiet+0.502
zeb+0.489
isexual+0.471
+0.464
Neg logit contributions
 welf-0.662
 weap-0.617
 scrut-0.615
 ingred-0.602
ships-0.589
Token admittedly
Token ID33603
Feature activation-4.52e+00

Pos logit contributions
 welf+0.052
 weap+0.049
 scrut+0.048
 ingred+0.047
ships+0.046
Neg logit contributions
 Nice-0.050
quiet-0.048
zeb-0.047
isexual-0.045
-0.045
Token tiny
Token ID7009
Feature activation-4.74e-01

Pos logit contributions
 Nice+2.950
quiet+2.784
zeb+2.675
+2.551
isexual+2.495
Neg logit contributions
 welf-3.801
 weap-3.545
 ingred-3.503
 scrut-3.464
ships-3.455
Token piece
Token ID3704
Feature activation-4.52e-01

Pos logit contributions
 Nice+0.362
quiet+0.343
zeb+0.337
isexual+0.324
+0.323
Neg logit contributions
 welf-0.355
 weap-0.329
 scrut-0.328
 ingred-0.318
ships-0.311
Token of
Token ID286
Feature activation+2.71e-01

Pos logit contributions
 Nice+0.326
quiet+0.312
zeb+0.309
isexual+0.299
+0.292
Neg logit contributions
 welf-0.355
 weap-0.330
 scrut-0.327
 ingred-0.320
ships-0.314
Token good
Token ID922
Feature activation+1.10e+00

Pos logit contributions
 welf+0.192
 weap+0.177
 scrut+0.176
 ingred+0.171
ships+0.169
Neg logit contributions
 Nice-0.217
quiet-0.208
zeb-0.205
isexual-0.198
-0.195
Token news
Token ID1705
Feature activation+4.66e-01

Pos logit contributions
 welf+0.915
 weap+0.854
 scrut+0.847
 ingred+0.830
ships+0.814
Neg logit contributions
 Nice-0.750
quiet-0.716
zeb-0.707
isexual-0.681
-0.667
Token be
Token ID307
Feature activation+3.94e-01

Pos logit contributions
 Nice+0.891
quiet+0.863
zeb+0.842
isexual+0.819
+0.796
Neg logit contributions
 welf-1.070
 weap-0.989
 scrut-0.982
 ingred-0.965
ships-0.959
Token explained
Token ID4893
Feature activation-1.52e-01

Pos logit contributions
 welf+0.323
 weap+0.301
 scrut+0.297
 ingred+0.294
ships+0.290
Neg logit contributions
 Nice-0.269
quiet-0.257
zeb-0.254
isexual-0.246
-0.238
Token away
Token ID1497
Feature activation-1.53e+00

Pos logit contributions
 Nice+0.084
quiet+0.080
zeb+0.078
isexual+0.074
+0.072
Neg logit contributions
 welf-0.146
 weap-0.138
 scrut-0.136
 ingred-0.135
ships-0.132
Token as
Token ID355
Feature activation-2.11e-01

Pos logit contributions
 Nice+1.009
quiet+0.968
zeb+0.953
isexual+0.912
+0.897
Neg logit contributions
 welf-1.284
 weap-1.201
 scrut-1.182
 ingred-1.177
ships-1.148
Token an
Token ID281
Feature activation-8.26e-01

Pos logit contributions
 Nice+0.146
quiet+0.139
zeb+0.137
isexual+0.132
+0.129
Neg logit contributions
 welf-0.172
 weap-0.160
 scrut-0.159
 ingred-0.156
ships-0.154
Token aber
Token ID42499
Feature activation-4.49e+00

Pos logit contributions
 Nice+0.556
quiet+0.527
zeb+0.521
isexual+0.505
+0.493
Neg logit contributions
 welf-0.686
 weap-0.641
 scrut-0.634
 ingred-0.622
ships-0.615
Tokenration
Token ID1358
Feature activation-2.63e+00

Pos logit contributions
 Nice+2.245
quiet+2.164
zeb+2.066
isexual+2.002
igue+1.932
Neg logit contributions
 welf-4.497
 weap-4.272
 scrut-4.215
 ingred-4.146
 unden-4.104
Token of
Token ID286
Feature activation-3.28e-01

Pos logit contributions
 Nice+1.760
quiet+1.658
zeb+1.647
isexual+1.579
+1.546
Neg logit contributions
 welf-2.199
 weap-2.060
 scrut-2.025
 ingred-2.015
ships-1.954
Token the
Token ID262
Feature activation-1.31e-01

Pos logit contributions
 Nice+0.216
quiet+0.203
zeb+0.202
isexual+0.194
+0.190
Neg logit contributions
 welf-0.278
 weap-0.260
 scrut-0.258
 ingred-0.253
ships-0.250
Token primitive
Token ID20049
Feature activation-3.02e+00

Pos logit contributions
 Nice+0.087
quiet+0.083
zeb+0.082
isexual+0.079
+0.077
Neg logit contributions
 welf-0.111
 weap-0.104
 scrut-0.103
 ingred-0.101
ships-0.099
Token mind
Token ID2000
Feature activation+1.40e+00

Pos logit contributions
 Nice+2.092
quiet+1.925
zeb+1.922
isexual+1.828
+1.826
Neg logit contributions
 welf-2.446
 weap-2.275
 scrut-2.258
 ingred-2.232
ships-2.189
Token army
Token ID5428
Feature activation+5.90e-01

Pos logit contributions
 welf+0.902
 weap+0.840
 scrut+0.833
 ingred+0.814
ships+0.801
Neg logit contributions
 Nice-0.810
quiet-0.774
zeb-0.766
isexual-0.742
-0.723
Token and
Token ID290
Feature activation-3.23e-01

Pos logit contributions
 welf+0.483
 weap+0.449
 scrut+0.446
 ingred+0.438
ships+0.429
Neg logit contributions
 Nice-0.406
quiet-0.387
zeb-0.385
isexual-0.370
-0.362
Token its
Token ID663
Feature activation-1.20e+00

Pos logit contributions
 Nice+0.208
quiet+0.197
zeb+0.195
isexual+0.187
+0.183
Neg logit contributions
 welf-0.278
 weap-0.261
 scrut-0.259
 ingred-0.254
ships-0.251
Token allies
Token ID7681
Feature activation-3.27e-01

Pos logit contributions
 Nice+0.891
quiet+0.834
zeb+0.830
isexual+0.795
+0.785
Neg logit contributions
 welf-0.920
 weap-0.854
 scrut-0.853
 ingred-0.837
ships-0.825
Token captured
Token ID7907
Feature activation-1.06e-01

Pos logit contributions
 Nice+0.222
quiet+0.211
zeb+0.209
isexual+0.201
+0.197
Neg logit contributions
 welf-0.272
 weap-0.253
 scrut-0.251
 ingred-0.247
ships-0.242
Token turf
Token ID29553
Feature activation-4.48e+00

Pos logit contributions
 Nice+0.070
quiet+0.065
zeb+0.065
isexual+0.062
+0.061
Neg logit contributions
 welf-0.091
 weap-0.085
 scrut-0.085
 ingred-0.083
ships-0.082
Token around
Token ID1088
Feature activation-1.42e+00

Pos logit contributions
 Nice+2.742
quiet+2.581
zeb+2.512
+2.390
isexual+2.358
Neg logit contributions
 welf-4.053
 weap-3.751
 scrut-3.748
 ingred-3.704
 unden-3.585
Token the
Token ID262
Feature activation-5.03e-01

Pos logit contributions
 Nice+0.865
quiet+0.808
zeb+0.803
isexual+0.768
+0.749
Neg logit contributions
 welf-1.281
 weap-1.203
 scrut-1.196
 ingred-1.171
ships-1.152
Token southern
Token ID8372
Feature activation+1.02e+00

Pos logit contributions
 Nice+0.311
quiet+0.295
zeb+0.291
isexual+0.281
+0.273
Neg logit contributions
 welf-0.446
 weap-0.419
 scrut-0.416
 ingred-0.408
ships-0.402
Token edge
Token ID5743
Feature activation-1.32e+00

Pos logit contributions
 welf+0.914
 weap+0.858
 scrut+0.852
 ingred+0.835
ships+0.823
Neg logit contributions
 Nice-0.619
quiet-0.589
zeb-0.582
isexual-0.561
-0.543
Token of
Token ID286
Feature activation-9.36e-02

Pos logit contributions
 Nice+0.971
quiet+0.930
zeb+0.921
isexual+0.895
+0.871
Neg logit contributions
 welf-1.012
 weap-0.939
 scrut-0.931
 ingred-0.911
ships-0.897
Token amongst
Token ID12077
Feature activation-1.45e+00

Pos logit contributions
 Nice+1.371
quiet+1.293
zeb+1.273
isexual+1.210
+1.175
Neg logit contributions
 welf-2.021
 weap-1.893
 scrut-1.885
 ingred-1.855
ships-1.810
Token the
Token ID262
Feature activation-3.98e-01

Pos logit contributions
 Nice+0.934
quiet+0.872
zeb+0.861
isexual+0.826
+0.801
Neg logit contributions
 welf-1.252
 weap-1.179
 scrut-1.167
 ingred-1.152
ships-1.141
Token officers
Token ID3790
Feature activation+4.15e-02

Pos logit contributions
 Nice+0.267
quiet+0.251
zeb+0.247
isexual+0.239
+0.232
Neg logit contributions
 welf-0.332
 weap-0.312
 scrut-0.308
 ingred-0.303
ships-0.301
Token,
Token ID11
Feature activation-2.44e-01

Pos logit contributions
 welf+0.036
 weap+0.034
 scrut+0.034
 ingred+0.033
ships+0.033
Neg logit contributions
 Nice-0.026
quiet-0.025
zeb-0.025
isexual-0.024
-0.023
Token with
Token ID351
Feature activation+2.93e-01

Pos logit contributions
 Nice+0.163
quiet+0.154
zeb+0.153
isexual+0.147
+0.143
Neg logit contributions
 welf-0.205
 weap-0.192
 scrut-0.190
 ingred-0.187
ships-0.184
Token crude
Token ID14897
Feature activation-4.47e+00

Pos logit contributions
 welf+0.242
 weap+0.226
 scrut+0.224
 ingred+0.220
ships+0.217
Neg logit contributions
 Nice-0.199
quiet-0.189
zeb-0.187
isexual-0.180
-0.176
Token and
Token ID290
Feature activation-5.40e-01

Pos logit contributions
 Nice+3.054
quiet+2.826
zeb+2.814
isexual+2.698
+2.630
Neg logit contributions
 welf-3.637
 scrut-3.327
 weap-3.317
ships-3.286
 ingred-3.259
Token disgusting
Token ID23374
Feature activation-1.52e+00

Pos logit contributions
 Nice+0.329
quiet+0.311
zeb+0.308
isexual+0.296
+0.287
Neg logit contributions
 welf-0.484
 weap-0.454
 scrut-0.450
 ingred-0.442
ships-0.436
Token comments
Token ID3651
Feature activation-1.95e+00

Pos logit contributions
 Nice+1.022
quiet+0.952
zeb+0.946
isexual+0.908
+0.887
Neg logit contributions
 welf-1.259
 weap-1.163
 scrut-1.161
ships-1.141
 ingred-1.133
Token.""
Token ID32203
Feature activation-4.13e-01

Pos logit contributions
 Nice+1.245
quiet+1.178
zeb+1.160
isexual+1.112
+1.084
Neg logit contributions
 welf-1.702
 weap-1.589
 scrut-1.574
 ingred-1.543
ships-1.527
TokenOh
Token ID5812
Feature activation-2.32e-01

Pos logit contributions
 Nice+0.315
quiet+0.299
zeb+0.295
isexual+0.286
+0.280
Neg logit contributions
 welf-0.314
 weap-0.290
 scrut-0.288
 ingred-0.284
 unden-0.274
Token honey
Token ID12498
Feature activation-1.79e+00

Pos logit contributions
 Nice+0.396
quiet+0.373
zeb+0.369
isexual+0.356
+0.347
Neg logit contributions
 welf-0.491
 weap-0.458
 scrut-0.454
 ingred-0.446
ships-0.442
Tokencomb
Token ID24011
Feature activation-1.71e+00

Pos logit contributions
 Nice+1.080
quiet+1.025
zeb+1.011
isexual+0.962
+0.938
Neg logit contributions
 welf-1.609
 weap-1.507
 scrut-1.498
 ingred-1.471
ships-1.442
Token to
Token ID284
Feature activation-3.93e-01

Pos logit contributions
 Nice+1.143
quiet+1.071
zeb+1.059
isexual+1.024
+1.004
Neg logit contributions
 welf-1.425
 weap-1.334
 scrut-1.313
 ingred-1.296
ships-1.282
Token mimic
Token ID26332
Feature activation-1.49e+00

Pos logit contributions
 Nice+0.265
quiet+0.250
zeb+0.246
isexual+0.240
+0.234
Neg logit contributions
 welf-0.330
 weap-0.308
 scrut-0.303
 ingred-0.298
ships-0.293
Token the
Token ID262
Feature activation-1.85e-01

