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

    Neuronpedia

    INDEX
    Explanations

    references to images and their credits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ActionTypes
    -0.22
    831
    -0.16
    عÙĨÙĪاÙĨ
    -0.15
    avad
    -0.14
     fond
    -0.14
    _HDR
    -0.14
    erson
    -0.14
    Ø´ÙĨ
    -0.14
    gil
    -0.14
    arrant
    -0.14
    POSITIVE LOGITS
     PA
    0.28
    PA
    0.27
    _PA
    0.20
     PRESS
    0.20
    Mirror
    0.20
     Press
    0.19
     Mirror
    0.19
     Pictures
    0.18
    mirror
    0.18
    Picture
    0.18
    Act Density 0.015%

    No Known Activations