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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "see" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hofmann
    -0.71
     Wadsworth
    -0.70
     Hoffman
    -0.68
    knapp
    -0.67
     universitarios
    -0.66
    Grath
    -0.63
     loisirs
    -0.63
     Kaufman
    -0.63
    metaData
    -0.63
    kowym
    -0.61
    POSITIVE LOGITS
     see
    2.45
     sees
    2.28
    See
    2.15
    see
    2.12
     SEE
    2.09
     See
    2.06
     Sees
    2.01
     seeing
    1.88
    SEE
    1.81
    sees
    1.75
    Act Density 0.081%

    No Known Activations