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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations involving exponents and powers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Pyle
    -0.74
    FieldError
    -0.73
     Keith
    -0.71
    Keith
    -0.70
     Roz
    -0.70
    findBy
    -0.69
    Kiel
    -0.69
    Kal
    -0.68
     Genova
    -0.68
     delar
    -0.67
    POSITIVE LOGITS
    )^{
    1.09
    .^
    1.09
    )^
    1.04
    ))^
    1.03
    "^
    1.02
    $^{
    1.00
    })^
    1.00
    })^{
    0.98
    %^
    0.98
    ]^
    0.98
    Act Density 1.215%

    No Known Activations