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

    Neuronpedia

    INDEX
    Explanations

    words related to movement or change in position

    oai_token-act-pair · gpt-3.5-turbo

    words related to movement or transitions, specifically descending, trailing, and sliding actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wart
    -0.84
    fit
    -0.72
     Pigs
    -0.71
    ruit
    -0.71
     fry
    -0.68
    reen
    -0.66
    warts
    -0.64
    aires
    -0.63
    anan
    -0.62
    ottage
    -0.62
    POSITIVE LOGITS
     descending
    2.76
     ascending
    2.36
     trailing
    2.34
     sliding
    1.97
     desc
    1.57
     slipping
    1.40
     Desc
    1.32
     trailed
    1.29
     descended
    1.29
    desc
    1.27
    Act Density 0.033%

    No Known Activations