INDEX
Explanations
mentions of poetry and poems-related terms
references to poetry and poets
New Auto-Interp
Negative Logits
rals
-0.78
erate
-0.78
negie
-0.72
avez
-0.72
perature
-0.71
tch
-0.71
anson
-0.69
disadvant
-0.69
clamp
-0.68
rador
-0.66
POSITIVE LOGITS
poetry
1.26
poems
1.24
poem
1.22
laureate
1.22
poets
1.06
poet
1.04
poetic
0.99
verse
0.86
issance
0.85
lyric
0.84
Activations Density 0.040%