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

    Neuronpedia

    INDEX
    Explanations

    words related to extremism or radicalism, particularly in the context of political or religious ideologies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.74
    fman
    -0.74
    ursed
    -0.73
    pty
    -0.70
    aird
    -0.70
    FACE
    -0.70
    urses
    -0.69
    hner
    -0.69
    ORD
    -0.69
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    POSITIVE LOGITS
    ism
    1.17
    ized
    1.11
    ization
    1.10
     Islamist
    1.09
    izing
    1.09
     Islamists
    1.07
     fringe
    0.96
     chic
    0.96
    isation
    0.95
    ising
    0.94
    Act Density 0.060%

    No Known Activations