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

    Neuronpedia

    INDEX
    Explanations

    comparisons or relationships involving size or strength

    oai_token-act-pair · gpt-3.5-turbo

    comparative and relational terms regarding size, age, loyalty, and other attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.60
    Quote
    -0.58
    ellectual
    -0.57
     Ave
    -0.55
    MSN
    -0.55
    hemy
    -0.54
     Advertisement
    -0.54
     PAT
    -0.54
     Normandy
    -0.54
    ilet
    -0.53
    POSITIVE LOGITS
     resembling
    0.94
    ascript
    0.87
     enough
    0.83
    itaire
    0.77
     resembles
    0.73
     vers
    0.73
     describ
    0.72
    tained
    0.72
     resembled
    0.70
    enough
    0.70
    Act Density 0.319%

    No Known Activations