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

    Neuronpedia

    INDEX
    Explanations

    attends to specific functional terms or nouns from their enclosing parentheses or brackets

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.13
    2:0.12
    3:0.11
    4:0.34
    5:0.03
    6:0.06
    7:0.08
    Negative Logits
    Geplaatst
    -0.38
    '):
    -0.34
    __':
    -0.32
    ,’”
    -0.32
    AddTagHelper
    -0.32
     joaat
    -0.32
    MarshalTo
    -0.31
     '{@
    -0.31
    Personensuche
    -0.31
    ?’
    -0.31
    POSITIVE LOGITS
    ー
    0.21
     Co
    0.20
     El
    0.20
    IND
    0.19
     osz
    0.19
    El
    0.19
     EL
    0.19
    整
    0.18
    Co
    0.18
     overlay
    0.18
    Act Density 1.315%

    No Known Activations