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

    Neuronpedia

    INDEX
    Explanations

    words related to controversies, disputes, and debates

    oai_token-act-pair · gpt-3.5-turbo

    references to controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.75
    urances
    -0.74
    ©¶æ
    -0.73
    ingers
    -0.72
    avement
    -0.71
    berman
    -0.69
    glas
    -0.68
    icrobial
    -0.68
    atal
    -0.67
    itions
    -0.67
    POSITIVE LOGITS
     controversy
    0.99
     controversies
    0.94
    naire
    0.93
     uproar
    0.92
     flared
    0.85
     revolving
    0.85
     erupted
    0.83
     arises
    0.82
     involving
    0.81
    naires
    0.80
    Act Density 0.014%

    No Known Activations