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

    Neuronpedia

    INDEX
    Explanations

    adverbs ending in -ly

    oai_token-act-pair · gpt-3.5-turbo

    adverbs and related modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pirate
    -0.65
     treasure
    -0.64
     plate
    -0.62
    ocene
    -0.61
     Fairy
    -0.60
    letter
    -0.60
    fr
    -0.59
     vest
    -0.58
     mouth
    -0.57
     Moonlight
    -0.57
    POSITIVE LOGITS
    terness
    0.86
    iration
    0.73
     conclud
    0.71
    olate
    0.71
    uthor
    0.68
    ccording
    0.68
     speaking
    0.67
    entimes
    0.67
     trained
    0.67
     compr
    0.66
    Act Density 0.043%

    No Known Activations