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

    Neuronpedia

    INDEX
    Explanations

    words related to the action of 'deposing' or 'removing someone or something from a position of power or authority'

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "deprivation" or being "deposed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dragonbound
    -0.97
     Millennium
    -0.80
    SHIP
    -0.78
    ãĤ¤ãĥĪ
    -0.76
    WORK
    -0.74
    ALLY
    -0.70
    姫
    -0.70
    ãĥ´ãĤ¡
    -0.67
    MY
    -0.67
     Hole
    -0.67
    POSITIVE LOGITS
    utations
    1.13
    utation
    1.10
    reci
    1.03
    raved
    1.00
    ository
    1.00
    ravity
    1.00
    orters
    0.96
    rogram
    0.93
    amping
    0.92
    rec
    0.91
    Act Density 0.025%

    No Known Activations