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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, specifically years and weeks

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

    time periods and completions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alimentaria
    -0.40
    latego
    -0.40
     própria
    -0.39
    only
    -0.38
     olmayan
    -0.37
     seules
    -0.37
     lisäksi
    -0.36
     tylko
    -0.36
     propias
    -0.36
     propia
    -0.36
    POSITIVE LOGITS
    endphp
    0.79
     year
    0.73
     Year
    0.73
     YEAR
    0.68
     Month
    0.68
     week
    0.66
    ðsíða
    0.66
     month
    0.66
    astify
    0.63
    Year
    0.63
    Act Density 0.070%

    No Known Activations