INDEX
Explanations
specific noun/phrase continuations
New Auto-Interp
Negative Logits
Getting
0.45
a
0.43
stechn
0.42
↵
0.41
function
0.41
Getting
0.39
Brut
0.39
veniva
0.39
Funktion
0.39
funkci
0.38
POSITIVE LOGITS
tumeur
0.53
enggak
0.53
billionaires
0.52
tumours
0.48
socialists
0.47
sunflowers
0.47
exams
0.47
gays
0.46
tumors
0.46
allies
0.46
Activations Density 0.000%