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

    Neuronpedia

    INDEX
    Explanations

    elements related to actions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eki
    -0.17
    æ¯
    -0.15
    amus
    -0.15
     tá»Ń
    -0.15
    orus
    -0.14
     drunken
    -0.13
    ehen
    -0.13
    stinence
    -0.13
    <X
    -0.13
    amat
    -0.13
    POSITIVE LOGITS
    MMdd
    0.14
    /cop
    0.14
    chwitz
    0.13
     treff
    0.13
    YPE
    0.13
    ifndef
    0.13
    'gc
    0.13
    'nda
    0.13
    herits
    0.13
    ublic
    0.13
    Act Density 0.108%

    No Known Activations