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

    Neuronpedia

    INDEX
    Explanations

    attends to abstract or conceptual tokens from more specific, concrete tokens related to actions or states

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.13
    3:0.08
    4:0.07
    5:0.02
    6:0.19
    7:0.31
    Negative Logits
     ویکی‌پدیا
    -0.24
    ferd
    -0.23
    año
    -0.22
     Rockefeller
    -0.22
     يتيمه
    -0.22
     same
    -0.22
    ViewStyle
    -0.21
    location
    -0.21
    PageIndex
    -0.21
    AttributeSet
    -0.21
    POSITIVE LOGITS
    NUMX
    0.41
    はじめに
    0.36
    помним
    0.35
    %?
    0.35
    ?')
    0.34
    ?>
    0.34
    Bref
    0.34
    leſs
    0.34
    »?
    0.33
     fieldNum
    0.33
    Act Density 0.351%

    No Known Activations