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

    Neuronpedia

    INDEX
    Explanations

    references to peace activists and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DebuggerStep
    -0.48
     nhật
    -0.46
    >{@
    -0.46
    теристики
    -0.44
     propOrder
    -0.43
     Picchu
    -0.41
     للمعارف
    -0.41
     guapa
    -0.41
    Слу
    -0.40
    脚注の使い方
    -0.39
    POSITIVE LOGITS
     violence
    0.72
    violence
    0.66
     Violence
    0.63
    Violence
    0.63
     peace
    0.57
     conflict
    0.56
    peace
    0.56
     violent
    0.55
    conflict
    0.54
     Konflikt
    0.53
    Act Density 0.391%

    No Known Activations