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

    Neuronpedia

    INDEX
    Explanations

    instances of text that indicate corrections or errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     obt
    -0.15
    zes
    -0.14
     Calc
    -0.14
    arte
    -0.14
    ola
    -0.14
    BoxLayout
    -0.14
    \Collection
    -0.14
    adapter
    -0.13
     decent
    -0.13
     Elliott
    -0.13
    POSITIVE LOGITS
    iffin
    0.17
    folio
    0.14
    á»ijng
    0.14
    .Interval
    0.14
    "./
    0.14
    ån
    0.14
    uits
    0.14
    riz
    0.13
    527
    0.13
     hang
    0.13
    Act Density 0.149%

    No Known Activations