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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating amounts or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Référence
    -0.50
    sigkeit
    -0.48
    ,
    -0.43
    lalu
    -0.43
    .
    -0.43
     (
    -0.42
     ioe
    -0.41
    ;
    -0.41
    (
    -0.41
    CodedInputStream
    -0.41
    POSITIVE LOGITS
     nearly
    1.03
    nearly
    0.99
     leaſt
    0.94
    تقاوى
    0.94
     Nearly
    0.85
     hundreds
    0.85
     amount
    0.84
     dozen
    0.84
    Geplaatst
    0.83
    kháu
    0.82
    Act Density 0.529%

    No Known Activations