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

    Neuronpedia

    INDEX
    Explanations

    active verbs that indicate actions, particularly in reports or testimonies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    verbs related to performing or executing actions (like "makes", "sets", "starts", "shows", "tells").

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    tal
    -0.77
    P
    -0.66
    to
    -0.65
    pr
    -0.65
    B
    -0.64
    the
    -0.64
    R
    -0.64
    tro
    -0.63
    t
    -0.62
    be
    -0.62
    POSITIVE LOGITS
    ')")
    1.08
     كومونز
    1.06
     itſelf
    1.04
    BibitemShut
    1.02
    AddTagHelper
    1.01
    ercises
    0.98
    ."</
    0.97
    fährt
    0.95
    Sucks
    0.93
    IMAS
    0.92
    Act Density 0.463%

    No Known Activations