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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens that indicate suggestion or implication from corresponding later tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.12
    2:0.11
    3:0.09
    4:0.04
    5:0.02
    6:0.07
    7:0.40
    Negative Logits
    StoryboardSegue
    -0.34
    xFFFFFF
    -0.32
    ValueStyle
    -0.31
    MeasureSpec
    -0.28
    TintMode
    -0.28
     Kommune
    -0.28
    ulaski
    -0.28
    RTLI
    -0.28
    fjspx
    -0.28
    DispatchToProps
    -0.27
    POSITIVE LOGITS
     sauvages
    0.31
    новништво
    0.30
    ')")
    0.29
     يتيمه
    0.29
    اریخ
    0.29
    INCLUDED
    0.28
    itee
    0.27
     trekken
    0.27
    )._
    0.27
     >=",
    0.26
    Act Density 0.429%

    No Known Activations