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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions related to large numbers or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argout
    -0.60
     Flan
    -0.60
     š
    -0.58
    Assertions
    -0.58
    bat
    -0.57
     []:
    -0.56
    Flan
    -0.56
    خاذ
    -0.55
     เป
    -0.55
    gnome
    -0.54
    POSITIVE LOGITS
     Thousand
    1.00
    ousand
    1.00
    Thousand
    0.99
     millennium
    0.97
     Mille
    0.96
     millennials
    0.91
    mill
    0.91
     tausend
    0.90
     mill
    0.88
     thousand
    0.87
    Act Density 0.192%

    No Known Activations