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

    Neuronpedia

    INDEX
    Explanations

    mentions of terrorist groups and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to terrorist groups and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    othy
    -0.73
    bernatorial
    -0.73
     Circuit
    -0.73
    ðĿ
    -0.72
     Shore
    -0.70
    ~~~~
    -0.68
    vent
    -0.67
    è¯
    -0.66
     Deck
    -0.66
     Wells
    -0.65
    POSITIVE LOGITS
     Boko
    0.97
    wana
    0.90
    atics
    0.88
    affiliated
    0.86
     jihadists
    0.86
    leader
    0.85
     insurgents
    0.85
     affili
    0.83
     affiliation
    0.81
     leader
    0.80
    Act Density 0.039%

    No Known Activations