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

    Neuronpedia

    INDEX
    Explanations

    structured data and legal or formal language elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioni
    -0.14
    ÙĨدÙĩ
    -0.13
     USED
    -0.13
    å±ħ
    -0.13
    inet
    -0.13
     reign
    -0.13
    ucht
    -0.13
    ilit
    -0.13
    _USED
    -0.13
    ÙĦØ·
    -0.13
    POSITIVE LOGITS
     in
    0.44
     expressed
    0.29
    à¹ĥà¸Ļร
    0.24
     în
    0.24
     Ïĥε
    0.22
     written
    0.22
    à¹ĥà¸Ļ
    0.19
    express
    0.19
     rendered
    0.19
     entirely
    0.19
    Act Density 0.190%

    No Known Activations