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

    Neuronpedia

    INDEX
    Explanations

    attends to the closing bracket from numeric or function-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.11
    2:0.11
    3:0.13
    4:0.11
    5:0.09
    6:0.15
    7:0.16
    Negative Logits
    ValueStyle
    -0.42
    AddTagHelper
    -0.40
    EndContext
    -0.34
    UnitTesting
    -0.32
    elemField
    -0.32
    ñora
    -0.32
    WriteTagHelper
    -0.31
     tartalomajánló
    -0.31
     CTP
    -0.31
    GeoNames
    -0.31
    POSITIVE LOGITS
    RenderAtEndOf
    0.28
     psic
    0.28
    windowFixed
    0.27
    mondo
    0.26
    χν
    0.26
     sposo
    0.25
     specifik
    0.25
    gnan
    0.24
     us
    0.24
     HÀ
    0.24
    Act Density 0.023%

    No Known Activations