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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to roles and contributions in a professional and academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ations
    -0.97
    ת
    -0.82
    ם
    -0.77
    gerald
    -0.70
     ThemeData
    -0.67
    ness
    -0.66
    в
    -0.66
     poprzed
    -0.65
    cccccccc
    -0.65
    cccc
    -0.65
    POSITIVE LOGITS
    yyyy
    1.22
    yyy
    1.21
    ey
    1.20
    tory
    1.15
    yy
    1.10
     ary
    1.10
     Chy
    1.08
     Smarty
    1.08
     Bly
    1.08
    URY
    1.06
    Act Density 0.852%

    No Known Activations