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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "sealed" or variations of it

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     hålla
    -0.61
    mybatisplus
    -0.59
     lära
    -0.58
    <bos>
    -0.57
     känna
    -0.55
     tänka
    -0.54
     lägga
    -0.50
     finnas
    -0.49
     hjälpa
    -0.48
     läsa
    -0.47
    POSITIVE LOGITS
     Se
    1.09
    Se
    1.06
     SE
    0.91
     sergio
    0.86
     se
    0.85
     sebastian
    0.85
     Segovia
    0.83
     Seiz
    0.80
     Sé
    0.80
     Seer
    0.80
    Act Density 0.177%

    No Known Activations