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

    Neuronpedia

    INDEX
    Explanations

    attends to default-related tokens from assignment or configuration-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.11
    2:0.10
    3:0.09
    4:0.08
    5:0.05
    6:0.07
    7:0.37
    Negative Logits
     незавершена
    -0.33
    VIAF
    -0.32
    Portale
    -0.32
     AttributeSet
    -0.31
    cipital
    -0.29
    érience
    -0.29
    MigrationBuilder
    -0.28
    ohist
    -0.28
    setViewportView
    -0.28
    Архівовано
    -0.28
    POSITIVE LOGITS
     quæ
    0.40
     habet
    0.33
     perpétu
    0.32
     maternelle
    0.30
     chrétien
    0.30
     vertes
    0.30
     nameless
    0.30
     épu
    0.29
     Celui
    0.29
     ejus
    0.29
    Act Density 0.055%

    No Known Activations