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

    Neuronpedia

    INDEX
    Explanations

    words related to results, data, and information pertaining to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monroe
    -0.06
    jan
    -0.06
    ahn
    -0.05
     Buckley
    -0.05
    Ìģ
    -0.05
     registers
    -0.05
     Tow
    -0.05
     Guest
    -0.05
    ard
    -0.05
    (fn
    -0.05
    POSITIVE LOGITS
    ëij
    0.08
    à¥įफ
    0.08
    erville
    0.07
    edla
    0.07
    akov
    0.07
    ulado
    0.07
    _OCCURRED
    0.07
    adu
    0.07
    Intialized
    0.07
    BOR
    0.07
    Act Density 0.001%

    No Known Activations