Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to stars or stellar objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.54
     snippetHide
    -0.48
    <?
    -0.48
     informée
    -0.45
     niebies
    -0.45
     øns
    -0.45
    ofire
    -0.45
     Gläub
    -0.44
     samfun
    -0.44
     kijken
    -0.44
    POSITIVE LOGITS
     star
    1.60
    star
    1.41
     STAR
    1.23
     starred
    1.19
    STAR
    1.18
     stars
    1.11
     Star
    1.10
     estrella
    1.04
     superstar
    1.02
    Star
    1.02
    Act Density 0.195%

    No Known Activations