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

    Neuronpedia

    INDEX
    Explanations

    references to crime or criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aner
    -0.52
    ...');
    -0.49
    。
    -0.46
    в
    -0.46
     alkohol
    -0.46
    、「
    -0.44
    「
    -0.44
    кон
    -0.44
    。「
    -0.44
     plak
    -0.43
    POSITIVE LOGITS
    WriteBarrier
    0.89
     وتسجيلات
    0.84
    CPtr
    0.81
    awtextra
    0.76
     utafitiHapana
    0.75
    LookAnd
    0.74
     BoxDecoration
    0.71
     متعلقه
    0.70
    æder
    0.69
    VIAF
    0.68
    Act Density 0.554%

    No Known Activations