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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "feature" and its variants, indicating a focus on highlighting or emphasizing attributes or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seed
    -0.18
    iferay
    -0.17
    ipt
    -0.17
    ssi
    -0.16
    .inflate
    -0.16
    vod
    -0.15
    ych
    -0.15
    ses
    -0.15
    ehler
    -0.15
    nect
    -0.14
    POSITIVE LOGITS
     prominently
    0.20
    eking
    0.17
    ually
    0.16
     NotSupportedException
    0.16
    plate
    0.15
    uating
    0.15
    ória
    0.15
    izes
    0.14
    562
    0.14
    plates
    0.14
    Act Density 0.034%

    No Known Activations