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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating levels or quantities

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

    the X the Y comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.86
     nahilalakip
    -0.65
    GEBURTSDATUM
    -0.64
    \{\\
    -0.60
     CreateTagHelper
    -0.59
    +#+#
    -0.57
     EconPapers
    -0.57
    SourceChecksum
    -0.56
     لينك
    -0.56
     فريبيس
    -0.56
    POSITIVE LOGITS
     càng
    0.63
    越多
    0.51
     semakin
    0.43
    越好
    0.42
     progressively
    0.41
    StoryboardSegue
    0.40
    越是
    0.40
     Чем
    0.39
    愈
    0.39
     越
    0.38
    Act Density 0.521%

    No Known Activations