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

    Neuronpedia

    INDEX
    Explanations

    numeric sequences

    oai_token-act-pair · gpt-3.5-turbo

    elements related to numeric values or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nect
    -0.86
    NetMessage
    -0.85
    glers
    -0.79
    istically
    -0.78
    inately
    -0.78
    ansas
    -0.75
    enton
    -0.74
    istics
    -0.74
    oreal
    -0.74
    onomy
    -0.73
    POSITIVE LOGITS
    ³
    0.87
    ת
    0.79
    Į
    0.76
    ´
    0.75
    ²
    0.73
    vre
    0.73
    ¡
    0.73
    ãģį
    0.72
    rer
    0.72
    ÙĦ
    0.71
    Act Density 0.019%

    No Known Activations