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

    Neuronpedia

    INDEX
    Explanations

    references to notable literary works and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     _____
    -0.14
     ¿
    -0.13
     |
    -0.13
    âĢĥ
    -0.13
    CompleteListener
    -0.13
     ^
    -0.12
     âĹı
    -0.12
     ·
    -0.12
     bug
    -0.12
    \brief
    -0.12
    POSITIVE LOGITS
     ,
    0.38
     ,↵
    0.31
     ,↵↵
    0.28
     .č↵
    0.28
     ØĮ
    0.27
     ãĢģ
    0.25
     ,'
    0.23
     .↵
    0.22
     .↵↵
    0.22
     ,č↵
    0.22
    Act Density 0.356%

    No Known Activations