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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, likely related to news articles or stories

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussion
    -0.89
    anwhile
    -0.86
     unden
    -0.84
    wcs
    -0.83
     livest
    -0.80
    quartered
    -0.78
    obyl
    -0.78
     coincide
    -0.77
    ãĤ´
    -0.73
     destro
    -0.73
    POSITIVE LOGITS
     Hyde
    0.90
     Olympia
    0.90
     Claus
    0.87
     Robot
    0.86
     McMahon
    0.84
     Bezos
    0.84
     Ack
    0.84
     Spock
    0.83
     Pe
    0.82
     Rogers
    0.82
    Act Density 0.055%

    No Known Activations