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

    Neuronpedia

    INDEX
    Explanations

    instances of builder-related constructs in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹ĥà¸Ī
    -0.15
    vic
    -0.15
    صب
    -0.15
    fik
    -0.15
    allas
    -0.14
     Dort
    -0.14
    Ú¯ÛĮر
    -0.14
    imité
    -0.14
    ãĤ¶ãĥ¼
    -0.14
    porte
    -0.13
    POSITIVE LOGITS
    ick
    0.19
    668
    0.16
    ä¸ģ
    0.15
    ammer
    0.15
    strup
    0.14
    جÙĪ
    0.14
    éĤ¦
    0.14
    corp
    0.14
    490
    0.14
    боÑĤ
    0.13
    Act Density 0.010%

    No Known Activations