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

    Neuronpedia

    INDEX
    Explanations

    punctuated phrases signaling inquiries or reflections on experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iage
    -0.15
     ...(
    -0.15
    ...]↵↵
    -0.14
    .="
    -0.14
    åº
    -0.14
     ...)↵
    -0.13
    ++.
    -0.13
    ÄĽÅ¾
    -0.13
     ...
    -0.13
    .Wh
    -0.13
    POSITIVE LOGITS
     He
    0.15
     Hi
    0.14
    аза
    0.14
    รà¸ĩ
    0.14
     POD
    0.14
    cobra
    0.14
     ’
    0.13
    بÙĬر
    0.13
    .Exceptions
    0.13
    ubi
    0.13
    Act Density 0.028%

    No Known Activations