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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number nine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    escription
    -0.85
    enture
    -0.81
    iated
    -0.78
    dayName
    -0.78
    REDACTED
    -0.75
     Lauder
    -0.75
    channelAvailability
    -0.75
    holders
    -0.74
    iating
    -0.72
    holder
    -0.71
    POSITIVE LOGITS
    999
    1.24
    9999
    1.23
    06
    1.15
    08
    1.10
    07
    1.09
    04
    1.07
    09
    1.04
    03
    1.04
    79
    1.01
    090
    1.01
    Act Density 0.044%

    No Known Activations