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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens containing the letter "u" from various later tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.14
    2:0.08
    3:0.06
    4:0.17
    5:0.32
    6:0.05
    7:0.06
    Negative Logits
    expandindo
    -0.30
    Tikang
    -0.29
     للمعارف
    -0.26
     australiano
    -0.25
     squeeze
    -0.24
     nisso
    -0.23
    BNL
    -0.23
    DockStyle
    -0.23
     kaynağından
    -0.23
    enken
    -0.22
    POSITIVE LOGITS
    multer
    0.37
     translateY
    0.34
    resultCode
    0.33
     Weit
    0.32
    ddha
    0.32
     समीक्षाओं
    0.32
    ptest
    0.31
    帖最后由
    0.31
     fallo
    0.31
    PutMapping
    0.31
    Act Density 0.148%

    No Known Activations