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

    Neuronpedia

    INDEX
    Explanations

    the word "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nop
    -0.16
    integral
    -0.15
    emann
    -0.15
    ĮĴ
    -0.14
    -validate
    -0.14
    /slick
    -0.14
    idon
    -0.14
    Ãłng
    -0.14
    andro
    -0.14
    561
    -0.14
    POSITIVE LOGITS
    Directive
    0.15
    uzz
    0.15
    DC
    0.14
    CTR
    0.14
    iddles
    0.14
    ddy
    0.14
     Vac
    0.14
    ache
    0.14
    directive
    0.13
    coma
    0.13
    Act Density 0.059%

    No Known Activations