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

    Neuronpedia

    INDEX
    Explanations

    concepts related to relationships and societal assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TouchableOpacity
    -0.36
     Übersicht
    -0.35
    /*
    -0.35
     škoda
    -0.34
     calendriers
    -0.34
    ungkin
    -0.33
     olsun
    -0.32
    起了
    -0.31
     chyba
    -0.31
     nadzieję
    -0.31
    POSITIVE LOGITS
     means
    2.77
     Means
    2.34
     MEANS
    2.23
    means
    2.17
    Means
    2.16
     significa
    2.03
     berarti
    1.98
     bedeutet
    1.95
     betekent
    1.95
     meaning
    1.93
    Act Density 0.909%

    No Known Activations