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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and computer programming

    oai_token-act-pair · gpt-3.5-turbo

    forms of the term "eff" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-
    -0.73
     Galactic
    -0.71
    Story
    -0.65
     Sisters
    -0.64
     Passenger
    -0.64
    pole
    -0.64
    âĸ¬
    -0.64
     Polk
    -0.64
     Mata
    -0.62
    assian
    -0.62
    POSITIVE LOGITS
    icient
    1.26
    inition
    1.23
    riend
    1.09
    orce
    1.08
    inite
    1.07
    initions
    1.07
    ornia
    1.05
    onso
    1.04
    initely
    1.04
    iciency
    1.03
    Act Density 0.010%

    No Known Activations