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

    Neuronpedia

    INDEX
    Explanations

    references to safety regulations and incidents in industrial settings

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

    safety concerns and injuries

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

    mentions of physical harm, accidents, injuries, or workplace/operational safety hazards.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    descriptions of physical hazards and injuries, especially accidents or animal attacks, and references to industrial safety/guarding measures that prevent them.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     st
    -0.29
     voulu
    -0.28
    议
    -0.27
    得上
    -0.27
     ahead
    -0.26
    택
    -0.25
    ⓧ
    -0.25
    burgh
    -0.25
     skor
    -0.25
     siquiera
    -0.24
    POSITIVE LOGITS
     Safety
    0.60
    Safety
    0.59
    Tikang
    0.57
     safety
    0.56
    fatal
    0.56
     fatalities
    0.55
    safety
    0.54
    Παραπομπές
    0.54
    SAFETY
    0.54
     zwiſchen
    0.53
    Act Density 0.254%

    No Known Activations