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

    Neuronpedia

    INDEX
    Explanations

    identifiers and numeric comparisons

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    </h1>
    -0.49
    ьа
    -0.48
     AssemblyProduct
    -0.46
     Elbe
    -0.46
     dos
    -0.45
    клопе
    -0.43
    djang
    -0.42
    (&$
    -0.41
    culated
    -0.40
    :])
    -0.39
    POSITIVE LOGITS
     étoit
    0.88
     auroit
    0.84
     avoient
    0.82
     étoient
    0.81
     automatiques
    0.78
     Monfieur
    0.78
     Theſe
    0.73
     feroit
    0.71
     poffe
    0.70
     quelcon
    0.70
    Act Density 0.460%

    No Known Activations