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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power and control, specifically dominance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of dominance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eret
    -0.78
     HR
    -0.72
    idan
    -0.70
    gm
    -0.68
    rec
    -0.68
    rive
    -0.64
    gnu
    -0.64
    ead
    -0.63
    glass
    -0.63
    yrinth
    -0.63
    POSITIVE LOGITS
     dominance
    0.84
     dominate
    0.81
     precedence
    0.80
     overshadow
    0.79
     domination
    0.77
    xual
    0.77
     hegemony
    0.77
     supremacy
    0.76
    iveness
    0.74
     force
    0.70
    Act Density 0.033%

    No Known Activations