Pos logit contributions
 Nice+0.988
quiet+0.924
zeb+0.914
isexual+0.884
+0.866
Neg logit contributions
 welf-1.260
 weap-1.179
 scrut-1.166
 ingred-1.145
ships-1.135
Token compound
Token ID13061
Feature activation-4.45e+00

Pos logit contributions
 Nice+0.133
quiet+0.125
zeb+0.124
isexual+0.120
+0.118
Neg logit contributions
 welf-0.145
 weap-0.136
 scrut-0.134
 ingred-0.131
ships-0.130
Token eye
Token ID4151
Feature activation+1.33e+00

Pos logit contributions
 Nice+3.035
quiet+2.762
zeb+2.719
+2.649
isexual+2.638
Neg logit contributions
 welf-3.655
 weap-3.400
 scrut-3.353
CLASSIFIED-3.277
ships-3.269
Token of
Token ID286
Feature activation+3.22e-02

Pos logit contributions
 welf+1.004
 weap+0.934
 scrut+0.921
 ingred+0.900
ships+0.884
Neg logit contributions
 Nice-0.999
quiet-0.954
zeb-0.948
isexual-0.916
-0.896
Token a
Token ID257
Feature activation-6.86e-02

Pos logit contributions
 welf+0.026
 weap+0.024
 scrut+0.024
 ingred+0.024
ships+0.023
Neg logit contributions
 Nice-0.023
quiet-0.021
zeb-0.021
isexual-0.020
-0.020
Token fly
Token ID6129
Feature activation+6.26e-01

Pos logit contributions
 Nice+0.045
quiet+0.042
zeb+0.042
isexual+0.041
+0.039
Neg logit contributions
 welf-0.058
 weap-0.055
 scrut-0.054
 ingred-0.053
ships-0.053
Token.
Token ID13
Feature activation-3.39e-01

Pos logit contributions
 welf+0.484
 weap+0.450
 scrut+0.446
 ingred+0.437
ships+0.428
Neg logit contributions
 Nice-0.458
quiet-0.438
zeb-0.434
isexual-0.421
-0.410
Token since
Token ID1201
Feature activation-1.70e+00

Pos logit contributions
 Nice+1.154
quiet+1.098
zeb+1.077
isexual+1.028
+1.009
Neg logit contributions
 welf-1.538
 weap-1.425
 scrut-1.424
 ingred-1.404
ships-1.370
Token March
Token ID2805
Feature activation+7.89e-01

Pos logit contributions
 Nice+0.782
quiet+0.713
zeb+0.677
isexual+0.639
+0.628
Neg logit contributions
 welf-1.796
 weap-1.696
 scrut-1.681
 ingred-1.674
ships-1.645
Token 2009
Token ID3717
Feature activation+4.76e-01

Pos logit contributions
 welf+0.646
 weap+0.602
 scrut+0.596
 ingred+0.586
ships+0.574
Neg logit contributions
 Nice-0.546
quiet-0.520
zeb-0.512
isexual-0.494
-0.484
Token in
Token ID287
Feature activation+2.59e-01

Pos logit contributions
 welf+0.363
 weap+0.337
 scrut+0.334
 ingred+0.326
ships+0.321
Neg logit contributions
 Nice-0.354
quiet-0.339
zeb-0.336
isexual-0.326
-0.318
Token a
Token ID257
Feature activation-1.92e-01

Pos logit contributions
 welf+0.212
 weap+0.199
 scrut+0.195
 ingred+0.194
ships+0.190
Neg logit contributions
 Nice-0.181
quiet-0.171
zeb-0.167
isexual-0.162
-0.159
Token bid
Token ID8406
Feature activation-4.43e+00

Pos logit contributions
 Nice+0.094
quiet+0.087
zeb+0.085
isexual+0.081
+0.078
Neg logit contributions
 welf-0.196
 weap-0.186
 scrut-0.184
 ingred-0.182
ships-0.180
Token to
Token ID284
Feature activation-2.31e-01

Pos logit contributions
 Nice+2.154
quiet+2.045
zeb+1.975
isexual+1.874
+1.821
Neg logit contributions
 welf-4.454
 weap-4.217
 scrut-4.166
 ingred-4.122
 unden-4.044
Token help
Token ID1037
Feature activation-1.31e+00

Pos logit contributions
 Nice+0.153
quiet+0.146
zeb+0.143
isexual+0.138
+0.135
Neg logit contributions
 welf-0.196
 weap-0.183
 scrut-0.181
 ingred-0.178
ships-0.176
Token economic
Token ID3034
Feature activation+1.65e-01

Pos logit contributions
 Nice+0.870
quiet+0.828
zeb+0.811
isexual+0.786
+0.769
Neg logit contributions
 welf-1.105
 weap-1.035
 scrut-1.028
 ingred-1.006
ships-0.991
Token recovery
Token ID7628
Feature activation-6.47e-01

Pos logit contributions
 welf+0.136
 weap+0.128
 scrut+0.127
 ingred+0.124
ships+0.122
Neg logit contributions
 Nice-0.111
quiet-0.106
zeb-0.105
isexual-0.101
-0.099
Token.
Token ID13
Feature activation+1.61e-02

Pos logit contributions
 Nice+0.472
quiet+0.452
zeb+0.445
isexual+0.431
+0.422
Neg logit contributions
 welf-0.503
 weap-0.467
 scrut-0.463
 ingred-0.454
ships-0.444
Token in
Token ID287
Feature activation+1.81e-02

Pos logit contributions
 welf+0.078
 weap+0.072
 scrut+0.072
 ingred+0.070
ships+0.069
Neg logit contributions
 Nice-0.065
quiet-0.061
zeb-0.061
isexual-0.058
-0.058
Token turn
Token ID1210
Feature activation-1.88e+00

Pos logit contributions
 welf+0.016
 weap+0.015
 scrut+0.015
 ingred+0.015
ships+0.015
Neg logit contributions
 Nice-0.011
quiet-0.010
zeb-0.010
isexual-0.010
-0.009
Token results
Token ID2482
Feature activation-2.04e+00

Pos logit contributions
 Nice+1.359
quiet+1.289
zeb+1.281
isexual+1.235
+1.224
Neg logit contributions
 welf-1.475
 weap-1.365
 scrut-1.351
 ingred-1.330
 unden-1.290
Token in
Token ID287
Feature activation-4.11e-01

Pos logit contributions
 Nice+1.136
quiet+1.070
zeb+1.057
isexual+1.013
+0.983
Neg logit contributions
 welf-1.929
 weap-1.817
 scrut-1.805
 ingred-1.768
ships-1.744
Token the
Token ID262
Feature activation-6.11e-01

Pos logit contributions
 Nice+0.272
quiet+0.256
zeb+0.252
isexual+0.243
+0.239
Neg logit contributions
 welf-0.349
 weap-0.327
 scrut-0.325
 ingred-0.318
ships-0.312
Token dil
Token ID11844
Feature activation-4.41e+00

Pos logit contributions
 Nice+0.460
quiet+0.435
zeb+0.431
isexual+0.417
+0.410
Neg logit contributions
 welf-0.463
 weap-0.432
 scrut-0.427
 ingred-0.417
ships-0.408
Tokenution
Token ID1009
Feature activation-2.10e+00

Pos logit contributions
 Nice+2.447
quiet+2.354
zeb+2.313
isexual+2.215
igue+2.164
Neg logit contributions
 welf-4.175
 weap-3.955
 scrut-3.871
 ingred-3.850
 unden-3.762
Token of
Token ID286
Feature activation-5.44e-02

Pos logit contributions
 Nice+1.489
quiet+1.415
zeb+1.401
isexual+1.351
+1.329
Neg logit contributions
 welf-1.684
 weap-1.570
 scrut-1.555
 ingred-1.516
ships-1.480
Token talent
Token ID7401
Feature activation-6.16e-01

Pos logit contributions
 Nice+0.035
quiet+0.033
zeb+0.032
isexual+0.031
+0.030
Neg logit contributions
 welf-0.047
 weap-0.044
 scrut-0.044
 ingred-0.043
ships-0.042
Token that
Token ID326
Feature activation-5.14e-01

Pos logit contributions
 Nice+0.406
quiet+0.381
zeb+0.377
isexual+0.360
+0.356
Neg logit contributions
 welf-0.527
 weap-0.493
 scrut-0.489
 ingred-0.478
ships-0.468
Token the
Token ID262
Feature activation-2.49e-01

Pos logit contributions
 Nice+0.350
quiet+0.331
zeb+0.326
isexual+0.314
+0.312
Neg logit contributions
 welf-0.425
 weap-0.397
 scrut-0.394
 ingred-0.385
ships-0.378
Token passenger
Token ID11849
Feature activation+5.27e-01

Pos logit contributions
 Nice+0.106
quiet+0.099
zeb+0.097
isexual+0.094
+0.091
Neg logit contributions
 welf-0.132
 weap-0.123
 scrut-0.123
 ingred-0.121
ships-0.118
Token planes
Token ID13016
Feature activation+1.83e-01

Pos logit contributions
 welf+0.401
 weap+0.372
 scrut+0.371
 ingred+0.362
ships+0.353
Neg logit contributions
 Nice-0.393
quiet-0.375
zeb-0.371
isexual-0.359
-0.350
Token.
Token ID13
Feature activation-1.49e-01

Pos logit contributions
 welf+0.150
 weap+0.140
 scrut+0.139
 ingred+0.136
ships+0.133
Neg logit contributions
 Nice-0.126
quiet-0.120
zeb-0.118
isexual-0.114
-0.111
Token<|endoftext|>
Token ID50256
Feature activation+7.86e-01

Pos logit contributions
 Nice+0.100
quiet+0.094
zeb+0.093
isexual+0.089
+0.087
Neg logit contributions
 welf-0.126
 scrut-0.118
 weap-0.118
 ingred-0.116
 unden-0.112
TokenAn
Token ID2025
Feature activation+3.30e-01

Pos logit contributions
 welf+0.589
 weap+0.546
 scrut+0.541
 ingred+0.528
ships+0.516
Neg logit contributions
 Nice-0.595
quiet-0.572
zeb-0.566
isexual-0.550
-0.537
Token amateur
Token ID18585
Feature activation-4.37e+00

Pos logit contributions
 welf+0.278
 weap+0.260
 scrut+0.258
 ingred+0.252
ships+0.248
Neg logit contributions
 Nice-0.219
quiet-0.209
zeb-0.206
isexual-0.200
-0.194
Token football
Token ID4346
Feature activation+5.80e-01

Pos logit contributions
 Nice+2.955
quiet+2.719
zeb+2.692
isexual+2.606
+2.538
Neg logit contributions
 welf-3.577
 weap-3.349
 scrut-3.304
 ingred-3.284
ships-3.273
Token match
Token ID2872
Feature activation-1.87e+00

Pos logit contributions
 welf+0.474
 weap+0.443
 scrut+0.439
 ingred+0.430
ships+0.423
Neg logit contributions
 Nice-0.399
quiet-0.380
zeb-0.377
isexual-0.364
-0.355
Token in
Token ID287
Feature activation-5.54e-01

Pos logit contributions
 Nice+1.337
quiet+1.276
zeb+1.270
isexual+1.220
+1.197
Neg logit contributions
 welf-1.490
 weap-1.380
 scrut-1.357
 ingred-1.343
 unden-1.307
Token Brazil
Token ID7595
Feature activation-7.76e-01

Pos logit contributions
 Nice+0.356
quiet+0.332
zeb+0.328
isexual+0.317
+0.309
Neg logit contributions
 welf-0.483
 weap-0.453
 scrut-0.448
 ingred-0.441
ships-0.435
Token turned
Token ID2900
Feature activation-1.14e+00

Pos logit contributions
 Nice+0.532
quiet+0.503
zeb+0.499
isexual+0.480
+0.472
Neg logit contributions
 welf-0.643
 weap-0.599
 scrut-0.591
 ingred-0.582
ships-0.570
Token acquired
Token ID9477
Feature activation+6.46e-01

Pos logit contributions
 Nice+0.296
zeb+0.278
quiet+0.275
isexual+0.260
+0.258
Neg logit contributions
 welf-0.359
 weap-0.334
 scrut-0.329
 ingred-0.327
ships-0.323
Token by
Token ID416
Feature activation-4.18e-01

Pos logit contributions
 welf+0.548
 weap+0.511
 scrut+0.507
 ingred+0.499
ships+0.491
Neg logit contributions
 Nice-0.427
quiet-0.405
zeb-0.403
isexual-0.385
-0.377
Token reading
Token ID3555
Feature activation-1.13e+00

Pos logit contributions
 Nice+0.277
zeb+0.258
quiet+0.257
isexual+0.244
+0.240
Neg logit contributions
 welf-0.354
 weap-0.331
 scrut-0.327
 ingred-0.324
ships-0.321
Token from
Token ID422
Feature activation-4.67e-01

