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

    Neuronpedia

    INDEX
    Explanations

    colons used for introducing lists, explanations, or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оди
    -0.15
    igu
    -0.15
    oxel
    -0.15
    ings
    -0.14
     Wax
    -0.14
    ìĥģìĿĺ
    -0.14
     Ù¾ÛĮÚ©
    -0.14
    heck
    -0.14
    Ñŀ
    -0.14
    isse
    -0.14
    POSITIVE LOGITS
    aphael
    0.15
    icolon
    0.15
    sip
    0.15
     recipro
    0.15
    eload
    0.14
    -pocket
    0.14
    uls
    0.14
    clud
    0.14
    elage
    0.14
     Zion
    0.13
    Act Density 0.043%

    No Known Activations