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

    Neuronpedia

    INDEX
    Explanations

    negations or words that indicate absence or disagreement

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    rsiniz
    -0.85
    SerializedName
    -0.84
     Bourgoin
    -0.83
     DataTypes
    -0.80
     gerichtet
    -0.80
    جوايز
    -0.79
     angekommen
    -0.78
    WriteBarrier
    -0.78
    허
    -0.77
    Portály
    -0.77
    POSITIVE LOGITS
    Gimme
    0.62
    робнее
    0.59
    сихо
    0.59
     Besch
    0.59
     EAS
    0.57
     tack
    0.56
    strptime
    0.56
    sprechend
    0.56
     rente
    0.56
     Gier
    0.56
    Act Density 0.019%

    No Known Activations