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

    Neuronpedia

    INDEX
    Explanations

    phrases related to utilizing resources or technology in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to utility and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oslov
    -0.74
    beard
    -0.73
     Hust
    -0.72
    stakes
    -0.65
    lies
    -0.65
     Empires
    -0.65
     publishers
    -0.64
    cot
    -0.63
     Foley
    -0.62
     Solitaire
    -0.62
    POSITIVE LOGITS
    isation
    1.15
     util
    1.14
    ised
    1.12
    izations
    1.09
    ization
    1.08
    util
    1.08
    izable
    1.04
    ocated
    1.03
    itation
    1.01
    izers
    0.99
    Act Density 0.011%

    No Known Activations