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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative forms of adjectives

    oai_token-act-pair · gpt-3.5-turbo

    comparative and superlative forms of adjectives and adverbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.73
    HF
    -0.70
    chwitz
    -0.69
    EP
    -0.69
    ARDIS
    -0.67
    ILLE
    -0.66
    ainted
    -0.64
     1933
    -0.63
    ç«
    -0.63
    shire
    -0.62
    POSITIVE LOGITS
     than
    1.33
     Than
    1.18
    than
    1.14
    iating
    0.84
     sibling
    0.73
    atible
    0.73
    idge
    0.71
    iable
    0.69
     ado
    0.69
    izont
    0.68
    Act Density 0.064%

    No Known Activations