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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts between situations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artz
    -0.17
     buflen
    -0.15
    apers
    -0.15
    Ñĩим
    -0.14
    upro
    -0.14
    ansi
    -0.14
    readystatechange
    -0.14
    idden
    -0.14
    headline
    -0.14
     Ston
    -0.14
    POSITIVE LOGITS
     he
    0.20
     said
    0.17
    shint
    0.17
     ê·¸ëĬĶ
    0.17
     added
    0.16
    ä»ĸ
    0.16
     вÑĸн
    0.16
    added
    0.15
    He
    0.14
     says
    0.14
    Act Density 0.154%

    No Known Activations