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

    Neuronpedia

    INDEX
    Explanations

    references to the acronym "NI" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ries
    -0.18
    arnings
    -0.16
    attered
    -0.14
    riers
    -0.14
    antaged
    -0.14
    ÙħÙĦØ©
    -0.14
    leaf
    -0.14
    efault
    -0.14
    raith
    -0.14
    aland
    -0.14
    POSITIVE LOGITS
    onds
    0.17
    114
    0.16
    iens
    0.15
    ÑĮи
    0.15
    838
    0.15
    inya
    0.15
    amo
    0.15
     n
    0.15
    Ïĩα
    0.14
     sho
    0.14
    Act Density 0.026%

    No Known Activations