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

    Neuronpedia

    INDEX
    Explanations

    information about reported killings and attacks, especially in conflict zones

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ational
    -0.76
    Completed
    -0.76
    Website
    -0.75
    $$$$
    -0.73
    caster
    -0.73
    Bey
    -0.70
    Publisher
    -0.69
    ibles
    -0.69
    ãĤ¹ãĥĪ
    -0.69
    oyer
    -0.69
    POSITIVE LOGITS
     infancy
    1.14
     childbirth
    1.13
     pursuit
    0.98
     relation
    0.93
     lieu
    0.92
     gunfire
    0.92
     Afghanistan
    0.90
     captivity
    0.89
     Rwanda
    0.88
     shootings
    0.85
    Act Density 0.131%

    No Known Activations