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

    Neuronpedia

    INDEX
    Explanations

    instances of events that imply wrongdoing or violations of justice

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

    preceding "happened", "occurred", or "took place"

    np_acts-logits-general · gemini-2.0-flash

    description of events occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.60
    rost
    -0.51
     ComVisible
    -0.51
     DEG
    -0.48
    InitVars
    -0.48
     متعلقه
    -0.48
    atrième
    -0.48
    IEU
    -0.48
     SearchView
    -0.47
     beaten
    -0.47
    POSITIVE LOGITS
     happened
    2.65
     occur
    2.63
     happen
    2.63
     occurred
    2.62
     happening
    2.58
     occurs
    2.54
     happens
    2.47
     Occur
    2.36
     occurring
    2.35
    occur
    2.20
    Act Density 0.862%

    No Known Activations