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

    Neuronpedia

    INDEX
    Explanations

    references to groups of individuals and their complex interactions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.20
    AndEndTag
    -1.10
     <>",
    -1.03
    ⓧ
    -0.96
    IntoConstraints
    -0.95
     ویکی‌پدیا
    -0.93
    SourceChecksum
    -0.93
     تضيفلها
    -0.93
     ivelany
    -0.92
    adaptiveStyles
    -0.90
    POSITIVE LOGITS
     syndrome
    0.48
     so
    0.44
    ché
    0.44
    oni
    0.44
    cato
    0.43
     th
    0.42
    CHED
    0.42
     Why
    0.42
    ONI
    0.41
     amp
    0.41
    Act Density 0.289%

    No Known Activations