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

    Neuronpedia

    INDEX
    Explanations

    negations and conditional phrases that express uncertainty or caution

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Jefus
    -0.94
     Chriftian
    -0.90
     ſche
    -0.87
    GEBURTSDATUM
    -0.84
     Majefty
    -0.83
     moschino
    -0.82
     fevere
    -0.80
    Personensuche
    -0.80
     Eocene
    -0.79
     pleaſure
    -0.79
    POSITIVE LOGITS
     have
    1.33
     be
    1.23
     not
    1.15
     can
    1.13
     also
    0.98
     do
    0.97
     will
    0.95
     make
    0.93
     could
    0.93
     had
    0.92
    Act Density 3.926%

    No Known Activations