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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal documents and formal procedures

    oai_token-act-pair · gpt-3.5-turbo

    sequences that indicate the presence of an end of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vulner
    -0.57
     practise
    -0.55
     Vaugh
    -0.52
     tatt
    -0.51
     spreads
    -0.51
     guarding
    -0.50
     advoc
    -0.50
     stretches
    -0.49
    avorite
    -0.48
     Sark
    -0.47
    POSITIVE LOGITS
     RELEASE
    0.71
     Robots
    0.66
     Forums
    0.65
    displayText
    0.65
     Quote
    0.64
     largeDownload
    0.63
    fml
    0.62
     Written
    0.61
     Beginning
    0.61
     Scene
    0.61
    Act Density 0.132%

    No Known Activations