Pos logit contributions
 Nice+0.701
zeb+0.655
quiet+0.654
isexual+0.620
+0.608
Neg logit contributions
 welf-0.999
 weap-0.934
 scrut-0.924
 ingred-0.914
ships-0.902
Token an
Token ID281
Feature activation-6.29e-01

Pos logit contributions
 Nice+0.310
quiet+0.291
zeb+0.290
isexual+0.277
+0.272
Neg logit contributions
 welf-0.394
 weap-0.368
 scrut-0.365
 ingred-0.360
ships-0.354
Token Atomic
Token ID28976
Feature activation-4.36e+00

Pos logit contributions
 Nice+0.419
quiet+0.395
zeb+0.393
isexual+0.377
+0.370
Neg logit contributions
 welf-0.529
 weap-0.493
 scrut-0.489
 ingred-0.480
ships-0.476
Token,
Token ID837
Feature activation-7.48e-01

Pos logit contributions
 Nice+3.052
zeb+2.872
quiet+2.846
+2.723
isexual+2.722
Neg logit contributions
 welf-3.465
 weap-3.217
 ingred-3.189
 scrut-3.177
ships-3.105
Token as
Token ID355
Feature activation+3.76e-02

Pos logit contributions
 Nice+0.479
quiet+0.445
zeb+0.442
isexual+0.421
+0.413
Neg logit contributions
 welf-0.654
 weap-0.610
 scrut-0.605
 ingred-0.599
ships-0.589
Token we
Token ID356
Feature activation-1.28e+00

Pos logit contributions
 welf+0.030
 weap+0.028
 scrut+0.027
 ingred+0.027
ships+0.027
Neg logit contributions
 Nice-0.027
quiet-0.026
zeb-0.025
isexual-0.024
-0.024
Token
Token ID447
Feature activation-1.83e-01

Pos logit contributions
 Nice+0.880
quiet+0.841
zeb+0.827
+0.798
isexual+0.790
Neg logit contributions
 welf-1.048
 weap-0.981
 ingred-0.962
 scrut-0.958
CLASSIFIED-0.937
Token
Token ID247
Feature activation+2.05e-01

Pos logit contributions
 Nice+0.116
quiet+0.111
zeb+0.109
+0.105
isexual+0.105
Neg logit contributions
 welf-0.162
 weap-0.150
 scrut-0.149
 ingred-0.145
 unden-0.143
Tokenrather
Token ID34330
Feature activation+2.49e-01

Pos logit contributions
 Nice+0.280
quiet+0.273
zeb+0.268
isexual+0.259
+0.252
Neg logit contributions
 welf-0.327
 weap-0.306
 scrut-0.302
 ingred-0.297
ships-0.288
Token-
Token ID12
Feature activation-5.79e-01

Pos logit contributions
 welf+0.209
 scrut+0.193
 weap+0.192
 ingred+0.191
 unden+0.188
Neg logit contributions
 Nice-0.174
quiet-0.171
zeb-0.166
isexual-0.159
-0.157
Tokenthan
Token ID14813
Feature activation-8.70e-01

Pos logit contributions
quiet+0.374
 Nice+0.372
zeb+0.358
isexual+0.347
+0.338
Neg logit contributions
 welf-0.501
 weap-0.474
 scrut-0.464
 ingred-0.459
 unden-0.448
Token-
Token ID12
Feature activation-7.07e-01

Pos logit contributions
 Nice+0.583
quiet+0.571
zeb+0.550
isexual+0.532
+0.525
Neg logit contributions
 welf-0.753
 weap-0.697
 ingred-0.697
 scrut-0.696
 unden-0.692
Tokenbre
Token ID4679
Feature activation+1.17e+00

Pos logit contributions
quiet+0.463
 Nice+0.455
zeb+0.439
isexual+0.425
+0.416
Neg logit contributions
 welf-0.619
 weap-0.583
 scrut-0.572
 ingred-0.567
 unden-0.558
Tokenxit
Token ID10198
Feature activation-4.36e+00

Pos logit contributions
 welf+0.812
 weap+0.747
 scrut+0.744
ships+0.724
 ingred+0.719
Neg logit contributions
 Nice-0.928
zeb-0.882
quiet-0.881
isexual-0.858
-0.831
Token-
Token ID12
Feature activation-4.80e-01

Pos logit contributions
 Nice+2.704
quiet+2.630
zeb+2.544
isexual+2.424
+2.416
Neg logit contributions
 welf-4.097
 unden-3.828
 scrut-3.771
 ingred-3.765
 weap-3.737
Tokenis
Token ID271
Feature activation-2.40e-01

Pos logit contributions
 Nice+0.358
quiet+0.348
zeb+0.341
isexual+0.332
+0.324
Neg logit contributions
 welf-0.367
 weap-0.340
 scrut-0.335
 ingred-0.328
 unden-0.318
Token-
Token ID12
Feature activation-6.13e-01

Pos logit contributions
 Nice+0.167
quiet+0.163
zeb+0.160
isexual+0.153
+0.150
Neg logit contributions
 welf-0.203
 weap-0.186
 scrut-0.186
 ingred-0.185
 unden-0.182
Tokenthe
Token ID1169
Feature activation-1.01e+00

Pos logit contributions
 Nice+0.411
quiet+0.400
zeb+0.392
isexual+0.378
+0.369
Neg logit contributions
 welf-0.517
 weap-0.482
 scrut-0.477
 ingred-0.469
 unden-0.458
Token-
Token ID12
Feature activation-5.08e-01

Pos logit contributions
 Nice+0.706
quiet+0.683
zeb+0.668
isexual+0.638
+0.628
Neg logit contributions
 welf-0.847
 scrut-0.783
 weap-0.783
 ingred-0.771
 unden-0.758
Token smell
Token ID8508
Feature activation+8.04e-01

Pos logit contributions
 welf+0.307
 weap+0.284
 scrut+0.282
 ingred+0.278
ships+0.274
Neg logit contributions
 Nice-0.240
quiet-0.230
zeb-0.225
isexual-0.217
-0.213
Token the
Token ID262
Feature activation+1.59e-01

Pos logit contributions
 welf+0.683
 weap+0.638
 scrut+0.632
 ingred+0.620
ships+0.613
Neg logit contributions
 Nice-0.529
quiet-0.501
zeb-0.497
isexual-0.476
-0.465
Token scent
Token ID21212
Feature activation+1.90e+00

Pos logit contributions
 welf+0.132
 weap+0.123
 scrut+0.122
 ingred+0.119
ships+0.118
Neg logit contributions
 Nice-0.107
quiet-0.102
zeb-0.101
isexual-0.097
-0.095
Token of
Token ID286
Feature activation+2.50e-01

Pos logit contributions
 welf+1.464
 weap+1.365
 scrut+1.356
 ingred+1.323
ships+1.301
Neg logit contributions
 Nice-1.376
quiet-1.320
zeb-1.305
isexual-1.271
-1.238
Token burning
Token ID9482
Feature activation-3.63e-01

Pos logit contributions
 welf+0.210
 weap+0.196
 scrut+0.194
 ingred+0.190
ships+0.188
Neg logit contributions
 Nice-0.166
quiet-0.158
zeb-0.156
isexual-0.150
-0.147
Token flesh
Token ID11222
Feature activation-4.34e+00

Pos logit contributions
 Nice+0.224
quiet+0.211
zeb+0.209
isexual+0.200
+0.196
Neg logit contributions
 welf-0.323
 weap-0.303
 scrut-0.300
 ingred-0.294
ships-0.292
Token.
Token ID13
Feature activation+8.96e-02

Pos logit contributions
 Nice+2.859
quiet+2.728
zeb+2.686
+2.533
isexual+2.525
Neg logit contributions
 welf-3.685
 weap-3.375
 scrut-3.330
 ingred-3.284
ships-3.222
Token
Token ID447
Feature activation-4.84e-01

Pos logit contributions
 welf+0.070
 weap+0.064
 scrut+0.064
 ingred+0.063
 unden+0.061
Neg logit contributions
 Nice-0.067
quiet-0.063
zeb-0.062
isexual-0.060
-0.059
Token
Token ID251
Feature activation-5.23e-01

Pos logit contributions
 Nice+0.380
quiet+0.365
zeb+0.362
isexual+0.352
+0.344
Neg logit contributions
 welf-0.347
 weap-0.320
 scrut-0.317
 ingred-0.310
ships-0.305
Token
Token ID198
Feature activation+3.56e-02

Pos logit contributions
 Nice+0.371
quiet+0.356
zeb+0.353
isexual+0.343
+0.333
Neg logit contributions
 welf-0.412
 weap-0.384
 scrut-0.380
 ingred-0.372
ships-0.366
Token
Token ID198
Feature activation+1.58e-01

Pos logit contributions
 welf+0.031
 weap+0.029
 scrut+0.029
 ingred+0.029
 unden+0.028
Neg logit contributions
 Nice-0.024
quiet-0.022
zeb-0.022
isexual-0.021
-0.021
Token Audio
Token ID13491
Feature activation+1.34e+00

Pos logit contributions
 welf+0.510
 weap+0.477
 scrut+0.473
 ingred+0.464
ships+0.457
Neg logit contributions
 Nice-0.397
quiet-0.379
zeb-0.374
isexual-0.362
-0.352
Token To
Token ID1675
Feature activation-1.33e-01

Pos logit contributions
 welf+1.060
 weap+0.987
 scrut+0.977
 ingred+0.957
ships+0.942
Neg logit contributions
 Nice-0.948
quiet-0.910
zeb-0.901
isexual-0.872
-0.851
Token O
Token ID440
Feature activation+6.37e-01

Pos logit contributions
 Nice+0.088
quiet+0.084
zeb+0.083
isexual+0.081
+0.078
Neg logit contributions
 welf-0.111
 weap-0.104
 scrut-0.103
 ingred-0.101
ships-0.099
Token&
Token ID5
Feature activation-1.60e+00

Pos logit contributions
 welf+0.521
 weap+0.486
 scrut+0.482
 ingred+0.472
ships+0.465
Neg logit contributions
 Nice-0.436
quiet-0.418
zeb-0.413
isexual-0.399
-0.389
TokenA
Token ID32
Feature activation+5.10e-01

Pos logit contributions
 Nice+1.123
quiet+1.048
zeb+1.042
isexual+1.002
+0.991
Neg logit contributions
 welf-1.337
 ingred-1.237
 weap-1.237
 scrut-1.237
 unden-1.204
Token Bits
Token ID44733
Feature activation-4.34e+00

Pos logit contributions
 welf+0.395
 weap+0.368
 scrut+0.364
 ingred+0.356
ships+0.351
Neg logit contributions
 Nice-0.368
quiet-0.354
zeb-0.351
isexual-0.340
-0.332
Token 2008
Token ID3648
Feature activation+1.22e+00

Pos logit contributions
 Nice+3.033
quiet+2.861
zeb+2.857
isexual+2.738
+2.659
Neg logit contributions
 welf-3.511
 weap-3.277
 scrut-3.255
 ingred-3.170
ships-3.107
Token01
Token ID486
Feature activation-1.67e-01

Pos logit contributions
 welf+0.575
 weap+0.507
 scrut+0.502
 ingred+0.482
ships+0.462
Neg logit contributions
 Nice-1.271
quiet-1.230
zeb-1.221
isexual-1.195
-1.178
Token11
Token ID1157
Feature activation+1.08e+00

Pos logit contributions
 Nice+0.160
quiet+0.155
zeb+0.155
isexual+0.151
+0.148
Neg logit contributions
 welf-0.090
 weap-0.081
 scrut-0.080
 ingred-0.077
ships-0.076
Token O
Token ID440
Feature activation+1.06e+00

Pos logit contributions
 welf+0.852
 weap+0.786
 scrut+0.781
 ingred+0.770
 unden+0.748
Neg logit contributions
 Nice-0.813
quiet-0.766
zeb-0.755
isexual-0.733
-0.715
Token&
Token ID5
Feature activation-1.44e+00

Pos logit contributions
 welf+0.910
 weap+0.848
 scrut+0.844
 ingred+0.831
 unden+0.813
Neg logit contributions
 Nice-0.694
quiet-0.660
zeb-0.653
isexual-0.631
-0.614
TokenNeil
Token ID29354
Feature activation-1.09e-01

Pos logit contributions
 welf+0.249
 weap+0.230
 scrut+0.228
 ingred+0.223
 unden+0.216
Neg logit contributions
 Nice-0.245
quiet-0.236
zeb-0.233
isexual-0.225
-0.221
Token Thomson
Token ID32425
Feature activation-1.63e+00

Pos logit contributions
 Nice+0.070
quiet+0.066
zeb+0.066
isexual+0.063
+0.061
Neg logit contributions
 welf-0.095
 weap-0.089
 scrut-0.088
 ingred-0.087
ships-0.085
Token -
Token ID532
Feature activation-9.47e-01

