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

    Neuronpedia

    INDEX
    Explanations

    repeated usage of the word "latter" to refer to previously mentioned concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.60
     or
    -0.57
     and
    -0.56
     []
    -0.54
     I
    -0.54
    [][]
    -0.53
     you
    -0.53
     for
    -0.52
     in
    -0.52
     more
    -0.50
    POSITIVE LOGITS
     متعلقه
    1.33
     تضيفلها
    1.16
     Majefty
    1.00
     Numerade
    0.99
     aforesaid
    0.96
     kasarigan
    0.95
    complexContent
    0.93
     Latter
    0.92
     aforementioned
    0.90
    rungsseite
    0.89
    Act Density 0.228%

    No Known Activations