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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    مصادر
    -0.93
     Roskov
    -0.83
     kasarigan
    -0.82
     Efq
    -0.80
     itſelf
    -0.77
     myſelf
    -0.77
    Collegamenti
    -0.77
     houſe
    -0.75
     ſtill
    -0.75
     morire
    -0.75
    POSITIVE LOGITS
     Rica
    0.66
    tifkan
    0.59
    phorbia
    0.57
    TagMode
    0.56
     Gal
    0.55
    runApp
    0.55
     Fra
    0.54
    HtmlAttribute
    0.54
     Kna
    0.53
    OPHY
    0.53
    Act Density 0.004%

    No Known Activations