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

    Neuronpedia

    INDEX
    Explanations

    expressions related to making observations, remarks, or notes about a topic

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

    introducing points or remarks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.60
    DockStyle
    -0.56
     Eſ
    -0.43
     ſind
    -0.43
    EndContext
    -0.42
     myſelf
    -0.42
     Anſ
    -0.42
    Gön
    -0.41
     HttpNotFound
    -0.41
     ſta
    -0.40
    POSITIVE LOGITS
     cautions
    0.68
     caveats
    0.65
     notes
    0.63
     considerations
    0.62
     comments
    0.60
     caution
    0.59
     remarks
    0.58
     Considerations
    0.56
     NOTES
    0.56
     Notes
    0.55
    Act Density 0.047%

    No Known Activations