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

    Neuronpedia

    INDEX
    Explanations

    terms related to monitoring and evaluation systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    monitoring tools, systems, studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sober
    -0.40
     crumpled
    -0.36
     buy
    -0.35
     compound
    -0.35
    âge
    -0.34
     crumbled
    -0.33
     compra
    -0.33
     McBride
    -0.33
     wrinkle
    -0.33
     ru
    -0.32
    POSITIVE LOGITS
     monitoring
    1.59
     Monitoring
    1.49
     monitor
    1.48
    monitoring
    1.46
     monitored
    1.41
    Monitoring
    1.41
     Monitor
    1.40
     monitors
    1.39
    monitor
    1.38
     MONITORING
    1.37
    Act Density 0.023%

    No Known Activations