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

    Neuronpedia

    INDEX
    Explanations

    references to cults

    oai_token-act-pair · gpt-3.5-turbo

    references to cults and cult-like groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deen
    -0.73
     Turk
    -0.70
    forth
    -0.66
    cknowled
    -0.65
    LOAD
    -0.64
     Lakes
    -0.63
     Shay
    -0.63
    horn
    -0.63
     Jav
    -0.62
    lled
    -0.62
    POSITIVE LOGITS
    ivating
    1.05
    ivation
    1.01
    ivated
    0.96
    cult
    0.96
    ists
    0.95
    etically
    0.94
     cult
    0.93
    etic
    0.92
    urally
    0.92
    ophon
    0.91
    Act Density 0.013%

    No Known Activations