Pos logit contributions
 Nice+1.091
quiet+1.031
zeb+1.023
isexual+0.980
+0.959
Neg logit contributions
 welf-1.386
 weap-1.289
 scrut-1.279
 ingred-1.255
ships-1.225
Token A
Token ID317
Feature activation+1.29e+00

Pos logit contributions
 Nice+0.638
quiet+0.602
zeb+0.596
isexual+0.575
+0.560
Neg logit contributions
 welf-0.796
 weap-0.741
 scrut-0.736
 ingred-0.723
ships-0.708
Token Det
Token ID4614
Feature activation-1.21e+00

Pos logit contributions
 welf+1.094
 weap+1.026
 scrut+1.017
 ingred+0.994
ships+0.982
Neg logit contributions
 Nice-0.834
quiet-0.799
zeb-0.790
isexual-0.765
-0.743
Tokenailed
Token ID6255
Feature activation+4.01e+00

Pos logit contributions
 Nice+0.892
quiet+0.860
zeb+0.846
isexual+0.825
+0.803
Neg logit contributions
 welf-0.942
 weap-0.874
 scrut-0.865
 ingred-0.847
ships-0.826
Token Review
Token ID6602
Feature activation+4.89e-01

Pos logit contributions
 welf+3.122
 weap+2.927
 scrut+2.900
 ingred+2.803
ships+2.782
Neg logit contributions
 Nice-2.748
quiet-2.698
zeb-2.678
isexual-2.597
-2.502
Token
Token ID198
Feature activation+8.20e-01

Pos logit contributions
 welf+0.385
 weap+0.359
 scrut+0.356
 ingred+0.348
ships+0.342
Neg logit contributions
 Nice-0.350
quiet-0.334
zeb-0.331
isexual-0.321
-0.313
Token
Token ID198
Feature activation+7.00e-01

Pos logit contributions
 welf+0.696
 weap+0.645
 scrut+0.643
 ingred+0.636
 unden+0.622
Neg logit contributions
 Nice-0.558
quiet-0.530
zeb-0.524
isexual-0.503
-0.493
Tokenhttp
Token ID4023
Feature activation-2.77e-02

Pos logit contributions
 welf+0.504
 weap+0.464
 scrut+0.460
 ingred+0.449
ships+0.437
Neg logit contributions
 Nice-0.553
quiet-0.533
zeb-0.528
isexual-0.511
-0.501
Token://
Token ID1378
Feature activation-6.45e-01

Pos logit contributions
 Nice+0.024
quiet+0.023
zeb+0.023
isexual+0.022
+0.022
Neg logit contributions
 welf-0.019
 scrut-0.017
 weap-0.017
 ingred-0.017
 unden-0.017
Token over
Token ID625
Feature activation+5.61e-01

Pos logit contributions
 welf+0.504
 weap+0.469
 scrut+0.463
 ingred+0.458
ships+0.445
Neg logit contributions
 Nice-0.451
quiet-0.429
zeb-0.423
isexual-0.405
-0.399
Token
Token ID851
Feature activation-4.48e-01

Pos logit contributions
 welf+0.497
 weap+0.465
 scrut+0.460
 ingred+0.454
ships+0.444
Neg logit contributions
 Nice-0.351
quiet-0.332
zeb-0.328
isexual-0.312
-0.305
Token the
Token ID262
Feature activation+3.49e-01

Pos logit contributions
 Nice+0.308
quiet+0.291
zeb+0.287
isexual+0.275
+0.269
Neg logit contributions
 welf-0.367
 weap-0.339
 scrut-0.338
 ingred-0.336
 unden-0.323
Token authority
Token ID4934
Feature activation+7.25e-01

Pos logit contributions
 welf+0.269
 weap+0.249
 scrut+0.246
 ingred+0.243
ships+0.236
Neg logit contributions
 Nice-0.258
quiet-0.244
zeb-0.241
isexual-0.232
-0.227
Token is
Token ID318
Feature activation+7.06e-01

Pos logit contributions
 welf+0.559
 weap+0.519
 scrut+0.512
 ingred+0.504
ships+0.493
Neg logit contributions
 Nice-0.533
quiet-0.510
zeb-0.505
isexual-0.487
-0.478
Token owed
Token ID21057
Feature activation+4.17e+00

Pos logit contributions
 welf+0.658
 weap+0.619
 scrut+0.615
 ingred+0.604
ships+0.595
Neg logit contributions
 Nice-0.404
quiet-0.382
zeb-0.377
isexual-0.362
-0.350
Token more
Token ID517
Feature activation+7.40e-02

Pos logit contributions
 welf+2.971
 weap+2.744
 scrut+2.718
 ingred+2.647
ships+2.603
Neg logit contributions
 Nice-3.288
quiet-3.161
zeb-3.134
isexual-3.048
-2.976
Token than
Token ID621
Feature activation-1.17e+00

Pos logit contributions
 welf+0.064
 weap+0.059
 scrut+0.059
 ingred+0.058
ships+0.057
Neg logit contributions
 Nice-0.048
quiet-0.045
zeb-0.045
isexual-0.042
-0.042
Token $
Token ID720
Feature activation-2.92e-01

Pos logit contributions
 Nice+1.109
quiet+1.048
zeb+1.037
isexual+1.004
+0.996
Neg logit contributions
 welf-0.670
 weap-0.602
 scrut-0.593
 ingred-0.586
CLASSIFIED-0.566
Token251
Token ID28072
Feature activation-1.42e-01

Pos logit contributions
 Nice+0.237
quiet+0.228
zeb+0.225
isexual+0.218
+0.215
Neg logit contributions
 welf-0.210
 scrut-0.192
 weap-0.192
 ingred-0.189
 unden-0.185
Token,
Token ID11
Feature activation+3.28e-01

Pos logit contributions
 Nice+0.095
quiet+0.091
zeb+0.090
isexual+0.087
+0.084
Neg logit contributions
 welf-0.118
 weap-0.111
 scrut-0.110
 ingred-0.107
ships-0.106
Token national
Token ID2260
Feature activation-1.59e+00

Pos logit contributions
 welf+0.307
 weap+0.289
 scrut+0.285
 ingred+0.281
ships+0.275
Neg logit contributions
 Nice-0.246
quiet-0.233
zeb-0.228
isexual-0.220
-0.216
Token cultures
Token ID13817
Feature activation+1.33e+00

Pos logit contributions
 Nice+1.179
quiet+1.113
zeb+1.098
isexual+1.068
+1.043
Neg logit contributions
 welf-1.212
 weap-1.137
 scrut-1.124
 ingred-1.107
ships-1.072
Token within
Token ID1626
Feature activation+1.43e-01

Pos logit contributions
 welf+1.081
 weap+1.008
 scrut+0.999
 ingred+0.978
ships+0.963
Neg logit contributions
 Nice-0.918
quiet-0.876
zeb-0.867
isexual-0.839
-0.818
Token the
Token ID262
Feature activation-5.72e-02

Pos logit contributions
 welf+0.122
 weap+0.115
 scrut+0.114
 ingred+0.112
ships+0.110
Neg logit contributions
 Nice-0.092
quiet-0.088
zeb-0.086
isexual-0.084
-0.082
Token British
Token ID3517
Feature activation-4.89e-01

Pos logit contributions
 Nice+0.035
quiet+0.033
zeb+0.033
isexual+0.032
+0.031
Neg logit contributions
 welf-0.051
 weap-0.048
 scrut-0.047
 ingred-0.046
ships-0.046
Token Isles
Token ID36217
Feature activation+3.64e+00

Pos logit contributions
 Nice+0.370
quiet+0.352
zeb+0.347
isexual+0.338
+0.331
Neg logit contributions
 welf-0.365
 weap-0.343
 scrut-0.338
 ingred-0.334
ships-0.323
Token can
Token ID460
Feature activation+4.01e-01

Pos logit contributions
 welf+2.934
 weap+2.733
 scrut+2.719
 ingred+2.638
ships+2.625
Neg logit contributions
 Nice-2.527
quiet-2.412
zeb-2.396
isexual-2.321
-2.244
Token claim
Token ID1624
Feature activation+1.76e-01

Pos logit contributions
 welf+0.310
 weap+0.288
 scrut+0.285
 ingred+0.280
ships+0.274
Neg logit contributions
 Nice-0.292
quiet-0.281
zeb-0.277
isexual-0.269
-0.263
Token to
Token ID284
Feature activation+5.98e-01

Pos logit contributions
 welf+0.149
 weap+0.140
 scrut+0.139
 ingred+0.137
ships+0.134
Neg logit contributions
 Nice-0.115
quiet-0.108
zeb-0.107
isexual-0.103
-0.102
Token be
Token ID307
Feature activation+1.06e+00

Pos logit contributions
 welf+0.450
 weap+0.419
 scrut+0.415
 ingred+0.407
ships+0.399
Neg logit contributions
 Nice-0.449
quiet-0.429
zeb-0.424
isexual-0.413
-0.405
Token literary
Token ID16716
Feature activation+2.68e-01

Pos logit contributions
 welf+0.896
 weap+0.838
 scrut+0.831
 ingred+0.814
ships+0.801
Neg logit contributions
 Nice-0.702
quiet-0.669
zeb-0.662
isexual-0.639
-0.622
Token Natural
Token ID12068
Feature activation-1.33e+00

Pos logit contributions
 Nice+0.051
quiet+0.048
zeb+0.047
isexual+0.046
+0.044
Neg logit contributions
 welf-0.071
 weap-0.067
 scrut-0.066
 ingred-0.065
ships-0.064
Token Markets
Token ID30251
Feature activation+1.71e-01

Pos logit contributions
 Nice+1.028
quiet+0.986
zeb+0.978
isexual+0.950
+0.928
Neg logit contributions
 welf-0.970
 weap-0.897
 scrut-0.889
 ingred-0.867
ships-0.852
Token will
Token ID481
Feature activation+9.53e-01

Pos logit contributions
 welf+0.141
 weap+0.132
 scrut+0.130
 ingred+0.128
ships+0.126
Neg logit contributions
 Nice-0.117
quiet-0.111
zeb-0.109
isexual-0.106
-0.103
Token open
Token ID1280
Feature activation+7.25e-01

Pos logit contributions
 welf+0.843
 weap+0.788
 scrut+0.783
 ingred+0.766
ships+0.756
Neg logit contributions
 Nice-0.596
quiet-0.565
zeb-0.556
isexual-0.538
-0.522
Token new
Token ID649
Feature activation+2.36e+00

Pos logit contributions
 welf+0.540
 weap+0.499
 scrut+0.494
 ingred+0.483
ships+0.474
Neg logit contributions
 Nice-0.554
quiet-0.530
zeb-0.524
isexual-0.509
-0.497
Token store
Token ID3650
Feature activation+3.55e+00

Pos logit contributions
 welf+1.413
 weap+1.286
 scrut+1.271
 ingred+1.234
ships+1.202
Neg logit contributions
 Nice-2.117
quiet-2.056
zeb-2.048
isexual-1.997
-1.955
Token at
Token ID379
Feature activation+1.53e+00

Pos logit contributions
 welf+2.239
 weap+2.071
 scrut+2.049
 ingred+2.013
ships+1.959
Neg logit contributions
 Nice-2.988
quiet-2.907
zeb-2.903
isexual-2.831
-2.765
Token Five
Token ID10579
Feature activation+3.52e-01

Pos logit contributions
 welf+1.271
 weap+1.186
 scrut+1.179
 ingred+1.151
ships+1.136
Neg logit contributions
 Nice-1.008
quiet-0.973
zeb-0.966
isexual-0.930
-0.905
Token Corn
Token ID11424
Feature activation+9.35e-01

Pos logit contributions
 welf+0.242
 weap+0.220
 scrut+0.220
 ingred+0.217
 unden+0.209
Neg logit contributions
 Nice-0.308
quiet-0.287
zeb-0.285
isexual-0.276
-0.272
Tokeners
Token ID364
Feature activation+1.69e+00

Pos logit contributions
 welf+0.726
 weap+0.673
 scrut+0.669
 ingred+0.653
ships+0.635
Neg logit contributions
 Nice-0.688
quiet-0.658
zeb-0.652
isexual-0.631
-0.617
Token in
Token ID287
Feature activation+7.61e-01

Pos logit contributions
 welf+1.472
 weap+1.398
 scrut+1.375
 ingred+1.372
ships+1.344
Neg logit contributions
 Nice-1.019
zeb-0.980
quiet-0.979
isexual-0.949
-0.924
Token Canadian
Token ID5398
Feature activation+1.10e+00

Pos logit contributions
 welf+0.159
 weap+0.152
 scrut+0.149
 ingred+0.147
ships+0.145
Neg logit contributions
 Nice-0.090
quiet-0.083
zeb-0.081
isexual-0.078
-0.076
Token public
Token ID1171
Feature activation+5.49e-01

Pos logit contributions
 welf+0.950
 weap+0.896
 scrut+0.880
 ingred+0.868
ships+0.858
Neg logit contributions
 Nice-0.713
quiet-0.674
zeb-0.659
isexual-0.643
-0.626
Token identify
Token ID5911
Feature activation+1.17e+00

