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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doInBackground
    -0.70
     发表于
    -0.56
    mtd
    -0.51
    لیس
    -0.47
     Kidman
    -0.46
     ald
    -0.46
    Morocco
    -0.46
     Congo
    -0.46
    diyesi
    -0.46
    ceae
    -0.46
    POSITIVE LOGITS
     estekak
    0.80
     thousand
    0.74
     halben
    0.74
     hundred
    0.73
    StructEnd
    0.70
     dozen
    0.68
    AccessFile
    0.68
     THAN
    0.66
     million
    0.65
     halbe
    0.65
    Act Density 0.225%

    No Known Activations