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

    Neuronpedia

    INDEX
    Explanations

    code elements related to functions and data handling in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ůst
    -0.15
    .Foundation
    -0.15
    imit
    -0.14
    acea
    -0.14
    ãĥĩãĥ«
    -0.13
    anca
    -0.13
     Welch
    -0.13
    \Bundle
    -0.13
    ково
    -0.13
    orna
    -0.13
    POSITIVE LOGITS
    zahl
    0.17
    ëĸ
    0.16
     ÑĢаÑģк
    0.16
    erson
    0.15
    rous
    0.15
    inary
    0.15
    wer
    0.14
    chin
    0.14
    kiye
    0.14
    rouw
    0.14
    Act Density 0.029%

    No Known Activations