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

    Neuronpedia

    INDEX
    Explanations

    references to various "forms" or "types" in a textual context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AJAS
    -0.82
     Keegan
    -0.80
     متعلقه
    -0.79
     NCC
    -0.79
    pædia
    -0.77
     Gä
    -0.77
     arbitrage
    -0.77
     Bracken
    -0.76
     cellpadding
    -0.75
    wyczaj
    -0.75
    POSITIVE LOGITS
     FORM
    1.66
     Forms
    1.56
     Form
    1.55
    Form
    1.47
     FORMS
    1.45
    form
    1.41
    FORM
    1.39
    Forms
    1.38
     forms
    1.38
    forms
    1.37
    Act Density 0.133%

    No Known Activations