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

    Neuronpedia

    INDEX
    Explanations

    references to images or visual representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GeoNames
    -0.62
     Graff
    -0.59
    hoenix
    -0.59
     Holtz
    -0.58
     Hoffman
    -0.58
     Hofmann
    -0.58
    colades
    -0.56
     Haas
    -0.53
     Folly
    -0.53
    Santis
    -0.52
    POSITIVE LOGITS
    picture
    1.20
    Picture
    1.16
     picture
    1.15
     PICTURE
    1.14
     Picture
    1.13
    PICTURE
    1.10
    pictures
    0.93
     Pictures
    0.91
     pictures
    0.90
    Pictures
    0.90
    Act Density 0.104%

    No Known Activations