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

    Neuronpedia

    INDEX
    Explanations

    phrases or contexts indicating observation or vision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    knapp
    -0.77
    Grath
    -0.74
     bezeichneter
    -0.74
     Hofmann
    -0.74
     lunghi
    -0.73
     loisirs
    -0.72
     @"/
    -0.71
     Marek
    -0.71
    unately
    -0.69
    ografija
    -0.69
    POSITIVE LOGITS
     Sees
    1.65
     sees
    1.57
     see
    1.48
     seen
    1.45
     saw
    1.43
     SEE
    1.42
    Saw
    1.39
    See
    1.39
     SEEN
    1.36
     Seen
    1.34
    Act Density 0.130%

    No Known Activations