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

    Neuronpedia

    INDEX
    Explanations

    numbers, likely connected to statistical information or figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character '³' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neg
    -0.72
    aido
    -0.71
    okin
    -0.70
    itton
    -0.69
    yrim
    -0.69
    istically
    -0.69
    ority
    -0.68
    ancial
    -0.66
    acters
    -0.66
    lear
    -0.65
    POSITIVE LOGITS
    enance
    0.77
    IBLE
    0.75
    Marie
    0.70
    xual
    0.69
    ibility
    0.68
    tics
    0.67
    enced
    0.67
    cart
    0.67
    tions
    0.66
     Sheen
    0.65
    Act Density 0.066%

    No Known Activations