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

    Neuronpedia

    INDEX
    Explanations

    references to violent incidents and deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    znam
    -0.14
     Chip
    -0.14
     cogn
    -0.13
     Caught
    -0.13
    062
    -0.13
    é¥
    -0.13
     scratch
    -0.13
    earn
    -0.13
     reck
    -0.13
    dio
    -0.12
    POSITIVE LOGITS
     bodies
    0.23
     discovery
    0.22
     found
    0.21
     discovered
    0.21
     FOUND
    0.19
     decomposition
    0.19
     Found
    0.19
     body
    0.19
     gefunden
    0.18
    found
    0.18
    Act Density 0.061%

    No Known Activations