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

    Neuronpedia

    INDEX
    Explanations

    phrases that utilize the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.13
     raiſ
    -1.06
     pleaſure
    -1.01
     Houſe
    -0.97
     ſta
    -0.96
     houſe
    -0.95
     ſever
    -0.94
     Conſ
    -0.94
     Anſ
    -0.93
    ſelf
    -0.93
    POSITIVE LOGITS
     as
    1.21
     As
    1.20
     AS
    1.17
    readAs
    1.05
    As
    1.03
     a
    0.92
     CreateTagHelper
    0.83
     an
    0.82
    as
    0.78
    AS
    0.75
    Act Density 0.343%

    No Known Activations