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

    Neuronpedia

    INDEX
    Explanations

    texts with references to a utopian or dystopian future

    oai_token-act-pair · gpt-3.5-turbo

    terms related to utopian and dystopian concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contest
    -0.64
    hips
    -0.63
     Dart
    -0.61
     Carnival
    -0.59
     roundup
    -0.58
     warnings
    -0.58
     endorsements
    -0.57
     search
    -0.57
     adversary
    -0.57
    wagen
    -0.56
    POSITIVE LOGITS
    ilitarian
    1.55
    opia
    1.29
    ility
    1.24
    ilities
    1.15
    ricular
    1.11
    ils
    1.10
    tering
    1.09
    iquette
    1.09
    terness
    1.07
    ter
    1.05
    Act Density 0.034%

    No Known Activations