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

    Neuronpedia

    INDEX
    Explanations

    attends to visually related tokens from tokens that appear later in the sequence

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.10
    2:0.13
    3:0.08
    4:0.07
    5:0.04
    6:0.08
    7:0.36
    Negative Logits
    bootstrapcdn
    -0.46
    uxxxx
    -0.45
    extAlignment
    -0.44
    Jeografia
    -0.41
    ptid
    -0.40
     Савезне
    -0.40
    PerformLayout
    -0.39
    SourceChecksum
    -0.38
    はじめに
    -0.37
    zzleHttp
    -0.37
    POSITIVE LOGITS
    יסטור
    0.26
     }^{(
    0.26
    hot
    0.25
    setDisplay
    0.24
     Kalyan
    0.24
     Wys
    0.23
     genel
    0.23
     ined
    0.23
    sig
    0.22
    Ann
    0.22
    Act Density 0.051%

    No Known Activations