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

    Neuronpedia

    INDEX
    Explanations

    references to historical and literary figures or events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    creen
    -0.73
    ¯
    -0.73
    CAST
    -0.71
    ALLY
    -0.71
    iques
    -0.68
    LCS
    -0.67
    Interstitial
    -0.67
    oÄŁ
    -0.64
    say
    -0.63
    icative
    -0.63
    POSITIVE LOGITS
    antry
    0.95
    Page
    0.74
     Six
    0.72
     McConnell
    0.68
    views
    0.65
     Page
    0.65
    witz
    0.62
    Maker
    0.60
     Nine
    0.59
     Count
    0.59
    Act Density 4.035%

    No Known Activations