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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.81
     P
    -0.63
    </em>
    -0.63
     I
    -0.60
    }`).
    -0.58
     
    -0.58
     ],
    -0.54
     )
    -0.54
     ]
    -0.52
    angas
    -0.52
    POSITIVE LOGITS
     Majefty
    1.27
     purpoſe
    1.16
     houſe
    1.14
     Reſ
    1.13
     pleaſure
    1.13
     Monfieur
    1.13
     reaſon
    1.10
     ſtate
    1.09
     Anſ
    1.08
     juſ
    1.07
    Act Density 0.288%

    No Known Activations