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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating large quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ['./
    -0.71
     @"/
    -0.70
     wireType
    -0.61
    ioc
    -0.59
    itext
    -0.58
     algún
    -0.57
    complexContent
    -0.56
    brać
    -0.56
     "../
    -0.55
    giphy
    -0.55
    POSITIVE LOGITS
     thousands
    1.65
     hundreds
    1.58
     Thousands
    1.50
    thousands
    1.50
    ousands
    1.48
     millions
    1.47
    Thousands
    1.46
     Hundreds
    1.46
    Hundreds
    1.45
    hundreds
    1.43
    Act Density 0.082%

    No Known Activations