Pos logit contributions
 welf+0.441
 weap+0.413
 scrut+0.406
 ingred+0.402
ships+0.391
Neg logit contributions
 Nice-0.386
quiet-0.370
zeb-0.364
isexual-0.352
-0.344
Token with
Token ID351
Feature activation+7.10e-01

Pos logit contributions
 welf+1.053
 weap+0.990
 scrut+0.982
 ingred+0.964
ships+0.950
Neg logit contributions
 Nice-0.707
quiet-0.669
zeb-0.661
isexual-0.637
-0.618
Token enough
Token ID1576
Feature activation+1.03e+00

Pos logit contributions
 welf+0.611
 weap+0.581
 scrut+0.572
 ingred+0.566
ships+0.551
Neg logit contributions
 Nice-0.459
quiet-0.428
zeb-0.422
isexual-0.410
-0.401
Token faces
Token ID6698
Feature activation+4.05e+00

Pos logit contributions
 welf+0.834
 weap+0.791
 scrut+0.776
 ingred+0.764
ships+0.746
Neg logit contributions
 Nice-0.709
quiet-0.669
zeb-0.660
isexual-0.646
-0.630
Token around
Token ID1088
Feature activation-1.25e+00

Pos logit contributions
 welf+3.564
 scrut+3.341
 weap+3.341
 ingred+3.243
ships+3.235
Neg logit contributions
 Nice-2.468
zeb-2.360
quiet-2.357
isexual-2.256
-2.164
Token the
Token ID262
Feature activation+1.35e-01

Pos logit contributions
 Nice+0.778
quiet+0.727
zeb+0.720
isexual+0.692
+0.677
Neg logit contributions
 welf-1.112
 weap-1.046
 scrut-1.034
 ingred-1.015
ships-0.997
Token table
Token ID3084
Feature activation-7.61e-01

Pos logit contributions
 welf+0.135
 weap+0.128
 scrut+0.126
 ingred+0.124
ships+0.123
Neg logit contributions
 Nice-0.069
quiet-0.064
zeb-0.063
isexual-0.060
-0.059
Token.
Token ID13
Feature activation+1.88e-01

Pos logit contributions
 Nice+0.438
quiet+0.415
zeb+0.405
isexual+0.392
+0.383
Neg logit contributions
 welf-0.708
 weap-0.667
 scrut-0.658
 ingred-0.651
ships-0.635
Token If
Token ID1002
Feature activation+2.02e+00

Pos logit contributions
 welf+0.158
 weap+0.148
 scrut+0.147
 ingred+0.146
 unden+0.141
Neg logit contributions
 Nice-0.129
quiet-0.120
zeb-0.119
isexual-0.114
-0.114
Token office
Token ID2607
Feature activation+4.07e-01

Pos logit contributions
 Nice+1.380
quiet+1.275
zeb+1.261
isexual+1.198
+1.143
Neg logit contributions
 welf-2.607
 scrut-2.466
 weap-2.451
 ingred-2.404
ships-2.384
Token secretary
Token ID7705
Feature activation-3.58e-02

Pos logit contributions
 welf+0.317
 weap+0.295
 scrut+0.292
 ingred+0.285
ships+0.282
Neg logit contributions
 Nice-0.297
quiet-0.284
zeb-0.280
isexual-0.271
-0.264
Token who
Token ID508
Feature activation-6.50e-01

Pos logit contributions
 Nice+0.025
quiet+0.024
zeb+0.024
isexual+0.023
+0.022
Neg logit contributions
 welf-0.029
 weap-0.027
 scrut-0.027
 ingred-0.026
ships-0.026
Token steals
Token ID28052
Feature activation+2.09e+00

Pos logit contributions
 Nice+0.475
quiet+0.456
zeb+0.449
isexual+0.435
+0.425
Neg logit contributions
 welf-0.506
 weap-0.469
 scrut-0.465
 ingred-0.456
ships-0.445
Token $
Token ID720
Feature activation-8.54e-01

Pos logit contributions
 welf+1.696
 weap+1.582
 scrut+1.567
 ingred+1.534
ships+1.510
Neg logit contributions
 Nice-1.439
quiet-1.375
zeb-1.362
isexual-1.318
-1.284
Token40
Token ID1821
Feature activation+5.66e-01

Pos logit contributions
 Nice+0.682
quiet+0.660
zeb+0.650
isexual+0.627
+0.619
Neg logit contributions
 welf-0.617
 scrut-0.567
 weap-0.567
 ingred-0.557
 unden-0.545
Token,
Token ID11
Feature activation+1.69e-02

Pos logit contributions
 welf+0.487
 weap+0.455
 scrut+0.453
 ingred+0.443
ships+0.436
Neg logit contributions
 Nice-0.366
quiet-0.348
zeb-0.344
isexual-0.331
-0.323
Token000
Token ID830
Feature activation-1.16e-01

Pos logit contributions
 welf+0.011
 weap+0.010
 scrut+0.010
 ingred+0.010
ships+0.010
Neg logit contributions
 Nice-0.014
quiet-0.014
zeb-0.014
isexual-0.013
-0.013
Token from
Token ID422
Feature activation+4.92e-03

Pos logit contributions
 Nice+0.069
quiet+0.065
zeb+0.064
isexual+0.061
+0.060
Neg logit contributions
 welf-0.106
 weap-0.100
 scrut-0.099
 ingred-0.097
ships-0.095
Token her
Token ID607
Feature activation+7.62e-01

Pos logit contributions
 welf+0.004
 weap+0.004
 scrut+0.004
 ingred+0.004
ships+0.004
Neg logit contributions
 Nice-0.003
quiet-0.003
zeb-0.003
isexual-0.003
-0.003
Token boss
Token ID6478
Feature activation-1.33e+00

Pos logit contributions
 welf+0.669
 weap+0.627
 scrut+0.623
 ingred+0.610
ships+0.602
Neg logit contributions
 Nice-0.479
quiet-0.454
zeb-0.448
isexual-0.432
-0.420
Token registration
Token ID9352
Feature activation+1.97e+00

Pos logit contributions
 welf+0.460
 weap+0.430
 scrut+0.426
 ingred+0.419
ships+0.413
Neg logit contributions
 Nice-0.391
quiet-0.367
zeb-0.363
isexual-0.353
-0.345
Token will
Token ID481
Feature activation+7.63e-01

Pos logit contributions
 welf+1.500
 weap+1.390
 scrut+1.381
 ingred+1.346
ships+1.325
Neg logit contributions
 Nice-1.466
quiet-1.409
zeb-1.397
isexual-1.354
-1.318
Token expire
Token ID24264
Feature activation-3.59e-01

Pos logit contributions
 welf+0.558
 weap+0.514
 scrut+0.509
 ingred+0.498
ships+0.488
Neg logit contributions
 Nice-0.590
quiet-0.568
zeb-0.561
isexual-0.547
-0.534
Token,
Token ID11
Feature activation+7.13e-01

Pos logit contributions
 Nice+0.229
quiet+0.216
zeb+0.212
isexual+0.205
+0.202
Neg logit contributions
 welf-0.313
 weap-0.292
 scrut-0.289
 ingred-0.287
ships-0.281
Token and
Token ID290
Feature activation+4.37e-01

Pos logit contributions
 welf+0.600
 weap+0.561
 scrut+0.554
 ingred+0.545
ships+0.538
Neg logit contributions
 Nice-0.474
quiet-0.451
zeb-0.445
isexual-0.429
-0.422
Token the
Token ID262
Feature activation+7.86e-01

Pos logit contributions
 welf+0.357
 weap+0.335
 scrut+0.329
 ingred+0.323
ships+0.321
Neg logit contributions
 Nice-0.300
quiet-0.285
zeb-0.281
isexual-0.270
-0.267
Token date
Token ID3128
Feature activation+1.07e+00

Pos logit contributions
 welf+0.650
 weap+0.607
 scrut+0.602
 ingred+0.590
ships+0.583
Neg logit contributions
 Nice-0.533
quiet-0.505
zeb-0.500
isexual-0.483
-0.472
Token of
Token ID286
Feature activation+9.34e-01

Pos logit contributions
 welf+0.866
 weap+0.808
 scrut+0.801
 ingred+0.784
ships+0.772
Neg logit contributions
 Nice-0.742
quiet-0.708
zeb-0.701
isexual-0.678
-0.662
Token that
Token ID326
Feature activation+2.96e-01

Pos logit contributions
 welf+0.771
 weap+0.719
 scrut+0.714
 ingred+0.698
ships+0.686
Neg logit contributions
 Nice-0.634
quiet-0.606
zeb-0.600
isexual-0.581
-0.564
Token exp
Token ID1033
Feature activation+3.08e-01

Pos logit contributions
 welf+0.231
 weap+0.214
 scrut+0.212
 ingred+0.207
ships+0.205
Neg logit contributions
 Nice-0.215
quiet-0.206
zeb-0.204
isexual-0.198
-0.194
Tokeniry
Token ID9045
Feature activation+1.28e+00

Pos logit contributions
 welf+0.336
 weap+0.318
 scrut+0.316
 ingred+0.312
ships+0.306
Neg logit contributions
 Nice-0.130
quiet-0.122
zeb-0.119
isexual-0.113
-0.109
Token give
Token ID1577
Feature activation-2.16e-01

Pos logit contributions
 welf+0.496
 weap+0.463
 scrut+0.457
 ingred+0.450
ships+0.442
Neg logit contributions
 Nice-0.446
quiet-0.421
zeb-0.416
isexual-0.401
-0.390
Token back
Token ID736
Feature activation+1.88e-01

Pos logit contributions
 Nice+0.136
quiet+0.127
zeb+0.125
isexual+0.119
+0.116
Neg logit contributions
 welf-0.193
 weap-0.180
 scrut-0.179
 ingred-0.175
ships-0.172
Token to
Token ID284
Feature activation+4.26e-01

Pos logit contributions
 welf+0.172
 weap+0.161
 scrut+0.160
 ingred+0.157
ships+0.154
Neg logit contributions
 Nice-0.113
quiet-0.106
zeb-0.104
isexual-0.100
-0.097
Token them
Token ID606
Feature activation+1.81e+00

Pos logit contributions
 welf+0.375
 weap+0.352
 scrut+0.350
 ingred+0.342
ships+0.337
Neg logit contributions
 Nice-0.269
quiet-0.253
zeb-0.250
isexual-0.240
-0.233
Token and
Token ID290
Feature activation+2.36e-01

Pos logit contributions
 welf+1.498
 weap+1.397
 scrut+1.387
 ingred+1.358
ships+1.335
Neg logit contributions
 Nice-1.228
quiet-1.167
zeb-1.155
isexual-1.117
-1.087
Token use
Token ID779
Feature activation+1.14e+00

Pos logit contributions
 welf+0.200
 weap+0.188
 scrut+0.186
 ingred+0.183
ships+0.179
Neg logit contributions
 Nice-0.156
quiet-0.147
zeb-0.145
isexual-0.140
-0.136
Token that
Token ID326
Feature activation+1.21e-01

Pos logit contributions
 welf+0.983
 weap+0.920
 scrut+0.913
 ingred+0.893
ships+0.880
Neg logit contributions
 Nice-0.737
quiet-0.693
zeb-0.688
isexual-0.661
-0.644
Token to
Token ID284
Feature activation+3.03e-01

Pos logit contributions
 welf+0.096
 weap+0.089
 scrut+0.088
 ingred+0.086
ships+0.085
Neg logit contributions
 Nice-0.087
quiet-0.082
zeb-0.082
isexual-0.078
-0.077
Token improve
Token ID2987
Feature activation+1.46e-02

Pos logit contributions
 welf+0.250
 weap+0.232
 scrut+0.231
 ingred+0.226
ships+0.222
Neg logit contributions
 Nice-0.209
quiet-0.196
zeb-0.194
isexual-0.187
-0.182
Token their
Token ID511
Feature activation+3.85e-01

Pos logit contributions
 welf+0.013
 weap+0.012
 scrut+0.012
 ingred+0.011
ships+0.011
Neg logit contributions
 Nice-0.009
quiet-0.009
zeb-0.009
isexual-0.008
-0.008
Token experience
Token ID1998
Feature activation+2.34e-01

Pos logit contributions
 welf+0.313
 weap+0.294
 scrut+0.291
 ingred+0.285
ships+0.278
Neg logit contributions
 Nice-0.270
quiet-0.253
zeb-0.248
isexual-0.238
-0.236
Token not
Token ID407
Feature activation-4.01e-01

Pos logit contributions
 Nice+1.318
quiet+1.229
zeb+1.209
isexual+1.152
+1.144
Neg logit contributions
 welf-1.665
 weap-1.553
 scrut-1.527
 ingred-1.513
ships-1.492
Token impossible
Token ID5340
Feature activation+1.36e+00

