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

    Neuronpedia

    INDEX
    Explanations

    references to death or dead entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typelib
    -0.88
    kkor
    -0.87
    adaptiveStyles
    -0.85
    Diweddarwch
    -0.84
    깐
    -0.84
     propOrder
    -0.83
    ябре
    -0.83
    roxene
    -0.81
    脚注の使い方
    -0.81
    Пусть
    -0.81
    POSITIVE LOGITS
     dead
    2.19
     Dead
    2.13
    Dead
    2.02
     DEAD
    2.01
    dead
    1.93
    DEAD
    1.64
    死
    1.20
     muertos
    1.11
     死
    1.07
     мерт
    1.04
    Act Density 0.058%

    No Known Activations