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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical indicators or references to figures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    cline
    -0.83
     giro
    -0.74
    )}}{
    -0.74
    alz
    -0.72
     Bort
    -0.72
     Rooney
    -0.71
    بال
    -0.70
     Picchu
    -0.69
    ctc
    -0.69
     Él
    -0.68
    POSITIVE LOGITS
     Jeffries
    0.84
    horabuena
    0.77
    yā
    0.76
    itize
    0.75
    0.73
     Dummies
    0.72
    begingroup
    0.71
     paramString
    0.71
     Sinha
    0.71
     Fournier
    0.71
    Act Density 0.011%

    No Known Activations