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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to various types or categories of "forms."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AJAS
    -0.87
    "])
    -0.87
     Keegan
    -0.86
    "]);
    -0.82
     Cáceres
    -0.82
     Leal
    -0.81
    ]++;
    -0.78
     Bracken
    -0.77
    lihood
    -0.77
     arbitrage
    -0.77
    POSITIVE LOGITS
     FORM
    1.81
     Form
    1.70
     Forms
    1.64
    form
    1.63
    Form
    1.60
     form
    1.59
     forms
    1.57
    FORM
    1.56
     FORMS
    1.55
    forms
    1.50
    Act Density 0.100%

    No Known Activations