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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of death or dead entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kkor
    -0.92
    깐
    -0.84
     betreft
    -0.84
    ябре
    -0.78
     betweenstory
    -0.76
     Marl
    -0.76
    AccessorTable
    -0.76
    Пусть
    -0.76
    zzleHttp
    -0.75
    morphosis
    -0.75
    POSITIVE LOGITS
     Dead
    1.53
     dead
    1.51
     DEAD
    1.47
    Dead
    1.45
    dead
    1.31
    DEAD
    1.19
    死
    0.80
     Toten
    0.78
     мерт
    0.77
     死
    0.76
    Act Density 0.066%

    No Known Activations