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

    Neuronpedia

    INDEX
    Explanations

    references to seeing or visual perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     universitarios
    -0.77
     lunghi
    -0.77
     loisirs
    -0.76
     bezeichneter
    -0.73
    knapp
    -0.72
     Mainland
    -0.72
     Hofmann
    -0.72
     Poehler
    -0.71
     @"/
    -0.71
    Grath
    -0.70
    POSITIVE LOGITS
     Sees
    1.72
     sees
    1.71
     saw
    1.57
     see
    1.57
     seen
    1.55
     SEE
    1.48
    Saw
    1.46
     SEEN
    1.45
    See
    1.45
     Seen
    1.43
    Act Density 0.139%

    No Known Activations