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

    Neuronpedia

    INDEX
    Explanations

    Verbs or phrases related to being in a position of power or control

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dominated" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pt
    -0.73
    issue
    -0.72
    lev
    -0.70
    venture
    -0.70
    ft
    -0.68
    abet
    -0.67
    sale
    -0.65
    leeve
    -0.65
    safety
    -0.64
    anger
    -0.64
    POSITIVE LOGITS
     dominated
    0.95
     dominates
    0.89
    xual
    0.85
     dominate
    0.82
     overshadowed
    0.77
     headlines
    0.73
    SHIP
    0.72
     predomin
    0.71
    rative
    0.67
    kef
    0.67
    Act Density 0.013%

    No Known Activations