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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific weekdays, particularly Wednesday

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </em>
    -0.81
     Gen
    -0.71
    4
    -0.71
    3
    -0.70
    orge
    -0.68
     pol
    -0.68
    ge
    -0.66
    gb
    -0.65
    </sub>
    -0.65
    ff
    -0.64
    POSITIVE LOGITS
     Wednesday
    2.20
     Tuesday
    2.16
    Wednesday
    2.16
     Thursday
    2.13
    Thursday
    2.10
    Tuesday
    2.06
     Monday
    1.87
     tuesday
    1.85
    Monday
    1.83
     Tuesdays
    1.82
    Act Density 0.036%

    No Known Activations