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

    Neuronpedia

    INDEX
    Explanations

    mentions of the concept of 'first'

    oai_token-act-pair · gpt-3.5-turbo

    references to first occurrences or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    politics
    -0.77
    md
    -0.72
    lag
    -0.72
    til
    -0.71
    lang
    -0.67
    each
    -0.65
    rice
    -0.64
    behind
    -0.64
    PLIED
    -0.64
    along
    -0.63
    POSITIVE LOGITS
     glimpse
    1.02
     ever
    1.01
     batch
    0.97
     EVER
    0.91
     tentative
    0.83
     incarnation
    0.78
     foray
    0.77
     installment
    0.77
     casualty
    0.76
     baseman
    0.76
    Act Density 0.088%

    No Known Activations