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

    Neuronpedia

    INDEX
    Explanations

    words related to fundamental beliefs, foundations, or origins

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe foundational beliefs or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.81
    yy
    -0.71
    fax
    -0.71
    ilst
    -0.70
    nw
    -0.70
    bats
    -0.69
    immer
    -0.69
    inarily
    -0.69
    bass
    -0.69
    ura
    -0.69
    POSITIVE LOGITS
     principles
    1.23
     belief
    1.04
     principle
    1.04
     ideals
    0.98
     falsehood
    0.97
     fear
    0.97
     conviction
    0.95
     beliefs
    0.93
     fundamentals
    0.91
     notions
    0.89
    Act Density 0.203%

    No Known Activations