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

    Neuronpedia

    INDEX
    Explanations

    unique identifier patterns like numbers with certain punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "11."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tradem
    -1.24
     volunte
    -1.04
     srf
    -0.95
     millenn
    -0.92
     exha
    -0.90
     conflic
    -0.88
     practition
    -0.88
    awaru
    -0.87
    ¥ŀ
    -0.86
     tremend
    -0.83
    POSITIVE LOGITS
    88
    1.14
    87
    1.14
    81
    1.07
    66
    1.06
    41
    1.06
    01
    1.06
    83
    1.05
    77
    1.04
    43
    1.03
    61
    1.01
    Act Density 0.019%

    No Known Activations