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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to the name "Cole"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Cole" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igans
    -0.61
    icles
    -0.60
     loader
    -0.60
    iating
    -0.60
     quo
    -0.57
    hip
    -0.57
     Compass
    -0.57
    icip
    -0.56
    icle
    -0.56
    ial
    -0.56
    POSITIVE LOGITS
    tto
    1.57
    tta
    1.40
    tti
    1.40
    lli
    1.12
    cule
    1.07
    ttes
    1.00
    brate
    1.00
    lla
    0.99
    tt
    0.98
    llo
    0.97
    Act Density 0.071%

    No Known Activations