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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating trends and relationships in data or patterns over time

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

    General trends or similar patterns

    np_acts-logits-general · gemini-2.0-flash

    general trends and patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Imagine
    -0.53
    udessa
    -0.51
     imagine
    -0.49
     Imagine
    -0.48
     halbe
    -0.48
     Imagin
    -0.47
     impossibile
    -0.46
    Imaginary
    -0.46
     intptr
    -0.46
     Berthe
    -0.46
    POSITIVE LOGITS
     trend
    2.92
     trends
    2.77
    trend
    2.42
     Trend
    2.34
    trends
    2.26
     Trends
    2.25
    Trend
    2.17
     pattern
    2.14
    Trends
    2.08
     TRENDS
    2.00
    Act Density 0.535%

    No Known Activations