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

    Neuronpedia

    INDEX
    Explanations

    words related to visual perception or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     universitarios
    -0.75
     loisirs
    -0.72
     Hofmann
    -0.71
    Grath
    -0.71
    unately
    -0.68
    knapp
    -0.67
     lunghi
    -0.67
     Gregorian
    -0.65
     bezeichneter
    -0.65
     Pokud
    -0.63
    POSITIVE LOGITS
     sees
    1.90
     Sees
    1.87
     see
    1.84
     SEE
    1.72
    See
    1.71
     See
    1.67
     saw
    1.65
    see
    1.63
     seeing
    1.62
     seen
    1.59
    Act Density 0.125%

    No Known Activations