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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with specific classifications or categorizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¸ĺรรม
    -0.15
    ãĥ¼ãĥĭ
    -0.14
    à¸Ľà¸£à¸°
    -0.14
     Unity
    -0.14
    udu
    -0.14
    usu
    -0.14
     passive
    -0.13
    rror
    -0.13
    ahn
    -0.13
    Unity
    -0.13
    POSITIVE LOGITS
     Burl
    0.15
    fol
    0.14
    (DBG
    0.14
     пÑĢоÑĩ
    0.14
    ,[],
    0.14
     WithEvents
    0.14
    auty
    0.14
    utom
    0.13
    issional
    0.13
     Fresh
    0.13
    Act Density 0.031%

    No Known Activations