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

    Neuronpedia

    INDEX
    Explanations

    numerical values or lists in a particular format that includes square brackets and numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or indices, likely indicating references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    escription
    -0.74
    REDACTED
    -0.74
     Lauder
    -0.73
    iator
    -0.72
    channelAvailability
    -0.71
     Ukrain
    -0.70
    itable
    -0.70
    ivari
    -0.70
    holders
    -0.69
    enture
    -0.68
    POSITIVE LOGITS
    999
    1.22
    9999
    1.22
    06
    1.19
    07
    1.13
    090
    1.12
    08
    1.10
    04
    1.07
    03
    1.07
    09
    1.06
    79
    1.00
    Act Density 0.053%

    No Known Activations