INDEX
Explanations
linguistic concepts related to verb tenses
New Auto-Interp
Negative Logits
ults
-0.15
ieces
-0.15
otta
-0.15
ourg
-0.15
DISCLAIM
-0.14
hier
-0.14
ILON
-0.14
Ïĩο
-0.14
_TER
-0.14
ibold
-0.14
POSITIVE LOGITS
tense
0.35
conjug
0.27
infinit
0.27
verb
0.26
Verb
0.26
Imper
0.25
Verb
0.25
Passive
0.25
passive
0.24
Past
0.24
Activations Density 0.044%