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

    Neuronpedia

    INDEX
    Explanations

    tech-related terms and internet platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific topics or entities related to health, safety, environmental, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ble
    -0.58
     Coastal
    -0.54
     Tropical
    -0.53
    hap
    -0.52
     Bod
    -0.51
    nos
    -0.51
    bre
    -0.50
    Hur
    -0.49
    Motor
    -0.48
    wegian
    -0.48
    POSITIVE LOGITS
     Citadel
    0.60
     rul
    0.55
     abroad
    0.55
     outweigh
    0.54
     immortality
    0.53
     syndrome
    0.53
     altogether
    0.53
     itself
    0.53
    anasia
    0.52
     disadvantages
    0.52
    Act Density 0.706%

    No Known Activations