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

    Neuronpedia

    INDEX
    Explanations

    names of characters and actors in a film or show

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     faſt
    -0.67
     raiſ
    -0.65
     greateſt
    -0.65
     Majefty
    -0.61
    ſelf
    -0.59
     pleaſure
    -0.58
     Jefus
    -0.57
     ſeveral
    -0.57
     Eſ
    -0.56
     Reſ
    -0.56
    POSITIVE LOGITS
    +#+#
    0.70
    GEBURTSDATUM
    0.60
    makeConstraints
    0.57
     فريبيس
    0.57
    💼
    0.56
    migrationBuilder
    0.56
    TintMode
    0.55
    RegressionTest
    0.54
    unknownFields
    0.54
    MemoryWarning
    0.53
    Act Density 0.010%

    No Known Activations