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

    Neuronpedia

    INDEX
    Explanations

    words indicating relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avia
    -0.16
    ulo
    -0.15
    eden
    -0.14
    ãĤĮãģ°
    -0.14
    arda
    -0.14
    å¾
    -0.14
    Tween
    -0.14
    det
    -0.14
    ssel
    -0.14
     freely
    -0.13
    POSITIVE LOGITS
     foss
    0.15
    -article
    0.15
    MMdd
    0.14
    à¤Łà¤°
    0.14
    luet
    0.14
    cm
    0.14
    umi
    0.14
    ulling
    0.14
    ych
    0.14
    anning
    0.14
    Act Density 0.002%

    No Known Activations