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

    Neuronpedia

    INDEX
    Explanations

    the presence of a start token in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.56
    ÁND
    -0.50
     vernac
    -0.48
    ده
    -0.47
    garet
    -0.47
    äns
    -0.47
     Chic
    -0.47
    felizmente
    -0.46
     today
    -0.46
    ropia
    -0.46
    POSITIVE LOGITS
    OGND
    0.92
     Signalez
    0.87
    (!__
    0.81
     للاسماء
    0.80
    MigrationBuilder
    0.80
     дописавши
    0.79
    GEBURTSDATUM
    0.76
    enumii
    0.70
     isNameExpr
    0.68
    RoutingModule
    0.66
    Act Density 0.013%

    No Known Activations