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

    Neuronpedia

    INDEX
    Explanations

    determiners of focus (e.g., "the goal here", "the question here")

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "here" and situational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RTX
    -0.67
     Doing
    -0.66
    zan
    -0.62
     Seym
    -0.60
     disadvant
    -0.60
     stuffing
    -0.60
     remnants
    -0.59
     Scenes
    -0.57
     BUS
    -0.57
     Accessories
    -0.56
    POSITIVE LOGITS
     revolves
    1.26
     depends
    1.18
     arises
    1.16
     is
    1.13
     boils
    1.12
     involves
    1.09
     reflects
    1.08
     consists
    1.08
     relates
    1.07
     belongs
    1.06
    Act Density 0.301%

    No Known Activations