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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "apart" with relatively high activation values

    oai_token-act-pair · gpt-3.5-turbo

    themes related to separation and division

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.36
     WATCHED
    -0.34
     Mages
    -0.33
     VIDEOS
    -0.30
    NetMessage
    -0.30
     Hide
    -0.30
     Background
    -0.29
    Ĥª
    -0.29
     Cards
    -0.28
     fixme
    -0.27
    POSITIVE LOGITS
    ividual
    0.38
    ocument
    0.35
    ierre
    0.32
    idth
    0.32
     lasted
    0.32
    uese
    0.31
    ardless
    0.31
    eree
    0.31
    okane
    0.31
    uart
    0.30
    Act Density 4.760%

    No Known Activations