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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming structure and syntax in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.78
    1
    -0.73
    The
    -0.72
    ,
    -0.71
    An
    -0.71
    In
    -0.68
    (
    -0.64
     
    -0.64
    ko
    -0.64
    -
    -0.64
    POSITIVE LOGITS
    GEBURTSDATUM
    1.68
    Geplaatst
    1.64
    تقاوى
    1.61
     Roskov
    1.61
     EconPapers
    1.60
    IndentedString
    1.55
    InjectAttribute
    1.55
    Autoritní
    1.53
     незавершена
    1.50
     beginnetje
    1.48
    Act Density 0.293%

    No Known Activations