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

    Neuronpedia

    INDEX
    Explanations

    terms related to interference and intervention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤоÑĢ
    -0.18
    uld
    -0.16
    lier
    -0.15
    нг
    -0.15
    н
    -0.15
    bao
    -0.14
    gger
    -0.14
    ard
    -0.14
    ÑģоÑĤ
    -0.14
    igned
    -0.14
    POSITIVE LOGITS
    EDIATE
    0.18
    386
    0.17
    ative
    0.17
    perial
    0.16
    å¼ı
    0.15
    ियर
    0.15
     between
    0.15
    elu
    0.15
    ently
    0.15
    /out
    0.14
    Act Density 0.038%

    No Known Activations