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

    Neuronpedia

    INDEX
    Explanations

    references to author names in academic citations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    orsese
    -0.80
     surla
    -0.73
    évaluateur
    -0.65
    __((
    -0.60
    TagMode
    -0.59
     <>",
    -0.58
    SuccessListener
    -0.58
    Distribuzione
    -0.56
    wahati
    -0.56
    ---*/
    -0.56
    POSITIVE LOGITS
    MigrationBuilder
    0.57
     مشين
    0.57
     kasarigan
    0.56
    folger
    0.54
    rafa
    0.51
     âgées
    0.50
     berta
    0.49
     Vikipedi
    0.48
    ANTS
    0.47
    Elev
    0.47
    Act Density 0.007%

    No Known Activations