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

    Neuronpedia

    INDEX
    Explanations

    references to downloadable or accessible content, particularly related to books and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dej
    -0.16
    lfw
    -0.15
     Lux
    -0.14
     Gent
    -0.14
     bottle
    -0.14
    lew
    -0.14
    392
    -0.14
    reas
    -0.14
    tember
    -0.13
    dogs
    -0.13
    POSITIVE LOGITS
    actal
    0.15
    aison
    0.15
     teb
    0.15
    abe
    0.14
    aba
    0.14
    ÄĽle
    0.14
    uctor
    0.14
    957
    0.14
    ħĮ
    0.14
    γά
    0.14
    Act Density 0.094%

    No Known Activations