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

    Neuronpedia

    INDEX
    Explanations

    links and references related to a specific platform

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vī
    -0.62
     kef
    -0.55
     mī
    -0.50
     dismant
    -0.49
     Dory
    -0.49
     vorrei
    -0.47
     scoffed
    -0.46
     neutralized
    -0.46
     Mercure
    -0.45
     Paradiso
    -0.45
    POSITIVE LOGITS
     Steam
    1.45
    Steam
    1.41
     steam
    1.41
    steam
    1.39
     STEAM
    1.19
     steamed
    0.93
     steaming
    0.86
     steamer
    0.85
     vapeur
    0.82
     étu
    0.73
    Act Density 0.072%

    No Known Activations