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

    Neuronpedia

    INDEX
    Explanations

    present participle verbs ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    words in various forms, particularly those related to verb tenses and endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.75
    emale
    -0.70
    essage
    -0.57
     Gaw
    -0.56
    accompan
    -0.56
     parap
    -0.56
    åŃIJ
    -0.55
     Staples
    -0.55
     [&
    -0.54
     Barkley
    -0.53
    POSITIVE LOGITS
    rad
    0.60
    leans
    0.60
    poses
    0.59
     largeDownload
    0.59
    chant
    0.58
    clair
    0.57
    chwitz
    0.57
    iliate
    0.57
    pos
    0.57
    aqu
    0.56
    Act Density 0.038%

    No Known Activations