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

    Neuronpedia

    INDEX
    Explanations

    attends to mathematical or scientific terms from a broader context of text that includes natural language

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.14
    1:0.07
    2:0.06
    3:0.05
    4:0.05
    5:0.04
    6:0.34
    7:0.19
    Negative Logits
     ganda
    -0.28
    Havolalar
    -0.26
     Maier
    -0.26
    cientes
    -0.25
     COLORS
    -0.25
     niente
    -0.25
     abz
    -0.25
     propOrder
    -0.25
     Alves
    -0.24
     Carver
    -0.24
    POSITIVE LOGITS
     AssemblyCulture
    0.46
    /***/
    0.45
    LikeLike
    0.44
    interopRequire
    0.42
     ujednoznacz
    0.41
     مشين
    0.41
    .[/
    0.40
    SequentialGroup
    0.40
    存于互联网档案馆
    0.40
    })*/
    0.40
    Act Density 0.007%

    No Known Activations