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

    Neuronpedia

    INDEX
    Explanations

    references to communication and legal matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    joice
    -0.68
    Mods
    -0.67
     wre
    -0.63
     sucker
    -0.63
     Majesty
    -0.62
     fundamentals
    -0.61
    pmwiki
    -0.61
     mete
    -0.60
     sights
    -0.60
     cataly
    -0.60
    POSITIVE LOGITS
     anonymity
    1.03
     emailed
    0.91
     HuffPost
    0.88
     surn
    0.85
     newsp
    0.80
    fax
    0.78
     confidentiality
    0.76
    ispers
    0.75
     disclosed
    0.74
     contacted
    0.73
    Act Density 1.300%

    No Known Activations