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

    Neuronpedia

    INDEX
    Explanations

    references to wrapping or enclosing actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    одо
    -0.17
    places
    -0.15
     alta
    -0.14
    ibase
    -0.14
    cup
    -0.14
    een
    -0.14
    quil
    -0.14
    ndo
    -0.14
    /front
    -0.14
    ltra
    -0.14
    POSITIVE LOGITS
    around
    0.21
    -around
    0.21
    .Wrap
    0.19
     wrap
    0.19
     wrapped
    0.17
     Wrapped
    0.17
     Wrap
    0.17
    TURE
    0.17
     wrapper
    0.16
    ict
    0.16
    Act Density 0.023%

    No Known Activations