INDEX
Explanations
expressions of desire or intent
New Auto-Interp
Negative Logits
uter
-0.17
Ïħγ
-0.15
obar
-0.15
ymes
-0.15
icht
-0.15
oui
-0.14
ichern
-0.14
Licensing
-0.14
icher
-0.14
owo
-0.14
POSITIVE LOGITS
etta
0.15
born
0.15
538
0.15
506
0.15
299
0.15
otten
0.14
atz
0.14
Meta
0.13
hor
0.13
kit
0.13
Activations Density 0.007%