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

    Neuronpedia

    INDEX
    Explanations

    words related to uprisings, revolts, and rebellions

    oai_token-act-pair · gpt-3.5-turbo

    references to rebellions and revolts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchin
    -0.86
    ewater
    -0.85
    illac
    -0.84
     Parenthood
    -0.81
    icrobial
    -0.73
    estone
    -0.72
     Hilbert
    -0.69
    foundation
    -0.69
    onut
    -0.68
    ŀ
    -0.68
    POSITIVE LOGITS
     rebellion
    1.01
     revolt
    0.95
     uprising
    0.87
     against
    0.84
     insurrection
    0.83
     defiant
    0.81
     overth
    0.79
     revol
    0.78
    naire
    0.77
     rebell
    0.77
    Act Density 0.039%

    No Known Activations