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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technological advancements and changes over time

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     sophistic
    -0.86
     unspeak
    -0.83
     indestru
    -0.83
     inconce
    -0.79
     shenan
    -0.78
     intrigu
    -0.76
     indescri
    -0.75
     hentai
    -0.75
     downvotes
    -0.74
     impra
    -0.73
    POSITIVE LOGITS
     anymore
    1.06
    <bos>
    0.85
     enää
    0.63
    otheby
    0.59
     lagi
    0.52
     AssemblyCulture
    0.49
    SourceChecksum
    0.48
     sumpay
    0.48
     traditional
    0.48
    Jereo
    0.48
    Act Density 0.470%

    No Known Activations