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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values, symbols, and editing indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ucapnya
    -0.38
     ujarnya
    -0.35
     distribu
    -0.32
     inspección
    -0.31
    tront
    -0.31
     distribución
    -0.31
    chel
    -0.30
     pungkas
    -0.30
    족
    -0.30
     Circulation
    -0.30
    POSITIVE LOGITS
    ScopeManager
    0.91
     MainAxisSize
    0.78
     виправивши
    0.78
     @"/
    0.75
    indd
    0.68
    FormTagHelper
    0.68
    Tikang
    0.67
    enumii
    0.65
     Exactos
    0.65
    :✨
    0.64
    Act Density 0.286%

    No Known Activations