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

    Neuronpedia

    INDEX
    Explanations

    instances of conflict between groups or regions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Discuss
    -0.76
    ftime
    -0.74
    bard
    -0.73
    ccording
    -0.73
    quest
    -0.73
    kar
    -0.72
    wow
    -0.72
    spir
    -0.71
    notations
    -0.71
    vier
    -0.70
    POSITIVE LOGITS
     its
    0.72
     Olympia
    0.66
     Silicon
    0.66
     vanquished
    0.66
     destiny
    0.66
     Chinatown
    0.65
     neighboring
    0.63
     neighbouring
    0.63
     ours
    0.62
     Customs
    0.62
    Act Density 0.098%

    No Known Activations