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

    Neuronpedia

    INDEX
    Explanations

    references to causes of death and associated medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DEAD
    -0.18
     Dead
    -0.18
    Dead
    -0.17
     Threat
    -0.16
    å¨ģ
    -0.15
    dead
    -0.15
     dead
    -0.15
     havoc
    -0.14
    threat
    -0.14
    destruct
    -0.14
    POSITIVE LOGITS
     natural
    0.27
     suff
    0.25
     complications
    0.24
    natural
    0.24
     drowning
    0.23
     Suff
    0.22
     Natural
    0.21
     carbon
    0.20
     drown
    0.20
     exposure
    0.20
    Act Density 0.135%

    No Known Activations