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

    Neuronpedia

    INDEX
    Explanations

    references to measurements and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.62
    riwal
    -0.60
     hundreds
    -0.58
     two
    -0.57
     thousands
    -0.55
     архивлан
    -0.55
    SequentialGroup
    -0.54
    Manbalar
    -0.54
    two
    -0.54
     hundred
    -0.53
    POSITIVE LOGITS
     nine
    1.01
     eight
    0.98
     ten
    0.89
     Eight
    0.89
     Nine
    0.88
     twelve
    0.86
     seven
    0.84
     Ten
    0.84
     eleven
    0.84
     NINE
    0.81
    Act Density 0.919%

    No Known Activations