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

    Neuronpedia

    INDEX
    Explanations

    attends to specific punctuation marks from related textual content

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.10
    2:0.08
    3:0.07
    4:0.07
    5:0.02
    6:0.10
    7:0.43
    Negative Logits
     implicitly
    -0.31
    aurus
    -0.30
    tetten
    -0.30
     daher
    -0.30
    脚注の使い方
    -0.30
     respectively
    -0.30
     subsequently
    -0.29
    ContentAlignment
    -0.29
    خرى
    -0.28
     Ceci
    -0.28
    POSITIVE LOGITS
    FormTagHelper
    0.39
    ❋
    0.34
    makeText
    0.33
    </blockquote>
    0.32
    FlowLayout
    0.32
     otomatig
    0.31
     ◄
    0.31
     disambiguazione
    0.30
    NameInMap
    0.30
    Nonnull
    0.30
    Act Density 0.856%

    No Known Activations