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

    Neuronpedia

    INDEX
    Explanations

    temporal phrases indicating dates and historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĺ¨
    -0.19
     yesterday
    -0.18
    Yesterday
    -0.15
    ä»Ĭå¹´
    -0.15
     minul
    -0.14
     Yesterday
    -0.14
    aso
    -0.14
    ober
    -0.14
    rist
    -0.14
    wen
    -0.14
    POSITIVE LOGITS
     subsequent
    0.20
     later
    0.19
     ensuing
    0.16
    ÑĭÑĪ
    0.15
     consequence
    0.15
     subsequently
    0.14
     Later
    0.14
     später
    0.14
     succeeding
    0.14
    Later
    0.14
    Act Density 0.071%

    No Known Activations