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

    Neuronpedia

    INDEX
    Explanations

    attends to time-related tokens marked with "mm" from subsequent tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.15
    2:0.19
    3:0.10
    4:0.07
    5:0.05
    6:0.11
    7:0.18
    Negative Logits
     Hues
    -0.30
     Pascual
    -0.30
     للمعارف
    -0.29
    rostis
    -0.28
     Leonard
    -0.28
    resizingMask
    -0.27
    guila
    -0.27
    urante
    -0.27
     Lande
    -0.27
    forKey
    -0.27
    POSITIVE LOGITS
    CWE
    0.31
    +#+#
    0.31
     Waray
    0.30
    MLLoader
    0.30
    UnsafeEnabled
    0.29
     Infórmanos
    0.29
     leb
    0.28
     QtCore
    0.28
     CWE
    0.26
    Hochspringen
    0.25
    Act Density 0.039%

    No Known Activations