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

    Neuronpedia

    INDEX
    Explanations

    captions or descriptions of images

    oai_token-act-pair · gpt-3.5-turbo

    references to images and visual content within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uren
    -0.78
    uca
    -0.73
    ilty
    -0.72
     hus
    -0.68
    onom
    -0.66
    em
    -0.63
    gat
    -0.62
    ym
    -0.62
     stump
    -0.62
     surrog
    -0.62
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.99
    --+
    0.80
    ROR
    0.78
    ################################
    0.77
    ################
    0.75
    --------------------------------------------------------
    0.72
     Mehran
    0.72
    ||||
    0.72
     Ré
    0.72
     [+
    0.72
    Act Density 0.134%

    No Known Activations