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

    Neuronpedia

    INDEX
    Explanations

    references to portions or segments within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     /\.
    -0.69
    IonicModule
    -0.67
    érables
    -0.66
    AntiForgeryToken
    -0.66
    kać
    -0.66
    :✨
    -0.61
    okovic
    -0.61
    umenical
    -0.59
    czaj
    -0.58
    ьаж
    -0.58
    POSITIVE LOGITS
     portion
    3.96
     Portion
    3.54
    portion
    3.43
     portions
    3.36
    Portion
    3.02
     Portions
    2.82
     porción
    2.32
     gedeelte
    1.31
     fraction
    1.29
    部分
    1.25
    Act Density 0.104%

    No Known Activations