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

    Neuronpedia

    INDEX
    Explanations

    adjectives or adverbs depicting extreme qualities

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe negative or extreme conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zsche
    -0.61
    OPS
    -0.60
    ighth
    -0.60
    Ô
    -0.59
     secondary
    -0.59
    çĽ
    -0.59
    ¦
    -0.58
    Pope
    -0.56
     readings
    -0.56
     permitting
    -0.55
    POSITIVE LOGITS
    amus
    0.78
    ially
    0.73
    atically
    0.70
    !!!!!!!!
    0.69
    yip
    0.69
    ly
    0.68
    !!!!
    0.68
    idious
    0.67
    iated
    0.67
    ciating
    0.67
    Act Density 0.131%

    No Known Activations