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

    Neuronpedia

    INDEX
    Explanations

    numbers or numerical patterns that are repeated across different sections of the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number nine or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itable
    -0.75
    itably
    -0.73
    iator
    -0.71
    iated
    -0.70
     Lauder
    -0.70
    ivari
    -0.68
    iating
    -0.67
    escription
    -0.66
     Ukrain
    -0.65
     bleach
    -0.65
    POSITIVE LOGITS
    9999
    1.30
    999
    1.26
    090
    1.17
    06
    1.17
    07
    1.12
    08
    1.09
    04
    1.08
    03
    1.06
    09
    1.04
    NEWS
    0.99
    Act Density 0.059%

    No Known Activations