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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantities or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WidgetItem
    -0.16
    zeit
    -0.14
    wij
    -0.14
     Barb
    -0.14
    ë¹Ī
    -0.13
     пеÑĢиод
    -0.13
    еÑĢж
    -0.13
    TMP
    -0.13
    OrFail
    -0.13
    çĦ¼
    -0.13
    POSITIVE LOGITS
     month
    0.32
     week
    0.27
     Month
    0.27
    month
    0.26
     decade
    0.25
     MONTH
    0.25
     year
    0.23
    Month
    0.23
    -month
    0.23
     hour
    0.23
    Act Density 0.061%

    No Known Activations