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

    Neuronpedia

    INDEX
    Explanations

    attends to numerical values in contexts related to phone numbers from preceding tokens that provide context or categories

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.18
    2:0.17
    3:0.04
    4:0.06
    5:0.07
    6:0.11
    7:0.24
    Negative Logits
     Normdatei
    -0.36
    dafx
    -0.35
    AndEndTag
    -0.35
    TagMode
    -0.34
    localctx
    -0.33
    protoimpl
    -0.33
     lenker
    -0.32
     OFDb
    -0.31
    ViewImports
    -0.30
    Synonyms
    -0.30
    POSITIVE LOGITS
     AssemblyTitle
    0.41
    原始内容存档于
    0.31
     motorista
    0.31
    ittäin
    0.30
    abstractmethod
    0.30
    Hozzáférés
    0.30
    ACTED
    0.29
    eien
    0.29
    +:+
    0.29
    цыі
    0.29
    Act Density 0.013%

    No Known Activations