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

    Neuronpedia

    INDEX
    Explanations

    attends to arbitrary token indices from numerical token representations

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.14
    1:0.20
    2:0.11
    3:0.15
    4:0.09
    5:0.14
    6:0.06
    7:0.08
    Negative Logits
     perla
    -0.28
    ss
    -0.26
    rs
    -0.24
     beaux
    -0.24
     finest
    -0.23
     Quig
    -0.23
     moti
    -0.23
    sourceMap
    -0.23
     intest
    -0.23
    its
    -0.22
    POSITIVE LOGITS
     }}"></
    0.49
    +:+
    0.46
    webElementGuid
    0.37
    tonode
    0.37
    PerformLayout
    0.35
     autorytatywna
    0.35
    namentales
    0.35
     GenerationType
    0.34
    SequentialGroup
    0.33
    poptosis
    0.33
    Act Density 0.012%

    No Known Activations