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

    Neuronpedia

    INDEX
    Explanations

    ariations of the phrase "you see"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "you'll see" along with various observations or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wake
    -0.72
    ovie
    -0.70
    onto
    -0.66
    inion
    -0.65
     agric
    -0.63
    trap
    -0.63
    ella
    -0.63
     adolesc
    -0.61
    union
    -0.61
    idity
    -0.61
    POSITIVE LOGITS
    dust
    1.00
     parallels
    0.83
     similarities
    0.76
     signs
    0.74
     flashes
    0.73
     lots
    0.72
     them
    0.69
    peak
    0.69
     glimps
    0.69
    inelli
    0.69
    Act Density 0.075%

    No Known Activations