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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating numerical or quantity references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    twimg
    -0.70
    MessageTagHelper
    -0.67
     bezeichneter
    -0.62
     AssemblyCulture
    -0.60
     оригіналу
    -0.58
     ivelany
    -0.57
     насељу
    -0.56
    Jeografia
    -0.56
    قایناق‌لار
    -0.56
     Мексичка
    -0.56
    POSITIVE LOGITS
     way
    4.31
    way
    3.04
    Way
    2.90
     Way
    2.81
     WAY
    2.76
    WAY
    2.49
     ways
    2.08
    ways
    1.79
     façon
    1.77
     manera
    1.72
    Act Density 0.580%

    No Known Activations