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

    Neuronpedia

    INDEX
    Explanations

    references to stages or classifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riwal
    -0.94
    ]))
    -0.85
    CrossRef
    -0.85
    }')
    -0.85
    ]--;
    -0.83
     \]
    -0.83
    }),
    -0.81
     Vienne
    -0.79
     Karlsson
    -0.79
    )),
    -0.79
    POSITIVE LOGITS
     Stage
    2.01
     STAGE
    1.97
    Stage
    1.94
    stage
    1.89
     stage
    1.86
    STAGE
    1.82
     stages
    1.78
    stages
    1.70
    Stages
    1.65
     Stages
    1.64
    Act Density 0.033%

    No Known Activations