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

    Neuronpedia

    INDEX
    Explanations

    terms related to healthcare policy and financial regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.69
     Soph
    -0.69
     TOUR
    -0.68
    Magikarp
    -0.67
     pestic
    -0.66
    Sensor
    -0.66
    ç·
    -0.65
     FIG
    -0.64
     Ath
    -0.62
    radio
    -0.62
    POSITIVE LOGITS
     indefinitely
    0.94
     unilaterally
    0.89
     cheaply
    0.89
     altogether
    0.88
     permanently
    0.81
     domestically
    0.79
     unnecessarily
    0.79
     globally
    0.78
     ASAP
    0.78
     amid
    0.77
    Act Density 0.145%

    No Known Activations