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

    Neuronpedia

    INDEX
    Explanations

    attends to variable-related tokens from paired punctuation tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.15
    1:0.16
    2:0.18
    3:0.09
    4:0.09
    5:0.05
    6:0.07
    7:0.18
    Negative Logits
    PYX
    -0.36
     estimés
    -0.33
    })*/
    -0.33
     VIAF
    -0.32
    VIAF
    -0.30
    findpost
    -0.30
    */)
    -0.30
    IndentedString
    -0.30
    fvar
    -0.30
    /*
    -0.29
    POSITIVE LOGITS
    はじめに
    0.25
     Italijanski
    0.24
     books
    0.23
    indakan
    0.22
    fortawesome
    0.21
    AFF
    0.21
     thing
    0.21
    böz
    0.20
     bomb
    0.20
    BagConstraints
    0.20
    Act Density 0.659%

    No Known Activations