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

    Neuronpedia

    INDEX
    Explanations

    words related to dominance or control in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dominance or control in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pt
    -0.69
    lev
    -0.67
    endment
    -0.65
    aration
    -0.65
    spir
    -0.61
    othy
    -0.60
    ilk
    -0.59
    ne
    -0.59
    resso
    -0.59
    ead
    -0.59
    POSITIVE LOGITS
     dominated
    0.74
     headlines
    0.73
    ICS
    0.69
    SHIP
    0.69
     dominates
    0.69
     overshadowed
    0.67
    pread
    0.65
    byss
    0.65
     Cav
    0.64
     dominate
    0.63
    Act Density 0.035%

    No Known Activations