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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of distance or location

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    🥲
    -0.58
     😭😭
    -0.57
     🤣🤣
    -0.56
     cirque
    -0.55
    ypeł
    -0.55
     🥲
    -0.55
     😌
    -0.54
     ❤️❤️
    -0.53
    😌
    -0.53
     amanda
    -0.53
    POSITIVE LOGITS
     tamen
    0.55
     MÁ
    0.54
     tabu
    0.54
     Okt
    0.53
     Gorb
    0.50
     geograf
    0.49
     antik
    0.49
     polig
    0.48
     monaster
    0.48
     Schrö
    0.48
    Act Density 0.208%

    No Known Activations