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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical representations related to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (Of
    -0.15
    ãģıãĤĵ
    -0.14
    ugh
    -0.14
    esteem
    -0.13
    elerik
    -0.13
    jon
    -0.13
     Shr
    -0.13
     franch
    -0.13
    oplevel
    -0.13
     retract
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥª
    0.16
    entes
    0.15
    anten
    0.15
    ATRIX
    0.14
    tim
    0.14
    atedRoute
    0.14
    ục
    0.14
    Auf
    0.14
    aterno
    0.14
     éħ
    0.14
    Act Density 0.011%

    No Known Activations