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

    Neuronpedia

    INDEX
    Explanations

    instances of warnings and alerts in a document

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

    warned that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.47
    principalColumn
    -0.43
     uda
    -0.43
     amicable
    -0.42
    rån
    -0.41
    ᅠ
    -0.40
    chables
    -0.40
     ModelExpression
    -0.40
    naires
    -0.40
     Royce
    -0.40
    POSITIVE LOGITS
     warning
    1.36
     warnings
    1.24
     warned
    1.24
     warns
    1.19
     Warning
    1.14
     warn
    1.12
    warning
    1.11
     WARNING
    1.07
     caution
    1.02
    Warning
    1.01
    Act Density 0.031%

    No Known Activations