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

    Neuronpedia

    INDEX
    Explanations

    information related to nuclear energy, nuclear warfare, nuclear safety, and nuclear ethics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to nuclear ethics and security discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.19
    3:0.10
    4:0.04
    5:0.06
    6:0.03
    7:0.06
    8:0.04
    9:0.17
    10:0.08
    11:0.03
    Negative Logits
     unconsciously
    -1.40
     Vegan
    -1.32
    xual
    -1.27
     Gaga
    -1.25
     Gamer
    -1.25
     Pagan
    -1.20
     Autism
    -1.20
    heard
    -1.20
     LGBTQ
    -1.19
     Ellie
    -1.19
    POSITIVE LOGITS
     reactors
    1.73
     submarines
    1.71
     submarine
    1.61
     reactor
    1.50
     decom
    1.45
     uranium
    1.43
     Annex
    1.39
     plutonium
    1.38
    uclear
    1.34
     warheads
    1.34
    Act Density 0.040%

    No Known Activations