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

    Neuronpedia

    INDEX
    Explanations

    affirmative or definitive phrases that assert certainty and clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uraa
    -0.17
    itler
    -0.16
    égor
    -0.16
    zcze
    -0.15
    sg
    -0.15
    arella
    -0.15
    URITY
    -0.15
    swer
    -0.15
    odb
    -0.14
    utar
    -0.14
    POSITIVE LOGITS
    days
    0.15
    osh
    0.14
    lian
    0.14
    ErrorException
    0.14
    iki
    0.14
    erness
    0.14
    ana
    0.14
    168
    0.14
    oya
    0.13
    ach
    0.13
    Act Density 0.372%

    No Known Activations