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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and specific titles or roles associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.55
    ashtra
    -0.55
    ĨĴ
    -0.53
    ICAN
    -0.50
    Ö
    -0.47
     tremend
    -0.47
    ãĤ¢ãĥ«
    -0.47
    leground
    -0.46
    Solar
    -0.46
    fml
    -0.46
    POSITIVE LOGITS
    pora
    0.58
    haw
    0.53
    hent
    0.53
    iffin
    0.53
    uez
    0.53
    otom
    0.47
    gently
    0.47
    ĸļ
    0.47
     Crescent
    0.47
    ioch
    0.46
    Act Density 1.587%

    No Known Activations