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

    Neuronpedia

    INDEX
    Explanations

    quotes and formal statements expressing opinions or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itals
    -0.18
    OfClass
    -0.15
    undy
    -0.15
    argent
    -0.14
     Unauthorized
    -0.14
     Gos
    -0.14
    á»ĩn
    -0.14
    alem
    -0.14
     Facts
    -0.14
    CPF
    -0.14
    POSITIVE LOGITS
    quine
    0.16
     cadre
    0.15
    plex
    0.15
    aeda
    0.15
    angler
    0.15
     stub
    0.14
    bold
    0.14
    phyl
    0.13
    spinner
    0.13
    iker
    0.13
    Act Density 0.029%

    No Known Activations