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

    Neuronpedia

    INDEX
    Explanations

    references to sources or citations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovny
    -0.16
    eci
    -0.15
    äch
    -0.14
    ocu
    -0.14
    овоÑĢ
    -0.14
     pint
    -0.14
     normal
    -0.14
    irse
    -0.14
    urdu
    -0.14
     Schl
    -0.13
    POSITIVE LOGITS
    hunt
    0.15
    ussia
    0.15
    ynos
    0.15
    ongo
    0.14
    ilyn
    0.14
    ãĤīãģļ
    0.14
    gaard
    0.14
    Sizer
    0.14
    amoto
    0.13
    ppo
    0.13
    Act Density 0.009%

    No Known Activations