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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific labels or symbols associated with various entities or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umerable
    -0.81
    kson
    -0.78
    keepers
    -0.75
    assetsadobe
    -0.71
     behavi
    -0.70
    unci
    -0.70
     Pelosi
    -0.69
    ¯¯¯¯¯¯¯¯
    -0.69
    aiman
    -0.69
     cooperating
    -0.69
    POSITIVE LOGITS
    VII
    1.22
    XX
    1.02
    III
    0.97
    II
    0.90
    Sax
    0.88
    YY
    0.87
     XX
    0.85
    VI
    0.83
    xx
    0.80
    XY
    0.80
    Act Density 0.019%

    No Known Activations