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

    Neuronpedia

    INDEX
    Explanations

    words related to physical actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to plural nouns and types of organisms or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bey
    -0.68
     Slov
    -0.64
     Lie
    -0.58
     Jesus
    -0.57
     Galile
    -0.57
    LESS
    -0.56
    HOU
    -0.56
    wright
    -0.56
     Nightmares
    -0.56
     bulls
    -0.55
    POSITIVE LOGITS
    aturated
    1.41
    atisf
    1.39
    ources
    1.35
    ystem
    1.35
    ensical
    1.32
    atellite
    1.32
    ocial
    1.31
    essions
    1.29
    istent
    1.28
    leeve
    1.27
    Act Density 0.131%

    No Known Activations