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

    Neuronpedia

    INDEX
    Explanations

    steps and sequences in procedural or instructional texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barbier
    -0.88
    }});
    -0.83
    "])
    -0.83
    tahankan
    -0.82
    }$)
    -0.80
    锢
    -0.78
    ↴
    -0.78
     Hauser
    -0.77
     Aner
    -0.77
     )}$
    -0.77
    POSITIVE LOGITS
     STEP
    2.15
     step
    2.05
     Step
    2.00
    Step
    1.94
     steps
    1.91
    step
    1.84
     Steps
    1.83
    STEP
    1.82
     STEPS
    1.74
    Steps
    1.65
    Act Density 0.059%

    No Known Activations