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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to statistics and polling data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLS
    -0.17
    luet
    -0.15
    ingham
    -0.15
    ¥IJ
    -0.14
    endet
    -0.14
    edom
    -0.14
    عÙĨ
    -0.14
    tainment
    -0.14
    pto
    -0.14
     Reid
    -0.14
    POSITIVE LOGITS
     Vig
    0.15
     decom
    0.15
    è¼
    0.14
     HEAP
    0.14
     Fle
    0.14
    rone
    0.14
    rina
    0.14
    orge
    0.14
     Decom
    0.14
    nit
    0.13
    Act Density 0.013%

    No Known Activations