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

    Neuronpedia

    INDEX
    Explanations

    mathematical and technical symbols or notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bkz
    -0.88
     trin
    -0.82
     Noth
    -0.79
    trin
    -0.77
     pst
    -0.74
     GTR
    -0.73
     Gwend
    -0.72
     Zin
    -0.72
     Lizzy
    -0.72
    ׂ
    -0.72
    POSITIVE LOGITS
    .]
    0.97
    ]].
    0.93
    ],
    0.91
    _]
    0.90
    ]]
    0.89
    ].
    0.86
     ],
    0.85
    !]
    0.84
    }]
    0.82
     $]$
    0.81
    Act Density 0.411%

    No Known Activations