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

    Neuronpedia

    INDEX
    Explanations

    data in an unusual text format that includes a mix of English and special characters

    oai_token-act-pair · gpt-3.5-turbo

    sequences of unique characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     strugg
    -0.82
     denomin
    -0.77
    vertisement
    -0.76
    axter
    -0.75
    ¥ŀ
    -0.75
     reconc
    -0.74
    wcs
    -0.74
     accrued
    -0.73
     outsider
    -0.73
     mathemat
    -0.71
    POSITIVE LOGITS
    «
    0.93
    âĶĢâĶĢâĶĢâĶĢ
    0.92
     ÙĪ
    0.90
    ivas
    0.87
    ABLE
    0.85
    =#
    0.83
    eers
    0.83
    anical
    0.82
    د
    0.82
    eor
    0.82
    Act Density 0.019%

    No Known Activations