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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases highlighting the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqlSession
    -0.71
    Bie
    -0.61
     Aimee
    -0.61
    ia
    -0.60
    Nef
    -0.60
    cu
    -0.58
     NEO
    -0.58
    見る
    -0.57
     InputDecoration
    -0.57
     Eug
    -0.57
    POSITIVE LOGITS
    ]]);
    1.01
     []:
    1.00
    ]**
    0.94
     które
    0.94
     والذي
    0.94
     която
    0.93
     that
    0.92
    migrationBuilder
    0.91
    Datuak
    0.90
     who
    0.89
    Act Density 0.208%

    No Known Activations