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

    Neuronpedia

    INDEX
    Explanations

    arrays or lists with specific formatting or structure

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    STERY
    -0.45
     Ho
    -0.44
    chooser
    -0.42
     voto
    -0.41
     selv
    -0.40
    存于互联网档案馆
    -0.40
     vorstellen
    -0.40
    المكان
    -0.39
     I
    -0.39
    logrus
    -0.39
    POSITIVE LOGITS
    ंदीखरीदारी
    0.84
     Shakspeare
    0.79
    GEBURTS
    0.76
    >--}}
    0.76
    ISupport
    0.75
    principalTable
    0.71
     Herm
    0.71
    IsContent
    0.70
    WriteAttribute
    0.70
    )__
    0.69
    Act Density 0.004%

    No Known Activations