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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens indicating a connection to a previous reference from tokens that appear afterward

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.10
    2:0.18
    3:0.08
    4:0.04
    5:0.03
    6:0.07
    7:0.37
    Negative Logits
    AddHtmlAttribute
    -0.42
     ProtoMessage
    -0.39
    AndEndTag
    -0.39
    __(/*!
    -0.36
     typelib
    -0.35
    SharedDtor
    -0.35
    EDEFAULT
    -0.35
    :✨
    -0.34
     otomatig
    -0.34
     onAnimation
    -0.33
    POSITIVE LOGITS
     noten
    0.23
    yorsunuz
    0.23
     motivos
    0.23
    woordig
    0.22
     motivo
    0.22
     (
    0.22
    vard
    0.21
    Debt
    0.21
     thoroughly
    0.21
     Джей
    0.20
    Act Density 0.010%

    No Known Activations