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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating persistence or ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdx
    -0.90
    :✨
    -0.90
    kosh
    -0.85
     ModelExpression
    -0.84
    PMailer
    -0.83
    kháu
    -0.81
    dersfield
    -0.81
     MotionEvent
    -0.81
    tagext
    -0.80
    RegistryLite
    -0.79
    POSITIVE LOGITS
     continue
    2.51
     continues
    2.40
     continued
    2.32
     continuing
    2.30
     Continue
    2.26
    continue
    2.16
     Continues
    2.05
    continues
    2.04
     CONTINUE
    2.00
    Continue
    1.97
    Act Density 0.054%

    No Known Activations