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

    Neuronpedia

    INDEX
    Explanations

    action verbs that are in the present participle form, often ending in '-ing'

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles indicating ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ère
    -0.75
    ensis
    -0.69
    ilaterally
    -0.67
    retty
    -0.65
    vu
    -0.65
    ividually
    -0.65
    bal
    -0.64
    ãĥĩãĤ£
    -0.63
    ternity
    -0.59
    farious
    -0.59
    POSITIVE LOGITS
    HAM
    0.62
    BUS
    0.62
     guiActive
    0.61
     electron
    0.61
    tons
    0.60
    redients
    0.59
    LY
    0.59
     Horror
    0.56
     largeDownload
    0.54
    wcsstore
    0.53
    Act Density 0.223%

    No Known Activations