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

    Neuronpedia

    INDEX
    Explanations

    lines or sections that denote a categorization, particularly in reference to content classification or organization

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    .
    -0.57
     
    -0.54
     (
    -0.53
    ’
    -0.52
    (
    -0.51
    ,
    -0.49
    I
    -0.44
     a
    -0.44
    '
    -0.43
    A
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    1.41
    Personensuche
    1.29
     виправивши
    1.28
    sizeCache
    1.22
    MigrationBuilder
    1.19
     saites
    1.19
     propOrder
    1.17
    featureID
    1.15
    OGND
    1.14
     "..\..\..\
    1.14
    Act Density 0.003%

    No Known Activations