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

    Neuronpedia

    INDEX
    Explanations

    attends to technical or institutional tokens from associated tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.43
    1:0.14
    2:0.13
    3:0.06
    4:0.06
    5:0.03
    6:0.04
    7:0.07
    Negative Logits
     disambiguazione
    -0.30
     fak
    -0.30
    Diwedd
    -0.29
     povezave
    -0.27
    gyz
    -0.27
    mergeFrom
    -0.27
    Referencie
    -0.27
    raseña
    -0.26
    Jegyzetek
    -0.26
    owatt
    -0.26
    POSITIVE LOGITS
     GenerationType
    0.38
    UnsafeEnabled
    0.31
    omitempty
    0.31
    abstractmethod
    0.29
    EditorBrowsable
    0.28
    Moy
    0.27
     initView
    0.27
     للمعارف
    0.27
     FetchType
    0.26
    VIAF
    0.26
    Act Density 0.514%

    No Known Activations