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

    Neuronpedia

    INDEX
    Explanations

    introductory markers or significant phrases that indicate the beginning of new segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     course
    -0.50
     including
    -0.47
     Course
    -0.44
     &
    -0.44
     lagi
    -0.43
     Jan
    -0.43
     and
    -0.43
    leg
    -0.43
    calaure
    -0.42
     Dec
    -0.42
    POSITIVE LOGITS
     Normdatei
    1.10
     архивлан
    1.08
    +#+#
    0.94
    ंदीखरीदारी
    0.92
    Tikang
    0.89
    ConstraintMaker
    0.88
     متعلقه
    0.85
     sherds
    0.85
    Datuak
    0.81
     utafitiHapana
    0.77
    Act Density 0.168%

    No Known Activations