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

    Neuronpedia

    INDEX
    Explanations

    phrases related to continuity or duration

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific token indicating the end of input

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acons
    -0.67
     scissors
    -0.63
    oka
    -0.62
    trak
    -0.62
     Otto
    -0.62
     cents
    -0.61
     chau
    -0.60
    oma
    -0.59
    Percent
    -0.59
    aram
    -0.59
    POSITIVE LOGITS
     entirety
    1.29
     entire
    1.23
     remainder
    1.08
     lifespan
    1.04
     globe
    0.99
     ordeal
    0.99
     whole
    0.97
     course
    0.96
     duration
    0.95
     process
    0.93
    Act Density 0.077%

    No Known Activations