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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a new section or topic in the text, indicating a significant shift in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.83
    ^(@)
    -0.81
    LikeLiked
    -0.80
    %";
    -0.78
     لينك
    -0.77
    poin
    -0.77
     ISD
    -0.77
    ressee
    -0.74
    ˏ
    -0.73
     Manne
    -0.73
    POSITIVE LOGITS
    </sup>
    0.98
    </sub>
    0.82
    ⁄
    0.80
    </u>
    0.77
    <u>
    0.75
    </s>
    0.70
    o
    0.69
    ️
    0.66
    i
    0.66
      
    0.62
    Act Density 0.245%

    No Known Activations