Pos logit contributions
 Nice+0.265
quiet+0.249
zeb+0.246
isexual+0.235
+0.231
Neg logit contributions
 welf-0.342
 weap-0.321
 scrut-0.315
 ingred-0.311
ships-0.307
Token that
Token ID326
Feature activation+1.24e-01

Pos logit contributions
 welf+1.132
 weap+1.061
 scrut+1.052
 ingred+1.033
ships+1.015
Neg logit contributions
 Nice-0.897
quiet-0.861
zeb-0.850
isexual-0.825
-0.796
Token this
Token ID428
Feature activation-1.29e-01

Pos logit contributions
 welf+0.111
 weap+0.103
 scrut+0.103
 ingred+0.101
ships+0.100
Neg logit contributions
 Nice-0.077
quiet-0.072
zeb-0.071
isexual-0.068
-0.066
Token could
Token ID714
Feature activation-1.02e+00

Pos logit contributions
 Nice+0.087
quiet+0.083
zeb+0.082
isexual+0.079
+0.077
Neg logit contributions
 welf-0.107
 weap-0.100
 scrut-0.099
 ingred-0.097
ships-0.096
Token happen
Token ID1645
Feature activation+6.01e-01

Pos logit contributions
 Nice+0.681
quiet+0.651
zeb+0.638
isexual+0.618
+0.607
Neg logit contributions
 welf-0.867
 weap-0.805
 scrut-0.798
 ingred-0.781
ships-0.770
Token again
Token ID757
Feature activation-1.86e+00

Pos logit contributions
 welf+0.470
 weap+0.437
 scrut+0.433
 ingred+0.423
ships+0.416
Neg logit contributions
 Nice-0.434
quiet-0.415
zeb-0.411
isexual-0.399
-0.389
Token.
Token ID13
Feature activation+3.93e-01

Pos logit contributions
 Nice+1.349
quiet+1.284
zeb+1.266
isexual+1.222
+1.210
Neg logit contributions
 welf-1.478
 weap-1.360
 scrut-1.351
 ingred-1.325
ships-1.290
Token
Token ID198
Feature activation-1.18e-01

Pos logit contributions
 welf+0.325
 weap+0.302
 scrut+0.300
 ingred+0.296
ships+0.288
Neg logit contributions
 Nice-0.273
quiet-0.256
zeb-0.255
isexual-0.245
-0.240
Token
Token ID198
Feature activation-1.52e-03

Pos logit contributions
 Nice+0.078
quiet+0.074
zeb+0.073
isexual+0.070
+0.069
Neg logit contributions
 welf-0.104
 weap-0.096
 scrut-0.096
 ingred-0.096
 unden-0.094
TokenIf
Token ID1532
Feature activation+1.79e+00

Pos logit contributions
 Nice+0.001
quiet+0.001
zeb+0.001
isexual+0.001
+0.001
Neg logit contributions
 welf-0.001
 weap-0.001
 scrut-0.001
 ingred-0.001
 unden-0.001
Token price
Token ID2756
Feature activation+3.67e-01

Pos logit contributions
 welf+0.059
 weap+0.054
 scrut+0.053
 ingred+0.053
ships+0.052
Neg logit contributions
 Nice-0.062
quiet-0.058
zeb-0.058
isexual-0.055
-0.055
Token they
Token ID484
Feature activation+6.30e-01

Pos logit contributions
 welf+0.299
 weap+0.279
 scrut+0.276
 ingred+0.271
ships+0.266
Neg logit contributions
 Nice-0.255
quiet-0.242
zeb-0.240
isexual-0.231
-0.227
Token will
Token ID481
Feature activation+8.15e-01

Pos logit contributions
 welf+0.498
 weap+0.463
 scrut+0.458
 ingred+0.453
ships+0.442
Neg logit contributions
 Nice-0.452
quiet-0.431
zeb-0.427
isexual-0.411
-0.405
Token want
Token ID765
Feature activation-2.22e-01

Pos logit contributions
 welf+0.605
 weap+0.557
 scrut+0.554
 ingred+0.543
ships+0.533
Neg logit contributions
 Nice-0.625
quiet-0.595
zeb-0.589
isexual-0.572
-0.563
Token,
Token ID11
Feature activation+7.40e-01

Pos logit contributions
 Nice+0.141
quiet+0.133
zeb+0.132
isexual+0.126
+0.124
Neg logit contributions
 welf-0.194
 weap-0.182
 scrut-0.181
 ingred-0.177
ships-0.174
Token so
Token ID523
Feature activation+5.38e-01

Pos logit contributions
 welf+0.623
 weap+0.582
 scrut+0.577
 ingred+0.570
ships+0.558
Neg logit contributions
 Nice-0.494
quiet-0.467
zeb-0.459
isexual-0.442
-0.434
Token factories
Token ID17590
Feature activation+1.25e+00

Pos logit contributions
 welf+0.458
 weap+0.428
 scrut+0.422
 ingred+0.417
ships+0.410
Neg logit contributions
 Nice-0.358
quiet-0.336
zeb-0.328
isexual-0.316
-0.313
Token will
Token ID481
Feature activation+8.58e-01

Pos logit contributions
 welf+1.016
 weap+0.947
 scrut+0.939
 ingred+0.920
ships+0.905
Neg logit contributions
 Nice-0.866
quiet-0.825
zeb-0.816
isexual-0.789
-0.770
Token close
Token ID1969
Feature activation+2.15e+00

Pos logit contributions
 welf+0.686
 weap+0.636
 scrut+0.632
 ingred+0.619
ships+0.610
Neg logit contributions
 Nice-0.608
quiet-0.582
zeb-0.573
isexual-0.556
-0.541
Token down
Token ID866
Feature activation-3.60e-01

Pos logit contributions
 welf+1.662
 weap+1.547
 scrut+1.534
 ingred+1.497
ships+1.474
Neg logit contributions
 Nice-1.554
quiet-1.489
zeb-1.478
isexual-1.437
-1.395
Token and
Token ID290
Feature activation+1.50e-01

Pos logit contributions
 Nice+0.243
quiet+0.231
zeb+0.228
isexual+0.219
+0.215
Neg logit contributions
 welf-0.301
 weap-0.281
 scrut-0.278
 ingred-0.273
ships-0.268
Token formidable
Token ID24599
Feature activation+3.12e+00

Pos logit contributions
 welf+0.240
 weap+0.225
 scrut+0.223
 ingred+0.218
ships+0.215
Neg logit contributions
 Nice-0.178
quiet-0.169
zeb-0.167
isexual-0.161
-0.157
Token Diana
Token ID25752
Feature activation-3.31e-01

Pos logit contributions
 welf+2.816
 weap+2.649
 scrut+2.631
 ingred+2.566
ships+2.524
Neg logit contributions
 Nice-1.834
quiet-1.765
zeb-1.749
isexual-1.691
-1.636
Token Vill
Token ID9757
Feature activation-1.75e+00

Pos logit contributions
 Nice+0.223
quiet+0.211
zeb+0.210
isexual+0.202
+0.197
Neg logit contributions
 welf-0.276
 weap-0.258
 scrut-0.256
 ingred-0.250
ships-0.247
Tokeniers
Token ID3183
Feature activation-8.58e-01

Pos logit contributions
 Nice+1.383
quiet+1.335
zeb+1.326
isexual+1.286
+1.259
Neg logit contributions
 welf-1.259
 weap-1.168
 scrut-1.151
 ingred-1.128
ships-1.093
Token.
Token ID13
Feature activation+1.03e-01

Pos logit contributions
 Nice+0.591
quiet+0.560
zeb+0.555
isexual+0.531
+0.522
Neg logit contributions
 welf-0.706
 weap-0.658
 scrut-0.653
 ingred-0.641
ships-0.629
Token She
Token ID1375
Feature activation-3.67e-01

Pos logit contributions
 welf+0.089
 weap+0.084
 scrut+0.083
 ingred+0.082
 unden+0.080
Neg logit contributions
 Nice-0.067
quiet-0.063
zeb-0.062
isexual-0.060
-0.058
Token is
Token ID318
Feature activation+3.25e-02

Pos logit contributions
 Nice+0.259
quiet+0.248
zeb+0.245
isexual+0.237
+0.231
Neg logit contributions
 welf-0.294
 weap-0.273
 scrut-0.271
 ingred-0.266
ships-0.260
Token too
Token ID1165
Feature activation-1.73e+00

Pos logit contributions
 welf+0.027
 weap+0.026
 scrut+0.025
 ingred+0.025
ships+0.024
Neg logit contributions
 Nice-0.021
quiet-0.020
zeb-0.020
isexual-0.020
-0.019
Token much
Token ID881
Feature activation+1.07e+00

Pos logit contributions
 Nice+0.986
quiet+0.921
zeb+0.910
isexual+0.866
+0.842
Neg logit contributions
 welf-1.618
 weap-1.522
 scrut-1.501
 ingred-1.490
ships-1.469
Token for
Token ID329
Feature activation-7.67e-01

Pos logit contributions
 welf+0.877
 weap+0.818
 scrut+0.811
 ingred+0.794
ships+0.781
Neg logit contributions
 Nice-0.735
quiet-0.701
zeb-0.694
isexual-0.671
-0.653
Token Jack
Token ID3619
Feature activation+7.40e-02

Pos logit contributions
 Nice+0.514
quiet+0.488
zeb+0.483
isexual+0.467
+0.454
Neg logit contributions
 welf-0.641
 weap-0.599
 scrut-0.594
 ingred-0.583
ships-0.573
Token and
Token ID290
Feature activation-3.22e-01

Pos logit contributions
 welf+0.109
 weap+0.102
 scrut+0.101
 ingred+0.099
ships+0.097
Neg logit contributions
 Nice-0.083
quiet-0.079
zeb-0.078
isexual-0.076
-0.074
Token vegetables
Token ID13701
Feature activation+4.40e-01

Pos logit contributions
 Nice+0.247
quiet+0.232
zeb+0.230
isexual+0.224
+0.218
Neg logit contributions
 welf-0.238
 weap-0.221
 scrut-0.221
 ingred-0.214
CLASSIFIED-0.211
Token,
Token ID11
Feature activation-2.33e-01

Pos logit contributions
 welf+0.376
 weap+0.351
 scrut+0.349
 ingred+0.341
ships+0.336
Neg logit contributions
 Nice-0.287
quiet-0.273
zeb-0.269
isexual-0.260
-0.253
Token keeps
Token ID7622
Feature activation+1.63e+00

Pos logit contributions
 Nice+0.165
quiet+0.156
zeb+0.153
isexual+0.149
+0.146
Neg logit contributions
 welf-0.187
 weap-0.175
 scrut-0.173
 ingred-0.170
CLASSIFIED-0.167
Token honey
Token ID12498
Feature activation-6.42e-02

Pos logit contributions
 welf+1.364
 weap+1.275
 scrut+1.265
 ingred+1.237
ships+1.219
Neg logit contributions
 Nice-1.087
quiet-1.037
zeb-1.028
isexual-0.994
-0.966
Tokenbees
Token ID41712
Feature activation-1.39e-01

Pos logit contributions
 Nice+0.041
quiet+0.039
zeb+0.039
isexual+0.037
+0.036
Neg logit contributions
 welf-0.056
 weap-0.052
 scrut-0.051
 ingred-0.050
ships-0.049
Token,
Token ID11
Feature activation-1.57e-01

Pos logit contributions
 Nice+0.084
quiet+0.080
zeb+0.080
isexual+0.076
+0.073
Neg logit contributions
 welf-0.126
 weap-0.119
 scrut-0.117
 ingred-0.115
ships-0.113
Token cultiv
Token ID11229
Feature activation+2.10e+00

Pos logit contributions
 Nice+0.111
quiet+0.105
zeb+0.104
isexual+0.100
+0.098
Neg logit contributions
 welf-0.125
 weap-0.117
 scrut-0.115
 ingred-0.114
ships-0.111
Tokenates
Token ID689
Feature activation+1.40e+00

Pos logit contributions
 welf+1.673
 weap+1.558
 scrut+1.545
 ingred+1.511
ships+1.488
Neg logit contributions
 Nice-1.481
quiet-1.414
zeb-1.401
isexual-1.356
-1.322
Token mushrooms
Token ID23452
Feature activation+4.71e-01

Pos logit contributions
 welf+1.137
 weap+1.060
 scrut+1.052
 ingred+1.030
ships+1.014
Neg logit contributions
 Nice-0.970
quiet-0.922
zeb-0.913
isexual-0.884
-0.861
Token,
Token ID11
Feature activation-2.26e-01

Pos logit contributions
 welf+0.397
 weap+0.371
 scrut+0.368
 ingred+0.361
ships+0.355
Neg logit contributions
 Nice-0.311
quiet-0.296
zeb-0.293
isexual-0.283
-0.275
Token of
Token ID286
Feature activation+1.20e-02

Pos logit contributions
 welf+0.620
 weap+0.576
 scrut+0.571
 ingred+0.559
ships+0.550
Neg logit contributions
 Nice-0.575
quiet-0.550
zeb-0.545
isexual-0.528
-0.515
Token books
Token ID3835
Feature activation-7.32e-01

