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

    Neuronpedia

    INDEX
    Explanations

    references to various departments and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sut
    -0.18
    immers
    -0.17
    ieber
    -0.17
    immer
    -0.16
    ups
    -0.15
    abbo
    -0.15
    lege
    -0.15
    fall
    -0.14
    ubyte
    -0.14
    гÑĥ
    -0.14
    POSITIVE LOGITS
    al
    0.25
    artment
    0.25
    ally
    0.21
    ial
    0.21
    als
    0.21
    alist
    0.20
    wide
    0.19
    份
    0.17
    ries
    0.16
    aliz
    0.16
    Act Density 0.032%

    No Known Activations