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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens associated with legal or procedural terminology from non-specific later tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.12
    2:0.13
    3:0.15
    4:0.11
    5:0.08
    6:0.14
    7:0.13
    Negative Logits
     متعلقه
    -0.29
     createState
    -0.27
     himo
    -0.27
    Jîn
    -0.26
     EconPapers
    -0.25
    indere
    -0.25
     jadx
    -0.24
    Surrey
    -0.23
     AllAfrica
    -0.23
    تقاوى
    -0.23
    POSITIVE LOGITS
    CodeAnalysis
    0.34
    PendingIntent
    0.28
    AnchorStyles
    0.28
    endphp
    0.27
    Tetapi
    0.27
    PointerException
    0.27
    épa
    0.25
    agaimana
    0.25
     Tetapi
    0.25
    клопе
    0.24
    Act Density 0.000%

    No Known Activations