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

    Neuronpedia

    INDEX
    Explanations

    references to groups or movements characterized by strong devotion or following

    oai_token-act-pair · gpt-3.5-turbo

    references to "cult" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forth
    -0.76
    deen
    -0.66
    Downloadha
    -0.64
     Ake
    -0.62
     Stra
    -0.62
    FORE
    -0.62
    Bloomberg
    -0.61
     OB
    -0.61
    lihood
    -0.61
    berry
    -0.60
    POSITIVE LOGITS
    ivating
    1.23
    ivated
    1.20
    ivation
    1.19
    urally
    1.14
    ures
    1.07
    ists
    1.04
    urable
    0.98
    ura
    0.96
    ogenic
    0.96
    ured
    0.93
    Act Density 0.050%

    No Known Activations