Pos logit contributions
 welf+0.009
 weap+0.009
 scrut+0.009
 ingred+0.009
ships+0.008
Neg logit contributions
 Nice-0.009
quiet-0.008
zeb-0.008
isexual-0.008
-0.008
Token that
Token ID326
Feature activation-5.30e-01

Pos logit contributions
 Nice+0.475
quiet+0.452
zeb+0.444
isexual+0.428
+0.420
Neg logit contributions
 welf-0.630
 weap-0.589
 scrut-0.584
 ingred-0.573
ships-0.561
Token you
Token ID345
Feature activation-8.81e-01

Pos logit contributions
 Nice+0.369
quiet+0.351
zeb+0.343
isexual+0.332
+0.329
Neg logit contributions
 welf-0.431
 weap-0.401
 scrut-0.396
 ingred-0.389
ships-0.383
Token want
Token ID765
Feature activation-7.13e-01

Pos logit contributions
 Nice+0.598
quiet+0.574
zeb+0.558
isexual+0.546
+0.538
Neg logit contributions
 welf-0.731
 weap-0.676
 scrut-0.668
 ingred-0.662
ships-0.644
Token to
Token ID284
Feature activation+9.91e-02

Pos logit contributions
 Nice+0.399
quiet+0.377
zeb+0.369
isexual+0.354
+0.345
Neg logit contributions
 welf-0.675
 weap-0.637
 scrut-0.630
 ingred-0.621
ships-0.609
Token read
Token ID1100
Feature activation-9.66e-01

Pos logit contributions
 welf+0.093
 weap+0.088
 scrut+0.086
 ingred+0.085
ships+0.084
Neg logit contributions
 Nice-0.056
quiet-0.053
zeb-0.052
isexual-0.050
-0.049
Token on
Token ID319
Feature activation-1.52e-02

Pos logit contributions
 Nice+0.603
quiet+0.575
zeb+0.559
isexual+0.543
+0.532
Neg logit contributions
 welf-0.856
 weap-0.798
 scrut-0.792
 ingred-0.781
ships-0.765
Token the
Token ID262
Feature activation+1.03e-01

Pos logit contributions
 Nice+0.011
quiet+0.010
zeb+0.010
isexual+0.010
+0.010
Neg logit contributions
 welf-0.012
 weap-0.011
 scrut-0.011
 ingred-0.011
ships-0.011
Token Kindle
Token ID27114
Feature activation-1.05e+00

Pos logit contributions
 welf+0.080
 weap+0.075
 scrut+0.074
 ingred+0.072
ships+0.071
Neg logit contributions
 Nice-0.075
quiet-0.072
zeb-0.071
isexual-0.069
-0.067
Token,
Token ID11
Feature activation+3.50e-01

Pos logit contributions
 Nice+0.688
quiet+0.654
zeb+0.642
isexual+0.616
+0.611
Neg logit contributions
 welf-0.891
 weap-0.835
 scrut-0.825
 ingred-0.820
ships-0.801
Token mind
Token ID2000
Feature activation+2.01e+00

Pos logit contributions
 Nice+0.112
quiet+0.108
zeb+0.106
isexual+0.103
+0.101
Neg logit contributions
 welf-0.134
 weap-0.125
 scrut-0.123
 ingred-0.122
ships-0.118
Token,
Token ID11
Feature activation+2.90e-01

Pos logit contributions
 welf+1.625
 weap+1.515
 scrut+1.502
 ingred+1.470
ships+1.446
Neg logit contributions
 Nice-1.398
quiet-1.334
zeb-1.321
isexual-1.279
-1.246
Token we
Token ID356
Feature activation+1.59e-01

Pos logit contributions
 welf+0.242
 weap+0.225
 scrut+0.223
 ingred+0.220
ships+0.215
Neg logit contributions
 Nice-0.196
quiet-0.186
zeb-0.182
isexual-0.176
-0.173
Token do
Token ID466
Feature activation+1.10e+00

Pos logit contributions
 welf+0.129
 weap+0.120
 scrut+0.118
 ingred+0.117
ships+0.114
Neg logit contributions
 Nice-0.111
quiet-0.106
zeb-0.105
isexual-0.101
-0.100
Token realize
Token ID6537
Feature activation+3.85e-01

Pos logit contributions
 welf+0.863
 weap+0.798
 scrut+0.791
 ingred+0.777
ships+0.764
Neg logit contributions
 Nice-0.796
quiet-0.760
zeb-0.750
isexual-0.727
-0.713
Token that
Token ID326
Feature activation-5.30e-02

Pos logit contributions
 welf+0.330
 weap+0.309
 scrut+0.305
 ingred+0.301
ships+0.295
Neg logit contributions
 Nice-0.251
quiet-0.237
zeb-0.233
isexual-0.226
-0.221
Token some
Token ID617
Feature activation+2.70e-01

Pos logit contributions
 Nice+0.035
quiet+0.033
zeb+0.033
isexual+0.031
+0.031
Neg logit contributions
 welf-0.045
 weap-0.042
 scrut-0.041
 ingred-0.041
ships-0.040
Token are
Token ID389
Feature activation-4.47e-01

Pos logit contributions
 welf+0.213
 weap+0.198
 scrut+0.195
 ingred+0.192
ships+0.188
Neg logit contributions
 Nice-0.194
quiet-0.185
zeb-0.183
isexual-0.176
-0.173
Token more
Token ID517
Feature activation-5.11e-01

Pos logit contributions
 Nice+0.289
quiet+0.273
zeb+0.268
isexual+0.259
+0.253
Neg logit contributions
 welf-0.387
 weap-0.361
 scrut-0.357
 ingred-0.351
ships-0.346
Token exciting
Token ID7895
Feature activation+2.96e-01

Pos logit contributions
 Nice+0.335
quiet+0.316
zeb+0.310
isexual+0.300
+0.292
Neg logit contributions
 welf-0.437
 weap-0.407
 scrut-0.401
 ingred-0.396
ships-0.391
Token than
Token ID621
Feature activation-1.28e+00

Pos logit contributions
 welf+0.249
 weap+0.232
 scrut+0.231
 ingred+0.226
ships+0.222
Neg logit contributions
 Nice-0.197
quiet-0.187
zeb-0.185
isexual-0.178
-0.174
Token,
Token ID11
Feature activation-2.16e-01

Pos logit contributions
 Nice+0.569
quiet+0.540
zeb+0.536
isexual+0.515
+0.503
Neg logit contributions
 welf-0.649
 weap-0.604
 scrut-0.599
 ingred-0.588
ships-0.574
Token and
Token ID290
Feature activation-1.38e-01

Pos logit contributions
 Nice+0.143
quiet+0.134
zeb+0.132
isexual+0.128
+0.124
Neg logit contributions
 welf-0.185
 weap-0.173
 scrut-0.172
 ingred-0.169
ships-0.167
Token to
Token ID284
Feature activation-2.10e-02

Pos logit contributions
 Nice+0.091
quiet+0.086
zeb+0.085
isexual+0.083
+0.079
Neg logit contributions
 welf-0.117
 weap-0.110
 scrut-0.109
 ingred-0.107
ships-0.106
Token continue
Token ID2555
Feature activation-4.52e-01

Pos logit contributions
 Nice+0.015
quiet+0.014
zeb+0.014
isexual+0.014
+0.013
Neg logit contributions
 welf-0.017
 weap-0.016
 scrut-0.015
 ingred-0.015
ships-0.015
Token paying
Token ID5989
Feature activation-1.04e-02

Pos logit contributions
 Nice+0.275
quiet+0.259
zeb+0.255
isexual+0.247
+0.237
Neg logit contributions
 welf-0.406
 weap-0.383
 scrut-0.378
 ingred-0.372
ships-0.368
Token my
Token ID616
Feature activation-2.90e-01

Pos logit contributions
 Nice+0.008
quiet+0.007
zeb+0.007
isexual+0.007
+0.007
Neg logit contributions
 welf-0.008
 weap-0.007
 scrut-0.007
 ingred-0.007
ships-0.007
Token tit
Token ID5259
Feature activation-1.68e+00

Pos logit contributions
 Nice+0.213
quiet+0.201
zeb+0.200
isexual+0.193
+0.188
Neg logit contributions
 welf-0.225
 weap-0.210
 scrut-0.207
 ingred-0.203
ships-0.201
Tokenhes
Token ID956
Feature activation-1.06e+00

Pos logit contributions
 Nice+1.177
quiet+1.123
zeb+1.118
isexual+1.066
+1.051
Neg logit contributions
 welf-1.354
 weap-1.268
 scrut-1.263
 ingred-1.234
ships-1.208
Token to
Token ID284
Feature activation+8.76e-02

Pos logit contributions
 Nice+0.711
quiet+0.675
zeb+0.667
isexual+0.642
+0.623
Neg logit contributions
 welf-0.891
 weap-0.833
 scrut-0.828
 ingred-0.814
ships-0.798
Token the
Token ID262
Feature activation-1.17e-01

Pos logit contributions
 welf+0.073
 weap+0.069
 scrut+0.068
 ingred+0.067
ships+0.066
Neg logit contributions
 Nice-0.059
quiet-0.056
zeb-0.055
isexual-0.054
-0.052
Token church
Token ID4928
Feature activation+1.91e-01

Pos logit contributions
 Nice+0.073
quiet+0.069
zeb+0.068
isexual+0.066
+0.063
Neg logit contributions
 welf-0.104
 weap-0.098
 scrut-0.097
 ingred-0.095
ships-0.094
Tokenaine
Token ID5718
Feature activation+1.97e-02

Pos logit contributions
 welf+0.058
 weap+0.054
 scrut+0.053
 ingred+0.053
ships+0.052
Neg logit contributions
 Nice-0.041
quiet-0.039
zeb-0.038
isexual-0.036
-0.036
Token also
Token ID635
Feature activation-5.74e-01

Pos logit contributions
 welf+0.016
 weap+0.015
 scrut+0.014
 ingred+0.014
ships+0.014
Neg logit contributions
 Nice-0.014
quiet-0.013
zeb-0.013
isexual-0.013
-0.013
Token did
Token ID750
Feature activation+2.65e-01

Pos logit contributions
 Nice+0.418
quiet+0.398
zeb+0.398
isexual+0.378
+0.374
Neg logit contributions
 welf-0.452
 weap-0.419
 scrut-0.411
 ingred-0.410
ships-0.399
Token a
Token ID257
Feature activation-1.69e-01

Pos logit contributions
 welf+0.216
 weap+0.202
 scrut+0.199
 ingred+0.197
ships+0.195
Neg logit contributions
 Nice-0.185
quiet-0.175
zeb-0.174
isexual-0.166
-0.164
Token good
Token ID922
Feature activation+6.78e-01

Pos logit contributions
 Nice+0.106
quiet+0.100
zeb+0.099
isexual+0.094
+0.092
Neg logit contributions
 welf-0.149
 weap-0.140
 scrut-0.138
 ingred-0.137
ships-0.135
Token job
Token ID1693
Feature activation-2.51e+00

Pos logit contributions
 welf+0.510
 weap+0.475
 scrut+0.468
 ingred+0.459
ships+0.451
Neg logit contributions
 Nice-0.511
quiet-0.488
zeb-0.484
isexual-0.469
-0.459
Token repeatedly
Token ID7830
Feature activation+1.15e+00

Pos logit contributions
 Nice+1.673
quiet+1.582
zeb+1.562
isexual+1.484
+1.468
Neg logit contributions
 welf-2.110
 weap-1.987
 ingred-1.921
 scrut-1.914
ships-1.886
Token pressing
Token ID12273
Feature activation-1.14e-01

Pos logit contributions
 welf+0.977
 weap+0.914
 scrut+0.904
 ingred+0.888
ships+0.874
Neg logit contributions
 Nice-0.756
quiet-0.720
zeb-0.712
isexual-0.686
-0.669
Token on
Token ID319
Feature activation-4.32e-01

Pos logit contributions
 Nice+0.072
quiet+0.067
zeb+0.066
isexual+0.063
+0.062
Neg logit contributions
 welf-0.101
 weap-0.095
 scrut-0.094
 ingred-0.092
ships-0.091
Token Trump
Token ID1301
Feature activation-1.55e+00

Pos logit contributions
 Nice+0.267
quiet+0.249
zeb+0.246
isexual+0.236
+0.230
Neg logit contributions
 welf-0.386
 weap-0.363
 scrut-0.361
 ingred-0.354
ships-0.349
Token
Token ID447
Feature activation-4.39e-01

Pos logit contributions
 Nice+0.943
quiet+0.897
zeb+0.886
isexual+0.847
+0.831
Neg logit contributions
 welf-1.394
 weap-1.305
 scrut-1.293
 ingred-1.274
ships-1.247
Token especially
Token ID2592
Feature activation-1.24e+00

