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

    Neuronpedia

    INDEX
    Explanations

    special characters, particularly various forms of the © symbol and accents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -1.21
    GEBURTSDATUM
    -1.13
     preſent
    -1.01
     purpoſe
    -1.00
     ſy
    -1.00
     ſtate
    -0.99
     prefent
    -0.98
     fevere
    -0.98
     propOrder
    -0.96
     uſe
    -0.94
    POSITIVE LOGITS
    </em>
    0.98
    </i>
    0.89
    s
    0.81
     }}$
    0.78
    </sub>
    0.78
    </strong>
    0.76
     }}
    0.71
    </b>
    0.70
    </sup>
    0.70
    [toxicity=0]
    0.69
    Act Density 0.054%

    No Known Activations