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

    Neuronpedia

    INDEX
    Explanations

    attends to numerical values from adjacent numerical separators

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.17
    2:0.10
    3:0.09
    4:0.09
    5:0.04
    6:0.12
    7:0.23
    Negative Logits
    исленность
    -0.37
     propOrder
    -0.36
    клопе
    -0.35
    RUnlock
    -0.34
     consultato
    -0.34
    GEBURTSDATUM
    -0.34
     thiệu
    -0.33
    ">—
    -0.33
    ="#"><
    -0.33
    fortawesome
    -0.33
    POSITIVE LOGITS
     يتيمه
    0.27
    ante
    0.22
    isen
    0.22
    </em>
    0.21
    ant
    0.20
    Mostly
    0.20
     Mostly
    0.20
    んじゃない
    0.20
     Sam
    0.20
     held
    0.20
    Act Density 0.394%

    No Known Activations