Pos logit contributions
 welf+0.074
 weap+0.069
 scrut+0.068
 ingred+0.067
ships+0.066
Neg logit contributions
 Nice-0.061
quiet-0.058
zeb-0.057
isexual-0.055
-0.054
Token when
Token ID618
Feature activation+8.70e-02

Pos logit contributions
 Nice+0.791
quiet+0.749
zeb+0.737
isexual+0.708
+0.694
Neg logit contributions
 welf-1.090
 weap-1.018
 scrut-1.010
 ingred-0.992
ships-0.975
Token you
Token ID345
Feature activation-1.28e+00

Pos logit contributions
 welf+0.072
 weap+0.066
 scrut+0.066
 ingred+0.065
ships+0.064
Neg logit contributions
 Nice-0.060
quiet-0.057
zeb-0.056
isexual-0.054
-0.053
Token consider
Token ID2074
Feature activation-7.02e-01

Pos logit contributions
 Nice+0.899
quiet+0.863
zeb+0.843
isexual+0.814
+0.812
Neg logit contributions
 welf-1.036
 weap-0.958
 scrut-0.945
 ingred-0.938
ships-0.915
Token the
Token ID262
Feature activation-1.92e-01

Pos logit contributions
 Nice+0.470
quiet+0.441
zeb+0.434
isexual+0.418
+0.412
Neg logit contributions
 welf-0.592
 weap-0.552
 scrut-0.548
 ingred-0.539
ships-0.530
Token Las
Token ID10123
Feature activation-2.70e+00

Pos logit contributions
 Nice+0.146
quiet+0.138
zeb+0.137
isexual+0.131
+0.130
Neg logit contributions
 welf-0.144
 weap-0.133
 scrut-0.132
 ingred-0.129
ships-0.128
Token Vegas
Token ID9621
Feature activation-2.51e+00

Pos logit contributions
 Nice+1.769
quiet+1.663
zeb+1.653
isexual+1.569
igue+1.554
Neg logit contributions
 welf-2.347
 scrut-2.196
 weap-2.175
 ingred-2.164
 unden-2.147
Token case
Token ID1339
Feature activation+1.99e+00

Pos logit contributions
 Nice+1.683
zeb+1.563
quiet+1.549
isexual+1.471
+1.442
Neg logit contributions
 welf-2.113
 scrut-1.976
 weap-1.971
 ingred-1.924
ships-1.915
Token in
Token ID287
Feature activation+1.35e-01

Pos logit contributions
 welf+1.562
 weap+1.454
 scrut+1.442
 ingred+1.408
ships+1.389
Neg logit contributions
 Nice-1.426
quiet-1.364
zeb-1.350
isexual-1.314
-1.274
Token its
Token ID663
Feature activation-1.50e+00

Pos logit contributions
 welf+0.102
 weap+0.095
 scrut+0.094
 ingred+0.092
ships+0.091
Neg logit contributions
 Nice-0.101
quiet-0.097
zeb-0.095
isexual-0.092
-0.090
Token larger
Token ID4025
Feature activation-4.03e-01

Pos logit contributions
 Nice+1.331
quiet+1.274
zeb+1.271
isexual+1.222
+1.207
Neg logit contributions
 welf-0.915
 weap-0.839
 scrut-0.826
 ingred-0.809
ships-0.788
Token pest
Token ID28064
Feature activation-7.70e-02

Pos logit contributions
 Nice+0.316
quiet+0.300
zeb+0.297
isexual+0.285
+0.277
Neg logit contributions
 welf-0.447
 weap-0.419
 scrut-0.415
 ingred-0.408
ships-0.403
Tokenil
Token ID346
Feature activation+8.83e-01

Pos logit contributions
 Nice+0.059
quiet+0.056
zeb+0.056
isexual+0.054
+0.053
Neg logit contributions
 welf-0.057
 weap-0.053
 scrut-0.052
 ingred-0.051
ships-0.050
Tokenent
Token ID298
Feature activation-1.38e+00

Pos logit contributions
 welf+0.803
 weap+0.757
 scrut+0.750
 ingred+0.736
ships+0.728
Neg logit contributions
 Nice-0.520
quiet-0.490
zeb-0.486
isexual-0.467
-0.453
Token congregation
Token ID28862
Feature activation-8.88e-01

Pos logit contributions
 Nice+0.938
quiet+0.888
zeb+0.879
isexual+0.843
+0.827
Neg logit contributions
 welf-1.143
 weap-1.069
 scrut-1.056
 ingred-1.039
ships-1.029
Token of
Token ID286
Feature activation-1.41e-01

Pos logit contributions
 Nice+0.608
quiet+0.581
zeb+0.575
isexual+0.552
+0.541
Neg logit contributions
 welf-0.728
 weap-0.681
 scrut-0.675
 ingred-0.662
ships-0.647
Token vap
Token ID38187
Feature activation-2.46e+00

Pos logit contributions
 Nice+0.095
quiet+0.090
zeb+0.089
isexual+0.086
+0.084
Neg logit contributions
 welf-0.117
 weap-0.109
 scrut-0.108
 ingred-0.106
ships-0.105
Tokenors
Token ID669
Feature activation-1.65e+00

Pos logit contributions
 Nice+1.585
quiet+1.515
zeb+1.498
isexual+1.447
+1.407
Neg logit contributions
 welf-2.122
 weap-1.988
 scrut-1.962
 ingred-1.917
 unden-1.879
Token.
Token ID13
Feature activation-4.13e-01

Pos logit contributions
 Nice+1.103
quiet+1.053
zeb+1.042
isexual+0.996
+0.977
Neg logit contributions
 welf-1.383
 weap-1.291
 scrut-1.279
 ingred-1.256
ships-1.229
Token
Token ID198
Feature activation-5.55e-01

Pos logit contributions
 Nice+0.294
quiet+0.282
zeb+0.280
isexual+0.272
+0.264
Neg logit contributions
 welf-0.324
 weap-0.302
 scrut-0.298
 ingred-0.292
ships-0.288
Token
Token ID198
Feature activation-5.91e-01

Pos logit contributions
 Nice+0.368
quiet+0.348
zeb+0.343
isexual+0.326
+0.323
Neg logit contributions
 welf-0.491
 ingred-0.455
 weap-0.455
 scrut-0.454
 unden-0.447
TokenWhat
Token ID2061
Feature activation+5.88e-02

Pos logit contributions
 Nice+0.455
quiet+0.439
zeb+0.431
isexual+0.415
+0.412
Neg logit contributions
 welf-0.442
 weap-0.410
 scrut-0.407
 ingred-0.400
 unden-0.386
Token stock
Token ID4283
Feature activation-6.16e-01

Pos logit contributions
 Nice+0.680
quiet+0.645
zeb+0.628
isexual+0.603
+0.591
Neg logit contributions
 welf-0.806
 weap-0.742
 scrut-0.728
 ingred-0.726
ships-0.710
Token was
Token ID373
Feature activation+1.48e-01

Pos logit contributions
 Nice+0.434
quiet+0.414
zeb+0.410
isexual+0.396
+0.386
Neg logit contributions
 welf-0.494
 weap-0.459
 scrut-0.457
 ingred-0.447
ships-0.437
Token trading
Token ID7313
Feature activation+4.08e-01

Pos logit contributions
 welf+0.115
 weap+0.107
 scrut+0.105
 ingred+0.104
ships+0.101
Neg logit contributions
 Nice-0.109
quiet-0.104
zeb-0.102
isexual-0.099
-0.097
Token when
Token ID618
Feature activation+2.39e-01

Pos logit contributions
 welf+0.360
 weap+0.337
 scrut+0.335
 ingred+0.329
ships+0.323
Neg logit contributions
 Nice-0.256
quiet-0.243
zeb-0.238
isexual-0.229
-0.223
Token the
Token ID262
Feature activation-3.79e-02

Pos logit contributions
 welf+0.206
 weap+0.192
 scrut+0.190
 ingred+0.187
ships+0.184
Neg logit contributions
 Nice-0.156
quiet-0.148
zeb-0.144
isexual-0.140
-0.137
Token bid
Token ID8406
Feature activation-3.98e+00

Pos logit contributions
 Nice+0.029
quiet+0.028
zeb+0.027
isexual+0.026
+0.026
Neg logit contributions
 welf-0.028
 weap-0.026
 scrut-0.026
 ingred-0.026
ships-0.025
Token approach
Token ID3164
Feature activation-6.91e-01

Pos logit contributions
 Nice+2.644
quiet+2.511
zeb+2.503
isexual+2.379
+2.299
Neg logit contributions
 welf-3.335
 weap-3.079
 ingred-3.028
 scrut-3.021
 unden-2.953
Token was
Token ID373
Feature activation+2.58e-02

Pos logit contributions
 Nice+0.492
quiet+0.469
zeb+0.464
isexual+0.449
+0.437
Neg logit contributions
 welf-0.550
 weap-0.511
 scrut-0.505
 ingred-0.498
ships-0.486
Token made
Token ID925
Feature activation-1.10e-01

Pos logit contributions
 welf+0.021
 weap+0.020
 scrut+0.019
 ingred+0.019
ships+0.019
Neg logit contributions
 Nice-0.018
quiet-0.017
zeb-0.017
isexual-0.016
-0.016
Token on
Token ID319
Feature activation-2.11e-01

Pos logit contributions
 Nice+0.078
quiet+0.075
zeb+0.073
isexual+0.071
+0.069
Neg logit contributions
 welf-0.088
 weap-0.081
 scrut-0.080
 ingred-0.079
ships-0.078
Token 1
Token ID352
Feature activation-1.85e+00

Pos logit contributions
 Nice+0.113
quiet+0.104
zeb+0.102
isexual+0.097
+0.094
Neg logit contributions
 welf-0.208
 weap-0.196
 scrut-0.194
 ingred-0.192
ships-0.189
Token a
Token ID257
Feature activation-1.74e-01

Pos logit contributions
 welf+0.268
 weap+0.252
 scrut+0.249
 ingred+0.244
ships+0.240
Neg logit contributions
 Nice-0.231
quiet-0.220
zeb-0.217
isexual-0.210
-0.204
Token week
Token ID1285
Feature activation+5.72e-02

Pos logit contributions
 Nice+0.118
quiet+0.113
zeb+0.112
isexual+0.108
+0.105
Neg logit contributions
 welf-0.144
 weap-0.134
 scrut-0.133
 ingred-0.130
ships-0.128
Token.
Token ID13
Feature activation+2.52e-01

Pos logit contributions
 welf+0.046
 weap+0.043
 scrut+0.043
 ingred+0.042
ships+0.041
Neg logit contributions
 Nice-0.040
quiet-0.038
zeb-0.038
isexual-0.037
-0.036
Token
Token ID198
Feature activation+1.06e-01

Pos logit contributions
 welf+0.209
 weap+0.195
 scrut+0.194
 ingred+0.190
ships+0.185
Neg logit contributions
 Nice-0.174
quiet-0.163
zeb-0.162
isexual-0.156
-0.153
Token
Token ID198
Feature activation+9.09e-02

Pos logit contributions
 welf+0.089
 weap+0.083
 scrut+0.083
 ingred+0.082
 unden+0.079
Neg logit contributions
 Nice-0.073
quiet-0.069
zeb-0.068
isexual-0.066
-0.065
TokenStill
Token ID9590
Feature activation-3.09e+00

Pos logit contributions
 welf+0.068
 weap+0.063
 scrut+0.063
 ingred+0.062
 unden+0.060
Neg logit contributions
 Nice-0.069
quiet-0.067
zeb-0.066
isexual-0.064
-0.063
Token,
Token ID11
Feature activation-4.93e-01

Pos logit contributions
 Nice+2.017
quiet+1.893
zeb+1.845
isexual+1.789
+1.741
Neg logit contributions
 welf-2.664
 weap-2.486
 scrut-2.470
 ingred-2.428
ships-2.375
Token there
Token ID612
Feature activation+7.08e-03

Pos logit contributions
 Nice+0.333
quiet+0.311
zeb+0.307
isexual+0.296
+0.290
Neg logit contributions
 welf-0.413
 weap-0.387
 scrut-0.384
 ingred-0.377
ships-0.371
Token is
Token ID318
Feature activation+9.82e-02

Pos logit contributions
 welf+0.006
 weap+0.005
 scrut+0.005
 ingred+0.005
ships+0.005
Neg logit contributions
 Nice-0.005
quiet-0.005
zeb-0.005
isexual-0.004
-0.004
Token a
Token ID257
Feature activation-1.70e-01

Pos logit contributions
 welf+0.080
 weap+0.075
 scrut+0.074
 ingred+0.072
ships+0.071
Neg logit contributions
 Nice-0.069
quiet-0.065
zeb-0.064
isexual-0.062
-0.060
Token right
Token ID826
Feature activation-3.53e-01

Pos logit contributions
 Nice+0.119
quiet+0.112
zeb+0.111
isexual+0.107
+0.104
Neg logit contributions
 welf-0.138
 weap-0.129
 scrut-0.127
 ingred-0.125
ships-0.124