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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "as" and its variants to denote comparisons and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onna
    -0.17
    anvas
    -0.16
     Declarations
    -0.16
     DÄĽ
    -0.16
    ntag
    -0.16
    à¸Ĭà¸Ļ
    -0.15
    imits
    -0.15
    _UNDEFINED
    -0.15
    ager
    -0.15
    inho
    -0.15
    POSITIVE LOGITS
     besides
    0.19
     yet
    0.15
     far
    0.15
     sparing
    0.14
     apart
    0.14
    urance
    0.14
     Nun
    0.14
    YLON
    0.14
    ervo
    0.14
    æŁĦ
    0.14
    Act Density 0.060%

    No Known Activations