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

    Neuronpedia

    INDEX
    Explanations

    opening phrases or introductory elements in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.59
     myſelf
    -1.56
     Monfieur
    -1.48
     pleaſure
    -1.43
     reaſon
    -1.43
     purpoſe
    -1.43
     ―――――
    -1.41
     iſt
    -1.40
     whoſe
    -1.38
     Jefus
    -1.38
    POSITIVE LOGITS
    s
    0.82
    </em>
    0.77
    e
    0.76
    </i>
    0.72
    o
    0.68
     
    0.68
    i
    0.68
    t
    0.67
    !
    0.65
    )
    0.65
    Act Density 0.107%

    No Known Activations