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

    Neuronpedia

    INDEX
    Explanations

    extremist groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of extremists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Buff
    -0.80
     Pool
    -0.78
     Harbor
    -0.70
     Harbour
    -0.69
     Lilly
    -0.68
    lain
    -0.67
     Sailor
    -0.66
     ping
    -0.65
     Landing
    -0.64
     docks
    -0.64
    POSITIVE LOGITS
     extremists
    3.16
     extremist
    3.03
     extremism
    2.97
     Extrem
    1.98
     radicals
    1.67
     fundamentalist
    1.56
     Islamist
    1.46
     jihadist
    1.44
     separatists
    1.43
     jihadists
    1.41
    Act Density 0.017%

    No Known Activations