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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data or specific coded values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     con
    -0.49
    uss
    -0.47
    ApiOperation
    -0.45
    ようになりました
    -0.44
    ようになります
    -0.44
    path
    -0.44
     path
    -0.42
     שוליים
    -0.42
     leiden
    -0.42
    temp
    -0.42
    POSITIVE LOGITS
     Reſ
    0.75
    twimg
    0.75
    styleType
    0.73
     HasFactory
    0.73
     betweenstory
    0.72
     Monfieur
    0.72
     cauſe
    0.71
     Anſ
    0.71
     Chriftian
    0.71
     Signalez
    0.70
    Act Density 0.002%

    No Known Activations