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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific types of symbols or punctuation, particularly in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contextLoads
    -1.10
     Italijanski
    -1.09
    ]")]
    -1.07
     bezeichneter
    -1.06
     שוליים
    -1.04
     للاسماء
    -1.04
    MigrationBuilder
    -1.02
    theless
    -0.98
    AsUp
    -0.97
     Савезне
    -0.97
    POSITIVE LOGITS
    [-
    1.38
    [(
    1.35
    ["
    1.24
    [_
    1.21
    [$
    1.20
    [\
    1.06
    [
    0.99
    [{
    0.98
    ['
    0.96
    [:
    0.95
    Act Density 0.407%

    No Known Activations