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

    Neuronpedia

    INDEX
    Explanations

    quantitative metrics and measurements related to studies and experiments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.95
    ArgsConstructor
    -0.90
     defaultstate
    -0.81
     &___
    -0.77
    endphp
    -0.76
    IntoConstraints
    -0.75
     linkovi
    -0.71
    PreferredItem
    -0.70
    protoimpl
    -0.69
    awtextra
    -0.68
    POSITIVE LOGITS
    overall
    0.67
    Overall
    0.66
     insgesamt
    0.66
     Altogether
    0.66
     comples
    0.65
    Total
    0.64
     overall
    0.63
    Totale
    0.62
     Gesamt
    0.62
     Insgesamt
    0.61
    Act Density 0.176%

    No Known Activations