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

    Neuronpedia

    INDEX
    Explanations

    attends to specific tokens that appear earlier in a sentence from later tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.12
    2:0.12
    3:0.28
    4:0.12
    5:0.05
    6:0.08
    7:0.10
    Negative Logits
     ModelExpression
    -0.48
     '\\;'
    -0.34
     unknownFields
    -0.34
     NSCoder
    -0.33
     calendriers
    -0.30
    #![
    -0.30
    Хьажоргаш
    -0.30
    brk
    -0.29
    onViewCreated
    -0.29
    RenderAtEndOf
    -0.29
    POSITIVE LOGITS
     autorytatywna
    0.37
    tagHelperRunner
    0.34
    bootstrapcdn
    0.32
     dalamnya
    0.31
     arşivlendi
    0.31
     ويكيپيديا
    0.29
    AdapterFactory
    0.28
    -------------</
    0.28
     صوتيه
    0.28
    ں
    0.28
    Act Density 0.000%

    No Known Activations