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

    Neuronpedia

    INDEX
    Explanations

    words related to vision and sight

    oai_token-act-pair · gpt-3.5-turbo

    words related to vision or sight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.89
    女
    -0.84
    76561
    -0.83
    accompan
    -0.78
    berman
    -0.72
    itaire
    -0.72
    regor
    -0.70
    é¾įå
    -0.70
    gee
    -0.68
    auder
    -0.67
    POSITIVE LOGITS
    mares
    1.22
    seeing
    0.92
    ened
    0.92
    edly
    0.90
    ful
    0.90
    enment
    0.88
    ight
    0.84
    ~~~~~~~~
    0.81
    ~~~~
    0.80
    edIn
    0.79
    Act Density 0.010%

    No Known Activations