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

    Neuronpedia

    INDEX
    Explanations

    commentary or annotations used for code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ------------------------------------------------
    -0.19
    ----------------------------------------------------------------
    -0.18
    ----------------
    -0.16
    --------------------------------------------------------------------------------
    -0.16
    wire
    -0.16
    ================================================================
    -0.15
    --------------------------------
    -0.15
    --------------------
    -0.15
    sg
    -0.15
    swire
    -0.15
    POSITIVE LOGITS
    s
    0.17
    TODO
    0.16
    undry
    0.15
    nds
    0.15
    ÏĤ
    0.14
    sik
    0.14
    Ùĩ
    0.14
    iance
    0.14
    ůj
    0.14
    itage
    0.14
    Act Density 0.095%

    No Known Activations