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

    Neuronpedia

    INDEX
    Explanations

    words related to power dynamics and control

    oai_token-act-pair · gpt-3.5-turbo

    themes related to power and control dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.72
    isc
    -0.71
     Alto
    -0.70
    idan
    -0.68
    Interstitial
    -0.67
    TED
    -0.66
    eret
    -0.65
    iera
    -0.65
    ãĤ©
    -0.64
     HR
    -0.62
    POSITIVE LOGITS
     hierarch
    0.92
     supremacy
    0.87
     domination
    0.86
     hegemony
    0.83
     hierarchy
    0.82
     exerted
    0.78
    SHIP
    0.77
     dominance
    0.76
    eering
    0.75
     dominion
    0.74
    Act Density 0.098%

    No Known Activations