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

    Neuronpedia

    INDEX
    Explanations

    ellipses and other forms of unfinished sentences or trailing thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ellipses, indicating omitted text or trailing thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ellipses and sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NUMX
    -1.00
     للمعارف
    -0.93
    NewUrlParser
    -0.85
    contentLoaded
    -0.78
    httphttps
    -0.77
    mybatisplus
    -0.76
    Autoritní
    -0.74
     مشين
    -0.74
    出版年
    -0.73
    MemoryWarning
    -0.72
    POSITIVE LOGITS
    ↵↵
    0.80
    !
    0.62
    ↵
    0.55
    ↵↵↵
    0.53
    ↵↵↵↵
    0.51
    0.51
    <eos>
    0.50
    ?
    0.48
                                   
    0.46
    RegressionTest
    0.46
    Act Density 0.062%

    No Known Activations