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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to wars or campaigns against certain societal issues, specifically emphasizing the phrase "war on"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "war on" in various contexts, particularly relating to social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iate
    -0.81
    rete
    -0.80
    VP
    -0.78
    ahime
    -0.78
    gaard
    -0.75
    auga
    -0.74
    SourceFile
    -0.73
    vp
    -0.72
    encies
    -0.70
    âĵĺ
    -0.70
    POSITIVE LOGITS
     Armageddon
    0.85
     terror
    0.72
     Atlantis
    0.71
     ruining
    0.69
     attrition
    0.67
     Barrett
    0.67
     AMERICA
    0.66
     war
    0.66
     Drugs
    0.65
     wheels
    0.64
    Act Density 0.073%

    No Known Activations