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

    Neuronpedia

    INDEX
    Explanations

    references to technology, computer science, and digital communication trends

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     gib
    -0.69
     decomp
    -0.65
     publicity
    -0.64
     Kafka
    -0.64
     assemb
    -0.63
    Buyable
    -0.63
     cob
    -0.62
    代
    -0.61
     GPS
    -0.60
    çīĪ
    -0.60
    POSITIVE LOGITS
    Ĵ
    1.05
    £
    0.98
    ¡
    0.93
    ¬
    0.91
    lege
    0.89
    ¯
    0.88
    ought
    0.87
    ¥
    0.87
    ĵ
    0.84
    ¤
    0.84
    Act Density 4.464%

    No Known Activations