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

    Neuronpedia

    INDEX
    Explanations

    references to events occurring after a specific action or trigger

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.80
    migrationBuilder
    -0.79
    complexContent
    -0.76
    ThroughAttribute
    -0.76
    لينكات
    -0.76
    MessageTagHelper
    -0.74
    hdashline
    -0.71
    coroutines
    -0.70
    ΑΙ
    -0.68
     gehouden
    -0.68
    POSITIVE LOGITS
     after
    1.74
    after
    1.68
     After
    1.63
    After
    1.63
     AFTER
    1.50
    AFTER
    1.46
     fter
    1.41
     dopo
    1.36
    Dopo
    1.27
     après
    1.26
    Act Density 0.775%

    No Known Activations