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

    Neuronpedia

    INDEX
    Explanations

    phrases or descriptions relating to capability or potential, particularly in terms of performance or function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anian
    -0.16
    fur
    -0.16
    emoc
    -0.16
    ede
    -0.16
    propertyName
    -0.15
    ee
    -0.15
     Obr
    -0.15
    à¤ķन
    -0.14
    arily
    -0.14
    edic
    -0.14
    POSITIVE LOGITS
    -bodied
    0.21
    ule
    0.17
     enough
    0.17
    ity
    0.16
    ippet
    0.16
    uler
    0.15
    cies
    0.15
    hood
    0.15
    ena
    0.15
    cheng
    0.14
    Act Density 0.010%

    No Known Activations