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

    Neuronpedia

    INDEX
    Explanations

    references to steps in a process or procedure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barbier
    -0.96
    "])
    -0.89
    }});
    -0.83
    锢
    -0.79
     )}$
    -0.78
    }$)
    -0.78
    tahankan
    -0.77
    ↴
    -0.77
     Ärz
    -0.77
     Hauser
    -0.76
    POSITIVE LOGITS
     STEP
    2.07
     step
    1.95
     Step
    1.94
    Step
    1.89
     steps
    1.81
    STEP
    1.75
     Steps
    1.75
    step
    1.75
     STEPS
    1.67
    Steps
    1.59
    Act Density 0.050%

    No Known Activations