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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks and text structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ensemble
    -0.17
    OMPI
    -0.15
     )↵↵↵↵↵↵↵↵
    -0.15
    ungi
    -0.15
    æĬŀ
    -0.14
    oge
    -0.14
    579
    -0.14
    ABCDEFGHIJKLMNOP
    -0.14
    umbo
    -0.14
    Cc
    -0.13
    POSITIVE LOGITS
    oret
    0.20
     affairs
    0.17
    lite
    0.14
     Soviet
    0.14
     κÏĮ
    0.14
     Affairs
    0.14
    ä¼ģ
    0.14
    .jpeg
    0.13
    ad
    0.13
     affair
    0.13
    Act Density 0.110%

    No Known Activations