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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time periods or durations

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

    during a time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anſ
    -0.68
     Majefty
    -0.68
     houſe
    -0.68
     purpoſe
    -0.67
     ſta
    -0.67
     ſtand
    -0.66
     ſte
    -0.66
     pleaſure
    -0.66
     dieux
    -0.63
     perſon
    -0.60
    POSITIVE LOGITS
     during
    1.91
    during
    1.79
     DURING
    1.64
     During
    1.61
    During
    1.59
    durante
    1.50
     durante
    1.47
     tijdens
    1.38
     Durante
    1.31
    Durante
    1.27
    Act Density 0.037%

    No Known Activations