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

    Neuronpedia

    INDEX
    Explanations

    the presence of underscores in a structured format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.83
    ?";
    -0.72
    />";
    -0.71
    horabuena
    -0.71
     MÁ
    -0.64
     tslint
    -0.63
     themſelves
    -0.62
    SequentialGroup
    -0.61
     HasFactory
    -0.60
     שוליים
    -0.59
    POSITIVE LOGITS
     nahilalakip
    0.78
    Mitglieder
    0.63
    remel
    0.63
    vallis
    0.63
    laceae
    0.61
    benhavn
    0.60
     Picchu
    0.60
    ValueStyle
    0.59
     Landis
    0.58
     Scotia
    0.57
    Act Density 0.008%

    No Known Activations