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

    Neuronpedia

    INDEX
    Explanations

    references to significant events or feedback related to performance evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stm
    -0.16
    AGMA
    -0.15
    cke
    -0.14
     Thumbnails
    -0.14
     Commerce
    -0.14
    cken
    -0.14
    polator
    -0.14
    že
    -0.14
    thr
    -0.14
    ÄĻki
    -0.14
    POSITIVE LOGITS
    ãĤº
    0.15
    à¸Ļว
    0.14
    Bulk
    0.14
    иÑģÑĮ
    0.14
    arb
    0.14
     ello
    0.13
     Bulk
    0.13
    ult
    0.13
     اÙĦاع
    0.13
    LBL
    0.13
    Act Density 0.195%

    No Known Activations