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

    Neuronpedia

    INDEX
    Explanations

    special characters, punctuation, and symbols often used in formal or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    àª
    -0.18
    ÑĦ
    -0.17
    %D
    -0.17
    à±
    -0.17
    à¨
    -0.17
    ëį°ìĿ´íĬ¸
    -0.17
    ש
    -0.16
    ×ķ×
    -0.16
    à°
    -0.16
    á
    -0.16
    POSITIVE LOGITS
     ×IJ
    0.28
     ×Ķ
    0.28
     ×ŀ
    0.27
     à¦
    0.27
     ×
    0.27
     ×ij
    0.27
     à
    0.26
     ׾
    0.26
     ש
    0.23
     à®
    0.22
    Act Density 0.005%

    No Known Activations