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

    Neuronpedia

    INDEX
    Explanations

    references to fan followings or devoted followers

    oai_token-act-pair · gpt-3.5-turbo

    references to cults and cult-like phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Turk
    -0.65
     Ake
    -0.64
     Stra
    -0.64
    etter
    -0.64
    etsk
    -0.62
    Bloomberg
    -0.62
     Vag
    -0.61
    forth
    -0.60
     Ness
    -0.59
     Nieto
    -0.58
    POSITIVE LOGITS
    ivating
    1.39
    ivated
    1.38
    ivation
    1.34
    urally
    1.28
    ures
    1.14
    urable
    1.03
    ured
    1.02
    ogenic
    0.98
    ists
    0.97
    ishly
    0.94
    Act Density 0.026%

    No Known Activations