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

    Neuronpedia

    INDEX
    Explanations

    high-frequency occurrences of the word "the" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -1.30
     myſelf
    -1.10
     itſelf
    -1.10
     auffi
    -1.05
     Majefty
    -1.02
     Houſe
    -1.02
     raiſ
    -1.01
     ſtate
    -0.95
     fubject
    -0.94
     purpoſe
    -0.93
    POSITIVE LOGITS
     The
    1.87
    The
    1.79
     THE
    1.64
     the
    1.64
    THE
    1.42
    the
    1.30
    rethe
    1.21
    ethe
    1.11
    sthe
    1.10
    ithe
    1.04
    Act Density 2.988%

    No Known Activations