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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers or citations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meli
    -0.15
    frei
    -0.15
    Motion
    -0.14
    ERV
    -0.14
    iese
    -0.14
    alem
    -0.13
    apel
    -0.13
    анÑĮ
    -0.13
    ottie
    -0.13
    ixel
    -0.13
    POSITIVE LOGITS
    201
    0.17
    arent
    0.16
    ÑĢеб
    0.16
     Twilight
    0.15
    anitize
    0.15
    æª
    0.15
     ãĢĪ
    0.14
    olini
    0.14
    ignKey
    0.14
     camb
    0.13
    Act Density 0.007%

    No Known Activations