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

    Neuronpedia

    INDEX
    Explanations

    ratios and numerical relationships within text

    oai_token-act-pair · gpt-3.5-turbo

    textual references to statistical ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gotten
    -0.88
    inelli
    -0.79
    dream
    -0.79
    uggage
    -0.71
    REAM
    -0.68
    usions
    -0.64
    pocket
    -0.64
    asts
    -0.64
    bies
    -0.63
    ORE
    -0.63
    POSITIVE LOGITS
    xual
    1.08
     ratios
    0.97
     ratio
    0.97
     mismatch
    0.85
    yip
    0.85
     numer
    0.79
    ically
    0.75
    ical
    0.72
     sum
    0.70
    nces
    0.69
    Act Density 0.018%

    No Known Activations