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

    Neuronpedia

    INDEX
    Explanations

    mentions of being the first in a particular context or achievement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "first" related to notable achievements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    morph
    -0.79
    maps
    -0.75
    mund
    -0.73
    aths
    -0.68
    styles
    -0.67
    iety
    -0.66
    bos
    -0.66
    md
    -0.64
    alus
    -0.64
    each
    -0.63
    POSITIVE LOGITS
     responders
    1.13
     baseman
    1.05
     installment
    0.92
     foray
    0.90
     casualty
    0.90
    born
    0.88
     hurdle
    0.86
     glimpse
    0.81
     incarnation
    0.80
     thing
    0.78
    Act Density 0.055%

    No Known Activations