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

    Neuronpedia

    INDEX
    Explanations

    specific programming or coding terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acao
    -0.16
    rated
    -0.15
    ictim
    -0.15
    cum
    -0.14
    žel
    -0.14
    .union
    -0.14
    cape
    -0.14
    eness
    -0.14
    itez
    -0.14
    ical
    -0.14
    POSITIVE LOGITS
    Formats
    0.17
    linger
    0.15
    oso
    0.15
    agr
    0.14
     cruz
    0.14
    etre
    0.14
     thinner
    0.14
    roe
    0.14
    ushman
    0.14
    ku
    0.14
    Act Density 0.042%

    No Known Activations