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

    Neuronpedia

    INDEX
    Explanations

    the occurrences of text at the bottom or side of a document

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating location or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dayName
    -0.76
    20439
    -0.73
    />
    -0.65
    resy
    -0.63
    etic
    -0.59
    ener
    -0.58
    wcsstore
    -0.58
     distur
    -0.58
    REF
    -0.57
    .''.
    -0.57
    POSITIVE LOGITS
     each
    0.85
     the
    0.81
    rium
    0.75
     nowhere
    0.75
    eatures
    0.73
     scrimmage
    0.73
     our
    0.68
     every
    0.68
    course
    0.67
    ellar
    0.66
    Act Density 0.111%

    No Known Activations