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

    Neuronpedia

    INDEX
    Explanations

    topics related to qualifications and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     impactful
    -1.05
     incentiv
    -0.97
     toolkit
    -0.91
     onboarding
    -0.88
     prioritize
    -0.87
     showcasing
    -0.84
     sourced
    -0.84
     upfront
    -0.83
     prioriti
    -0.82
     proactively
    -0.81
    POSITIVE LOGITS
     muß
    0.97
     daß
    0.95
     skall
    0.93
     läßt
    0.90
    faßt
    0.85
     mußte
    0.84
     müßte
    0.79
     mußten
    0.73
     giebt
    0.72
    MLLoader
    0.70
    Act Density 7.129%

    No Known Activations