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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ongoing activities or states

    oai_token-act-pair · gpt-3.5-turbo

    present tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Telesc
    -0.82
     Telescope
    -0.67
     cosmos
    -0.63
    acters
    -0.62
    fuck
    -0.62
     fuck
    -0.62
     civilizations
    -0.61
    ossom
    -0.61
     greatness
    -0.61
     Hitch
    -0.60
    POSITIVE LOGITS
     slated
    1.06
     now
    1.04
     currently
    1.01
     suing
    0.99
     expected
    0.99
     unlikely
    0.98
     scheduled
    0.98
     barred
    0.98
     reportedly
    0.96
     believed
    0.95
    Act Density 0.541%

    No Known Activations