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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey equivalence or similarity in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matmul
    -0.53
    AsUp
    -0.51
     <=",
    -0.51
    PDOException
    -0.50
    goire
    -0.49
    出版年
    -0.46
     contextLoads
    -0.45
    Getenv
    -0.45
    __':
    -0.45
     ellers
    -0.44
    POSITIVE LOGITS
     synonymous
    1.31
     interchangeably
    1.10
    same
    1.02
     synonym
    1.01
     same
    0.99
     dasselbe
    0.98
     hetzelfde
    0.96
    Same
    0.95
    SAME
    0.93
     Same
    0.92
    Act Density 0.476%

    No Known Activations