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

    Neuronpedia

    INDEX
    Explanations

    indicators of upcoming updates or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xac
    -0.15
    prd
    -0.14
    оза
    -0.14
    oreach
    -0.14
    inction
    -0.14
    527
    -0.14
    acen
    -0.14
    ocs
    -0.14
    chner
    -0.13
    isen
    -0.13
    POSITIVE LOGITS
     stay
    0.62
     Stay
    0.59
    Stay
    0.54
    stay
    0.52
     stayed
    0.49
     stays
    0.46
     staying
    0.41
     watch
    0.30
     expect
    0.30
     Expect
    0.28
    Act Density 0.117%

    No Known Activations