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

    Neuronpedia

    INDEX
    Explanations

    terms related to concepts, theories, and ideologies

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to theoretical frameworks and academic principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.71
    anwhile
    -0.59
    çīĪ
    -0.57
    OTAL
    -0.57
    aughed
    -0.56
    artney
    -0.55
    ONSORED
    -0.54
    Ire
    -0.54
    ÃĥÃĤ
    -0.54
    leased
    -0.52
    POSITIVE LOGITS
     versus
    0.65
     clauses
    0.65
    less
    0.63
    ism
    0.63
     vs
    0.59
    coin
    0.58
    ivism
    0.57
    paren
    0.57
    ativity
    0.57
     crochet
    0.56
    Act Density 1.204%

    No Known Activations