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

    Neuronpedia

    INDEX
    Explanations

    verbs related to serving a function or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating functions or roles of objects and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.69
    istani
    -0.65
    aband
    -0.61
    worth
    -0.61
    liam
    -0.60
    myra
    -0.58
    voy
    -0.57
    istine
    -0.57
    tg
    -0.57
    iscons
    -0.56
    POSITIVE LOGITS
     two
    1.38
     three
    1.31
     several
    1.26
     TWO
    1.21
     four
    1.15
     many
    1.12
     numerous
    1.05
     THREE
    1.04
    two
    0.98
     five
    0.96
    Act Density 0.457%

    No Known Activations