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

    Neuronpedia

    INDEX
    Explanations

    mathematical and statistical terminology related to equations and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lesh
    -0.16
    acute
    -0.15
    èij
    -0.15
    .dtype
    -0.15
    Lou
    -0.14
    reon
    -0.14
     Lov
    -0.14
     Loves
    -0.14
    ogue
    -0.13
    ļĮ
    -0.13
    POSITIVE LOGITS
     exp
    0.21
    exp
    0.19
     factor
    0.18
    (exp
    0.17
    factor
    0.17
     EXP
    0.16
     Factor
    0.16
     factorial
    0.16
     factors
    0.16
    (prod
    0.16
    Act Density 0.189%

    No Known Activations