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

    Neuronpedia

    INDEX
    Explanations

    expressions related to possibility or uncertainty

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

    expression of possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toallas
    -0.45
    CastException
    -0.42
     Valera
    -0.40
     Unies
    -0.40
    gheny
    -0.40
    visuel
    -0.39
     Laver
    -0.38
     toalha
    -0.38
    й
    -0.38
    enação
    -0.37
    POSITIVE LOGITS
     might
    1.57
    Might
    1.54
    might
    1.48
     Might
    1.46
     MIGHT
    1.35
     pourrait
    0.87
     könnte
    0.81
     podría
    0.80
     would
    0.79
     pourraient
    0.79
    Act Density 0.019%

    No Known Activations