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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or reasons for events

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

    "Due to" phrase

    np_acts-logits-general · gemini-2.0-flash

    due to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.68
     commandement
    -0.67
     enfans
    -0.60
     perſon
    -0.60
     ſtill
    -0.55
     ſhe
    -0.54
     argint
    -0.54
     ſer
    -0.52
    readString
    -0.52
     sánchez
    -0.51
    POSITIVE LOGITS
     due
    1.12
     DUE
    1.04
     Due
    1.03
    due
    0.98
    Due
    0.97
    DUE
    0.93
     devido
    0.77
     debido
    0.69
    Debido
    0.68
     owing
    0.65
    Act Density 0.077%

    No Known Activations