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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly those with multiple zeros

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auer
    -0.15
    ignet
    -0.15
    ÑĪов
    -0.14
    avo
    -0.14
    elfast
    -0.14
    ihat
    -0.14
    EXT
    -0.14
    576
    -0.13
    IFEST
    -0.13
    ASC
    -0.13
    POSITIVE LOGITS
    важа
    0.17
    outu
    0.16
    ãĥŃãĥ¼
    0.15
    ãĤ¯ãĥĪ
    0.14
    iros
    0.14
    kte
    0.14
     bunny
    0.14
    sect
    0.14
    .Object
    0.14
    ches
    0.13
    Act Density 0.000%

    No Known Activations