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

    Neuronpedia

    INDEX
    Explanations

    terminology related to metrics, measures, or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     насељу
    -0.43
     nakalista
    -0.40
     Bowman
    -0.39
     gedaan
    -0.38
     Huntingdon
    -0.37
    来不及
    -0.37
     Ausland
    -0.37
     leven
    -0.36
    amkeit
    -0.36
     Gum
    -0.35
    POSITIVE LOGITS
    age
    1.88
    AGE
    1.72
    ages
    1.66
     age
    1.66
    Age
    1.55
     Age
    1.52
     ages
    1.45
     AGE
    1.45
    aged
    1.42
    setAge
    1.34
    Act Density 0.384%

    No Known Activations