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

    Neuronpedia

    INDEX
    Explanations

    specific numerical expressions and citations within legal or academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓧ
    -1.16
    matchCondition
    -1.03
    下载附件
    -0.91
     дописавши
    -0.91
    '])->
    -0.90
    ########.
    -0.88
     незавершена
    -0.88
    تقاوى
    -0.87
    SourceChecksum
    -0.85
    %"),
    -0.84
    POSITIVE LOGITS
    .
    0.49
    3
    0.47
    9
    0.46
    5
    0.46
    ,
    0.46
     presunto
    0.45
    4
    0.45
    6
    0.45
    7
    0.43
    8
    0.42
    Act Density 0.636%

    No Known Activations