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

    Neuronpedia

    INDEX
    Explanations

    statements that provide explanations or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ñana
    -0.16
    iou
    -0.15
    ÌĢ
    -0.15
    readcr
    -0.14
     Ply
    -0.14
    _HW
    -0.14
    ACH
    -0.14
    .gs
    -0.14
    anni
    -0.14
     punk
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.17
    ¯ÃĤ
    0.17
    .Reporting
    0.16
    636
    0.15
    ']]],↵
    0.15
     Slov
    0.14
    /cms
    0.14
    اÙĪÛĮ
    0.14
     why
    0.14
    utex
    0.13
    Act Density 0.023%

    No Known Activations