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

    Neuronpedia

    INDEX
    Explanations

    phrases that attribute authorship to works, specifically books and writings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atever
    -0.77
    duino
    -0.72
    Minecraft
    -0.70
    ushima
    -0.70
     docks
    -0.68
    etheless
    -0.67
    chapter
    -0.65
    orest
    -0.65
    Recomm
    -0.65
    compl
    -0.65
    POSITIVE LOGITS
     Sonny
    0.90
     Laksh
    0.87
     Krish
    0.87
     Pru
    0.84
     Mikhail
    0.81
     Laure
    0.80
     Marilyn
    0.80
     Henri
    0.80
     Karen
    0.79
     Jimmy
    0.78
    Act Density 0.069%

    No Known Activations