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

    Neuronpedia

    INDEX
    Explanations

    statements or reports from official sources

    oai_token-act-pair · gpt-3.5-turbo

    references to statements and announcements attributed to various entities or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wick
    -0.74
     carbohyd
    -0.73
    chwitz
    -0.72
    endish
    -0.71
    gradation
    -0.69
    lied
    -0.68
    merce
    -0.68
    ighth
    -0.67
    faced
    -0.67
    ritional
    -0.66
    POSITIVE LOGITS
     afar
    1.10
     inside
    0.86
     whence
    0.86
     abroad
    0.81
     within
    0.74
     thence
    0.74
     Inside
    0.71
     Rabbi
    0.70
     atop
    0.69
     Washington
    0.68
    Act Density 0.099%

    No Known Activations