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

    Neuronpedia

    INDEX
    Explanations

    verbs related to legislative or formal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.75
    taboola
    -0.65
    nah
    -0.64
    won
    -0.64
    rw
    -0.61
    é¾įåĸļ士
    -0.61
    tis
    -0.61
    SPONSORED
    -0.60
    folk
    -0.60
     selves
    -0.59
    POSITIVE LOGITS
     himself
    1.29
     his
    0.96
     Himself
    0.87
     herself
    0.85
     tirelessly
    0.72
     diagrams
    0.70
     pioneering
    0.69
     seminal
    0.69
    ographs
    0.67
     extensively
    0.66
    Act Density 0.280%

    No Known Activations