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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of being dead or lifeless

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    kkor
    -1.02
     оригіналу
    -0.96
     myſelf
    -0.96
    RenderAtEndOf
    -0.94
     esboço
    -0.91
     itſelf
    -0.91
     Himo
    -0.90
    깐
    -0.87
    Viki
    -0.86
     Mundi
    -0.86
    POSITIVE LOGITS
     Dead
    1.33
     dead
    1.31
    Dead
    1.26
     DEAD
    1.22
    dead
    1.07
    DEAD
    0.95
    s
    0.76
    er
    0.69
    <b>
    0.68
    est
    0.68
    Act Density 0.009%

    No Known Activations