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

    Neuronpedia

    INDEX
    Explanations

    sentences with direct quotes

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and various forms of written expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atos
    -0.77
    agos
    -0.70
    cipled
    -0.69
     shootout
    -0.67
     III
    -0.65
    rio
    -0.65
    oteric
    -0.64
    ciples
    -0.63
     trucks
    -0.61
     rifles
    -0.61
    POSITIVE LOGITS
     she
    1.93
    she
    1.91
    She
    1.89
     She
    1.78
     her
    1.76
     hers
    1.73
     SHE
    1.70
    Her
    1.64
     Ms
    1.50
     Her
    1.48
    Act Density 1.339%

    No Known Activations