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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or negative outcomes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    abestanden
    -0.66
    AsUp
    -0.65
    RenderAtEndOf
    -0.65
    parsedMessage
    -0.65
    BeginInit
    -0.64
    transQ
    -0.62
     betweenstory
    -0.61
    __":
    -0.61
    __":
    -0.60
     Dernière
    -0.60
    POSITIVE LOGITS
     ReSharper
    0.67
    iastes
    0.65
    didSet
    0.60
    őle
    0.59
     ‘
    0.58
    autoconfigure
    0.57
    หวัด
    0.56
    supset
    0.55
     a
    0.54
    glyphicon
    0.53
    Act Density 0.027%

    No Known Activations