INDEX
Explanations
proper nouns related to particular individuals, especially those named Ruth
mentions of the name "Ruth," particularly in notable contexts or associations
New Auto-Interp
Negative Logits
gotten
-0.70
ctica
-0.68
Helsinki
-0.64
tein
-0.64
artney
-0.63
netflix
-0.62
olesc
-0.62
skies
-0.61
Thumbnails
-0.60
ãĤĬ
-0.60
POSITIVE LOGITS
anne
0.96
Ruth
0.91
uth
0.78
less
0.76
lessly
0.75
enthal
0.74
lyn
0.74
lessness
0.73
inate
0.70
anna
0.70
Activations Density 0.007%