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

    Neuronpedia

    INDEX
    Explanations

    references to death and its related concepts, particularly in the context of consequences and penalties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adpleegd
    -0.85
    ništ
    -0.79
     Préférences
    -0.70
    躇
    -0.70
     ComVisible
    -0.69
     @"/
    -0.65
    Референце
    -0.65
     AVA
    -0.64
    AutoresizingMask
    -0.63
    rungsseite
    -0.62
    POSITIVE LOGITS
     DEATH
    0.86
     death
    0.81
     śmier
    0.81
    DEATH
    0.79
    Death
    0.78
     Death
    0.77
    death
    0.76
     deaths
    0.71
     morte
    0.66
     Deaths
    0.64
    Act Density 0.104%

    No Known Activations