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

    Neuronpedia

    INDEX
    Explanations

    references to specific books and literary themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¡Ĺ
    -0.16
    arnation
    -0.15
    IDA
    -0.14
    LARI
    -0.14
     mah
    -0.13
    AMENT
    -0.13
    ISTA
    -0.13
    LEEP
    -0.13
    SR
    -0.13
    ida
    -0.13
    POSITIVE LOGITS
     Pig
    0.35
     pig
    0.29
    pig
    0.25
     pigs
    0.25
     Ralph
    0.25
     Lord
    0.24
     boys
    0.24
     Jack
    0.23
     Gold
    0.23
     sav
    0.23
    Act Density 0.002%

    No Known Activations