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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential or capability

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.95
    BagConstraints
    -0.91
    '):
    -0.88
     ')
    -0.87
     Ashraf
    -0.84
    WithIOException
    -0.82
    oa̍t
    -0.81
    "",
    -0.78
     CURIAM
    -0.77
    '));
    -0.77
    POSITIVE LOGITS
    ed
    0.61
     sorte
    0.54
    Bo
    0.52
     dön
    0.50
     bedo
    0.49
    <strong>
    0.48
    Te
    0.48
     موس
    0.48
    Mar
    0.48
    Don
    0.48
    Act Density 0.073%

    No Known Activations