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

    Neuronpedia

    INDEX
    Explanations

    words related to time, particularly years and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anes
    -0.17
    ::-
    -0.15
    ê¸ī
    -0.14
    bang
    -0.13
    BSD
    -0.13
     Furn
    -0.13
     Bowling
    -0.13
    èĤ¥
    -0.13
     æ©
    -0.13
    oder
    -0.13
    POSITIVE LOGITS
     worked
    0.23
     çalÄ±ÅŁ
    0.22
     lavor
    0.21
     stud
    0.20
     trabaj
    0.19
    worked
    0.19
     studied
    0.19
     studi
    0.19
     studying
    0.18
     ÑĢабоÑĤ
    0.18
    Act Density 0.039%

    No Known Activations