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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    quartered
    -0.69
    etheless
    -0.67
    Reloaded
    -0.61
    rontal
    -0.60
     Gleaming
    -0.58
    KNOWN
    -0.58
    ascular
    -0.56
     aggregation
    -0.55
     butterflies
    -0.55
    isode
    -0.54
    POSITIVE LOGITS
    lang
    0.73
     Quan
    0.72
    si
    0.72
     Lauder
    0.68
    dx
    0.65
    icio
    0.63
    dn
    0.62
    fi
    0.62
    ħĭ
    0.61
    ciating
    0.61
    Act Density 0.647%

    No Known Activations