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

    Neuronpedia

    INDEX
    Explanations

    various forms of warnings and alerts related to potential dangers or precautions

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

    the word "Warning" or "Alert" appearing as a prominent label or heading.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    ym
    -0.35
    linge
    -0.35
     étrangère
    -0.35
     Trouvez
    -0.34
    StartTag
    -0.34
    Executives
    -0.33
    lusconi
    -0.33
    деров
    -0.32
     étrangères
    -0.32
    ußen
    -0.32
    POSITIVE LOGITS
    astify
    0.82
    ViewImports
    0.74
     Alert
    0.74
     Warnings
    0.74
     alerts
    0.73
     Warning
    0.71
    Alert
    0.69
     alerting
    0.69
     warnings
    0.68
    PerformLayout
    0.66
    Act Density 0.218%

    No Known Activations