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

    Neuronpedia

    INDEX
    Explanations

    references to time, particularly phrases like "this past," "this," and "last."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abbage
    -0.15
     Thom
    -0.14
    atcher
    -0.13
    RICT
    -0.13
    ama
    -0.13
     tonight
    -0.13
    ìķ¤
    -0.13
    ıy
    -0.13
     noct
    -0.13
     Finance
    -0.13
    POSITIVE LOGITS
     year
    0.20
     month
    0.19
    yan
    0.17
    ibold
    0.17
     годÑĥ
    0.15
     mole
    0.15
    year
    0.15
    mentions
    0.14
    ilere
    0.14
    eon
    0.14
    Act Density 0.038%

    No Known Activations