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

    Neuronpedia

    INDEX
    Explanations

    periods and phrases indicating the end of statements or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ³
    -0.14
    ayette
    -0.14
    anas
    -0.14
    ÑĥлÑİ
    -0.14
     tool
    -0.14
    è´¹çĶ¨
    -0.14
    aks
    -0.13
     monopol
    -0.13
    ำ
    -0.13
    udy
    -0.13
    POSITIVE LOGITS
    AFX
    0.15
    ogram
    0.15
     Mickey
    0.15
    qli
    0.14
    (global
    0.14
     Dann
    0.14
    glob
    0.14
    osu
    0.14
     Glob
    0.14
     Wein
    0.13
    Act Density 0.004%

    No Known Activations