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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "saga" and its variations

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

    telling sagas, opera, shaggy, drama, growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TRAILING
    -0.43
     Fij
    -0.42
    mrb
    -0.41
     Athenians
    -0.40
    duino
    -0.40
     Colton
    -0.40
     Tick
    -0.39
    Chim
    -0.39
     Frenchman
    -0.38
    Tooth
    -0.38
    POSITIVE LOGITS
     Saga
    2.14
     saga
    2.03
    Saga
    1.95
    saga
    1.67
     sag
    1.07
     Sag
    0.98
    sag
    0.84
    Sag
    0.84
     story
    0.82
     odyssey
    0.81
    Act Density 0.002%

    No Known Activations