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

    Neuronpedia

    INDEX
    Explanations

    the presence of the substring "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /***/
    -0.83
    XMLSchema
    -0.77
     TestBed
    -0.77
     ModelExpression
    -0.72
    digarh
    -0.72
    IsMutable
    -0.72
    haustible
    -0.69
    ercises
    -0.69
    migrationBuilder
    -0.69
    ibatis
    -0.69
    POSITIVE LOGITS
    on
    2.69
    ON
    2.35
    ons
    2.02
    onn
    1.55
    oned
    1.53
    ONS
    1.50
    ón
    1.46
    onz
    1.43
    ron
    1.42
    ont
    1.42
    Act Density 0.163%

    No Known Activations