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

    Neuronpedia

    INDEX
    Explanations

    proper names, particularly those of individuals, in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.82
    AutoField
    -0.75
    parsedMessage
    -0.74
    CloseOperation
    -0.73
     باخ
    -0.68
     Référence
    -0.67
     Roskov
    -0.66
     CanadaChoose
    -0.66
     doInBackground
    -0.66
     <<<<<<<<<<<<<<
    -0.65
    POSITIVE LOGITS
     innere
    0.60
    psis
    0.57
    PhysRev
    0.52
    $__
    0.52
    Musée
    0.52
     Inner
    0.51
    etus
    0.50
     schwere
    0.49
     punitive
    0.49
     Goss
    0.48
    Act Density 0.047%

    No Known Activations