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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hierarchical ranks and positions of authority

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to power and hierarchy within social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bombs
    -0.85
     Collider
    -0.78
     Buzz
    -0.74
    REAM
    -0.74
    Crash
    -0.74
    Buzz
    -0.73
     glitch
    -0.73
     Recession
    -0.73
    FFER
    -0.73
    Kick
    -0.72
    POSITIVE LOGITS
     hereditary
    1.63
     nobility
    1.62
     aristocracy
    1.53
     hierarchy
    1.48
     hierarch
    1.42
     hierarchical
    1.37
     arist
    1.36
     superiors
    1.35
     nobles
    1.34
     priesthood
    1.33
    Act Density 0.526%

    No Known Activations