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

    Neuronpedia

    INDEX
    Explanations

    attends to descriptive tokens associated with numerical values from tokens that provide a comparative context or explanation

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.23
    2:0.13
    3:0.08
    4:0.08
    5:0.03
    6:0.06
    7:0.20
    Negative Logits
    ConstraintMaker
    -0.54
    DockStyle
    -0.39
    httphttps
    -0.37
     GenerationType
    -0.37
    ImageContext
    -0.36
    extAlignment
    -0.35
    Brainz
    -0.33
    istoitu
    -0.32
     Rés
    -0.32
    IntoConstraints
    -0.32
    POSITIVE LOGITS
    0.28
    uen
    0.26
    nes
    0.26
    SharedCtor
    0.25
     currently
    0.25
    tualmente
    0.25
    StructField
    0.25
    lar
    0.24
     carried
    0.23
     actualidad
    0.23
    Act Density 0.208%

    No Known Activations