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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mathematical or scientific concepts of integrals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    racks
    -0.70
     Langdon
    -0.69
    pho
    -0.67
     Hano
    -0.67
    Tempor
    -0.67
    ed
    -0.66
    a
    -0.65
    遣
    -0.64
     cervix
    -0.64
    TEMPLATES
    -0.64
    POSITIVE LOGITS
     Integral
    1.31
     integral
    1.20
    Integral
    1.20
    integral
    1.15
    %)$
    1.12
     integrals
    1.06
     Integrals
    0.90
    Добрый
    0.78
    ViewComponent
    0.73
    carril
    0.72
    Act Density 0.009%

    No Known Activations