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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and computer programming

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "o" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -0.87
     Seym
    -0.79
    ĸļ
    -0.71
     carriage
    -0.70
    rils
    -0.66
    tml
    -0.64
     condem
    -0.64
     unfocusedRange
    -0.63
     cryst
    -0.62
     ASP
    -0.61
    POSITIVE LOGITS
    zzi
    1.08
    zzo
    1.01
    vernment
    0.87
    ogle
    0.87
    jo
    0.86
    ctor
    0.85
    Desk
    0.85
    oh
    0.83
    ope
    0.83
    ctr
    0.83
    Act Density 0.035%

    No Known Activations