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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values indicating statistical data or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bourgoin
    -0.88
    ']))
    -0.86
     متعلقه
    -0.86
    entierung
    -0.80
    saraba
    -0.79
    ]='\
    -0.78
    amá
    -0.78
    '],$
    -0.78
    hhhhhhhh
    -0.78
     通販
    -0.75
    POSITIVE LOGITS
    4
    2.50
    5
    1.54
    3
    1.40
    6
    1.38
    8
    1.34
     Forty
    1.22
    ４
    1.22
    7
    1.20
    FOUR
    1.20
     Four
    1.17
    Act Density 0.845%

    No Known Activations