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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and phrases that indicate action or instruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asure
    -0.17
    erness
    -0.15
    ãģ£ãģ¨
    -0.14
    ambil
    -0.14
    854
    -0.14
    endale
    -0.13
    akov
    -0.13
    alam
    -0.13
    ISIBLE
    -0.13
    baum
    -0.13
    POSITIVE LOGITS
    ekl
    0.16
    опол
    0.16
     shells
    0.15
    pcl
    0.15
    رات
    0.15
    ung
    0.14
     jean
    0.14
    .Manifest
    0.13
     reins
    0.13
    it
    0.13
    Act Density 0.002%

    No Known Activations