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

    Neuronpedia

    INDEX
    Explanations

    keywords related to fundamental principles or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    words related to fundamental concepts and principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    peak
    -0.75
    quer
    -0.74
    crow
    -0.69
    ILLE
    -0.68
     Leone
    -0.68
    rov
    -0.67
    pless
    -0.66
    rescent
    -0.66
    pload
    -0.66
    annis
    -0.66
    POSITIVE LOGITS
    ists
    1.12
    ist
    1.01
    ism
    0.98
     tenets
    0.93
    izes
    0.91
     flaw
    0.88
    izing
    0.88
    ogy
    0.88
     flaws
    0.88
    ization
    0.87
    Act Density 0.038%

    No Known Activations