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

    Neuronpedia

    INDEX
    Explanations

    adjectives modified by '-est' or 'ful' which indicate a higher degree of a certain quality, such as the 'prettiest' or 'craziest'

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to amusing or bizarre experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aram
    -0.61
     constitu
    -0.59
     Vi
    -0.58
     Domain
    -0.57
     alone
    -0.57
     Sag
    -0.57
     pregn
    -0.57
     Pax
    -0.56
     Indo
    -0.56
     Hak
    -0.56
    POSITIVE LOGITS
    iest
    2.03
    iness
    1.89
    ily
    1.74
    iful
    1.73
    ier
    1.71
    ied
    1.46
    ies
    1.42
    ifully
    1.42
    ying
    1.36
    eless
    1.32
    Act Density 0.114%

    No Known Activations