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

    Neuronpedia

    INDEX
    Explanations

    death and dying

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases describing people who died or quantities of deaths.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    death
    -1.25
     Deceased
    -1.20
     deceased
    -1.10
    deceased
    -0.98
    decay
    -0.94
     DEATH
    -0.93
     tragedy
    -0.91
     cessation
    -0.88
    dead
    -0.86
     suicides
    -0.85
    POSITIVE LOGITS
     died
    1.70
     die
    1.66
     dies
    1.25
     murió
    1.20
    死ぬ
    0.96
     Die
    0.94
    Die
    0.90
    ujuk
    0.79
     kill
    0.78
     dienen
    0.78
    Act Density 0.071%

    No Known Activations