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

    Neuronpedia

    INDEX
    Explanations

    the word "because" indicating reasoning or causation

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

    introduces reasons or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTLR
    -0.47
    httphttps
    -0.46
    awtextra
    -0.46
    URLException
    -0.45
    StoryboardSegue
    -0.44
     getItemCount
    -0.44
    __':
    -0.44
    SwingConstants
    -0.43
    __':
    -0.43
     EconPapers
    -0.43
    POSITIVE LOGITS
    Grüsse
    0.44
     kasarigan
    0.44
    liesslich
    0.42
    UnusedPrivate
    0.41
    Personendaten
    0.41
     because
    0.41
     reason
    0.40
     OMITBAD
    0.40
     reasons
    0.40
     disambiguazione
    0.39
    Act Density 0.018%

    No Known Activations