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

    Neuronpedia

    INDEX
    Explanations

    time indicators and event dates

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

    time followed by "pm" or "am"

    np_acts-logits-general · gemini-2.0-flash

    pm time notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     morning
    -1.08
    Morning
    -0.96
     Morning
    -0.95
    morning
    -0.94
     MORNING
    -0.86
     mornings
    -0.86
     breakfast
    -0.81
     morgens
    -0.79
     утром
    -0.79
     am
    -0.79
    POSITIVE LOGITS
    pm
    1.04
    PM
    0.96
     PM
    0.96
     pm
    0.92
     Pm
    0.67
    pM
    0.67
    Pm
    0.67
     p
    0.66
    PMD
    0.63
    PMT
    0.51
    Act Density 0.123%

    No Known Activations