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

    Neuronpedia

    INDEX
    Explanations

    specific dates and times written in a particular format

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses and their usage in dates and lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tes
    -0.98
     Tes
    -0.88
    ela
    -0.84
    elo
    -0.79
    PLIC
    -0.79
    TP
    -0.78
    ba
    -0.77
     Joel
    -0.77
    nesota
    -0.75
    FER
    -0.73
    POSITIVE LOGITS
    11
    1.32
     11
    1.23
    2011
    1.02
    111
    1.01
     2011
    0.99
     eleven
    0.94
     111
    0.93
    117
    0.92
    raph
    0.90
    November
    0.89
    Act Density 0.263%

    No Known Activations