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

    Neuronpedia

    INDEX
    Explanations

    terms related to death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    death and doctors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gdx
    -0.42
    があると
    -0.34
     Western
    -0.31
     //
    -0.31
     Swing
    -0.30
     للاسماء
    -0.30
    JNIEnv
    -0.30
    能
    -0.30
     sil
    -0.30
     swing
    -0.29
    POSITIVE LOGITS
     death
    1.35
    death
    1.27
    Death
    1.20
     Death
    1.13
     DEATH
    1.06
    DEATH
    1.01
     muerte
    0.98
    deceased
    0.93
     śmierci
    0.91
     deaths
    0.89
    Act Density 0.001%

    No Known Activations