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

    Neuronpedia

    INDEX
    Explanations

    terms related to political ideologies and extremism

    oai_token-act-pair · gpt-3.5-turbo

    references to extremist political groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cola
    -0.76
     Doodle
    -0.73
    Anonymous
    -0.70
     ..............
    -0.70
    ||
    -0.69
    natureconservancy
    -0.69
     ACTIONS
    -0.67
    ADRA
    -0.67
     BB
    -0.65
     Moons
    -0.63
    POSITIVE LOGITS
    ishly
    0.86
    reaching
    0.81
    ibaba
    0.79
    coe
    0.77
    ctic
    0.76
     distances
    0.74
    rency
    0.73
    fetched
    0.72
    agher
    0.68
    inent
    0.68
    Act Density 0.118%

    No Known Activations