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

    Neuronpedia

    INDEX
    Explanations

    keywords related to workplace regulations and safety violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heimer
    -0.16
     Uhr
    -0.15
    istrovstvÃŃ
    -0.15
    .qq
    -0.14
    mdir
    -0.14
    urga
    -0.14
    acro
    -0.14
    alink
    -0.14
    atron
    -0.14
    ëĬ
    -0.13
    POSITIVE LOGITS
     violations
    0.17
    ÑĩиÑĤ
    0.17
    proper
    0.16
     ContentType
    0.16
     violation
    0.16
     Armour
    0.15
    iesen
    0.15
    éĭ
    0.15
     Viol
    0.15
     proper
    0.15
    Act Density 0.050%

    No Known Activations