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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "dead."

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

    dead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Winfrey
    -0.62
     ESM
    -0.62
     Avril
    -0.61
     LTS
    -0.59
    Mania
    -0.57
     CSP
    -0.57
     للمعارف
    -0.56
     TSM
    -0.56
     kasarigan
    -0.56
    ilever
    -0.56
    POSITIVE LOGITS
     dead
    1.98
    dead
    1.84
    Dead
    1.66
     Dead
    1.64
     DEAD
    1.63
    DEAD
    1.52
     muertos
    0.96
     muerta
    0.95
    isDead
    0.94
     мерт
    0.94
    Act Density 0.007%

    No Known Activations