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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens referring to personal control or action from tokens related to general categories or locales

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.23
    2:0.16
    3:0.07
    4:0.06
    5:0.03
    6:0.04
    7:0.21
    Negative Logits
    AnchorStyles
    -0.37
    帖最后由
    -0.33
     تعدى
    -0.32
    }}^
    -0.31
     Pristupljeno
    -0.30
    󠁢
    -0.29
     MainAxisSize
    -0.28
    مصادر
    -0.27
    |_{\
    -0.27
    MarshalTo
    -0.27
    POSITIVE LOGITS
     ComVisible
    0.29
     deltaTime
    0.27
    AutoScale
    0.27
    nefs
    0.27
    ousands
    0.27
    oredCriteria
    0.25
    UNITY
    0.25
    ilever
    0.25
    udadera
    0.24
    gency
    0.23
    Act Density 0.130%

    No Known Activations