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

    Neuronpedia

    INDEX
    Explanations

    terms related to sudden and unexpected deaths

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

    sudden or unexpected death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poroz
    -0.39
    riezmann
    -0.39
     Brabant
    -0.38
    dyž
    -0.37
     seeing
    -0.37
     draw
    -0.37
     Svensk
    -0.36
     belirt
    -0.36
     bordir
    -0.36
     groans
    -0.36
    POSITIVE LOGITS
     unexpectedly
    1.13
     suddenly
    0.94
    suddenly
    0.92
     abruptly
    0.78
     Suddenly
    0.77
    Suddenly
    0.75
     soudain
    0.73
    unexpected
    0.69
     plötzlich
    0.67
     Unexpected
    0.65
    Act Density 0.006%

    No Known Activations