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

    Neuronpedia

    INDEX
    Explanations

    terms related to foundational principles or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fundamental" and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leone
    -0.76
    pload
    -0.75
    quer
    -0.73
    wick
    -0.70
    fing
    -0.70
    crow
    -0.69
    chief
    -0.69
    ensen
    -0.69
    spr
    -0.68
    annis
    -0.68
    POSITIVE LOGITS
    ists
    1.22
    ist
    1.11
    ism
    1.10
     misunderstanding
    1.02
     tenets
    0.99
     principles
    0.97
    istic
    0.95
    izing
    0.95
     alteration
    0.94
    izes
    0.94
    Act Density 0.032%

    No Known Activations