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

    Neuronpedia

    INDEX
    Explanations

    references to specific cities or locations

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "AND" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reeves
    -0.73
     masters
    -0.67
     tele
    -0.62
     McKin
    -0.61
    sters
    -0.60
     Felix
    -0.59
     Mobil
    -0.59
     Ful
    -0.58
     Tec
    -0.58
     Cal
    -0.57
    POSITIVE LOGITS
    AND
    4.13
    ands
    1.97
    ander
    1.62
    anded
    1.45
    and
    1.40
    anders
    1.36
    BUT
    1.30
    ART
    1.30
    ADE
    1.29
    ANT
    1.28
    Act Density 0.012%

    No Known Activations