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

    Neuronpedia

    INDEX
    Explanations

    references to language laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /jav
    -0.18
     Leipzig
    -0.17
    Arizona
    -0.17
     Kür
    -0.16
    eya
    -0.15
     Arizona
    -0.15
     Tucson
    -0.15
     Orlando
    -0.15
     javafx
    -0.15
     Rochester
    -0.15
    POSITIVE LOGITS
     Welsh
    0.60
     Wales
    0.56
     Cardiff
    0.50
     Swansea
    0.47
    Wel
    0.43
     Aber
    0.39
     Rh
    0.37
     Glam
    0.36
     Camb
    0.35
     wel
    0.35
    Act Density 0.047%

    No Known Activations