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

    Neuronpedia

    INDEX
    Explanations

    words related to departure or leaving

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tyr
    -0.65
     etched
    -0.62
     indictment
    -0.60
     Brach
    -0.59
     Tsarnaev
    -0.59
     Mub
    -0.59
     Akin
    -0.58
     Coin
    -0.57
     Dude
    -0.57
     Publishers
    -0.56
    POSITIVE LOGITS
    lying
    1.44
    stretched
    1.38
    growth
    1.35
    lier
    1.30
    crop
    1.29
    posts
    1.27
    cro
    1.24
    flow
    1.24
    fitting
    1.23
    bur
    1.23
    Act Density 0.031%

    No Known Activations