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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing something out of the ordinary or unique

    oai_token-act-pair · gpt-3.5-turbo

    words that describe notable or exceptional qualities and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avering
    -0.70
    SEA
    -0.67
    enegger
    -0.66
     Cosponsors
    -0.64
    ancock
    -0.62
     majority
    -0.60
    ploy
    -0.60
    veyard
    -0.58
     Psychiat
    -0.57
    ighed
    -0.57
    POSITIVE LOGITS
     happened
    0.77
    ntil
    0.75
    else
    0.75
     else
    0.72
     happening
    0.71
    iates
    0.71
     happens
    0.71
    oward
    0.71
     transpired
    0.71
     happ
    0.70
    Act Density 0.089%

    No Known Activations