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

    Neuronpedia

    INDEX
    Explanations

    terms related to events and changes

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

    "Things" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    things happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نده
    -0.58
     ufe
    -0.49
    mede
    -0.48
    férences
    -0.48
    kannya
    -0.47
    iade
    -0.47
    ásban
    -0.45
    тра
    -0.43
    emplos
    -0.43
    leid
    -0.43
    POSITIVE LOGITS
     happening
    1.22
     happened
    0.99
     happens
    0.94
     happen
    0.94
     done
    0.91
     Happening
    0.84
     مشين
    0.83
    happened
    0.80
     amiss
    0.80
     wrong
    0.79
    Act Density 0.117%

    No Known Activations