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

    Neuronpedia

    INDEX
    Explanations

    instances of specific formatting or structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WebServlet
    -0.70
    tvguidetime
    -0.67
     Zing
    -0.59
    UseVisualStyle
    -0.58
    extAlignment
    -0.58
    schul
    -0.56
    YMS
    -0.55
    hundreds
    -0.55
    JOUR
    -0.54
    twimg
    -0.54
    POSITIVE LOGITS
    Overall
    0.93
     overall
    0.90
     Overall
    0.88
    overall
    0.82
    Analysts
    0.81
    总体
    0.77
     analysts
    0.75
     Nevertheless
    0.72
    Nevertheless
    0.72
     Nonetheless
    0.71
    Act Density 0.144%

    No Known Activations