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

    Neuronpedia

    INDEX
    Explanations

    opening and closing angle brackets in markup or code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mund
    -0.15
    itou
    -0.15
    ило
    -0.15
     fort
    -0.14
    ijken
    -0.14
     ÙĨÚ¯
    -0.14
    inkel
    -0.14
     spiral
    -0.14
     mere
    -0.13
    رÙĩ
    -0.13
    POSITIVE LOGITS
    aver
    0.17
     Hab
    0.15
    à¥Ģड
    0.15
    амп
    0.14
    999
    0.14
    889
    0.14
    887
    0.14
    amp
    0.14
    atro
    0.13
    ouve
    0.13
    Act Density 0.017%

    No Known Activations