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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people

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

    said people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.87
     estekak
    -0.85
    oa̍t
    -0.79
    GEBURTSDATUM
    -0.77
     ddelweddau
    -0.77
    ſchaft
    -0.75
     Савезне
    -0.75
     autorytatywna
    -0.74
    SourceChecksum
    -0.73
    PerformLayout
    -0.72
    POSITIVE LOGITS
     said
    0.35
     
    0.32
     powied
    0.30
     zust
    0.29
     wzi
    0.28
    "
    0.28
     spokesman
    0.28
    而在
    0.27
     (
    0.27
     řekl
    0.26
    Act Density 0.019%

    No Known Activations