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

    Neuronpedia

    INDEX
    Explanations

    expressions related to community and gathering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     celebrations
    -0.16
    utura
    -0.16
    gal
    -0.16
     gratuiti
    -0.16
     gala
    -0.15
    cele
    -0.15
    rica
    -0.14
    errat
    -0.14
     Gala
    -0.14
     StreamWriter
    -0.14
    POSITIVE LOGITS
     readings
    0.23
     rec
    0.22
     reading
    0.21
     blessing
    0.20
     Bless
    0.19
     read
    0.18
     introdu
    0.18
     invocation
    0.17
     sung
    0.17
    symbol
    0.17
    Act Density 0.119%

    No Known Activations