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

    Neuronpedia

    INDEX
    Explanations

    words related to authority, power, and hierarchy, often with intense emotional connotations

    oai_token-act-pair · gpt-3.5-turbo

    variations of the term "cult."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.74
    STON
    -0.73
    BY
    -0.65
    LOC
    -0.65
    creen
    -0.64
    士
    -0.63
    CHR
    -0.61
    ãĥīãĥ©ãĤ´ãĥ³
    -0.61
    女
    -0.61
    ETS
    -0.61
    POSITIVE LOGITS
    imately
    1.23
    iple
    1.16
    raviolet
    1.13
    urally
    1.01
    imates
    1.00
    iful
    0.95
    icultural
    0.95
    rition
    0.94
    anamo
    0.94
    ipl
    0.93
    Act Density 0.020%

    No Known Activations