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

    Neuronpedia

    INDEX
    Explanations

    mentions of political or social extremism

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "radical" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ursed
    -0.82
    ords
    -0.79
    hner
    -0.77
    sburgh
    -0.74
     Seller
    -0.73
    urses
    -0.71
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.70
    zzo
    -0.69
    ORD
    -0.68
    Crash
    -0.68
    POSITIVE LOGITS
     Islamist
    1.01
    ized
    0.99
    izing
    0.97
     Islamists
    0.95
    ism
    0.94
    ization
    0.92
    ising
    0.88
     fringe
    0.88
     leftist
    0.84
     Islamic
    0.82
    Act Density 0.015%

    No Known Activations