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

    Neuronpedia

    INDEX
    Explanations

    numeric quantities and their relevance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Allociné
    -0.59
    ség
    -0.59
     RSSSF
    -0.56
     savages
    -0.56
     AttributeSet
    -0.55
    úrese
    -0.55
     anhydride
    -0.55
    Przypisy
    -0.54
     Athenians
    -0.54
    ItemBackground
    -0.54
    POSITIVE LOGITS
     two
    1.40
     three
    1.35
     four
    1.22
    two
    1.15
     deux
    1.11
    three
    1.10
     trois
    1.09
     TWO
    1.05
     zwei
    1.04
     five
    1.01
    Act Density 0.567%

    No Known Activations