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

    Neuronpedia

    INDEX
    Explanations

    dates or numbers, particularly the number 15

    oai_token-act-pair · gpt-3.5-turbo

    references to the number "15" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.01
    undai
    -0.87
    ascus
    -0.86
     tremend
    -0.85
     pse
    -0.81
    atis
    -0.81
    psey
    -0.78
    iqueness
    -0.77
    ¥ŀ
    -0.76
     srf
    -0.75
    POSITIVE LOGITS
    th
    0.97
    20
    0.92
    15
    0.90
    85
    0.84
    55
    0.83
    50
    0.83
    25
    0.83
    33
    0.82
    %:
    0.81
    35
    0.81
    Act Density 0.031%

    No Known Activations