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

    Neuronpedia

    INDEX
    Explanations

    terms related to protests and social demonstrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     otomatig
    -0.46
    AutoField
    -0.38
     дописавши
    -0.37
     gange
    -0.37
    uría
    -0.35
    Παραπομπές
    -0.34
     fopen
    -0.33
    Odkazy
    -0.33
    abestanden
    -0.33
    Rujuakan
    -0.32
    POSITIVE LOGITS
     terrorist
    0.83
     fade
    0.79
     rebel
    0.77
     protest
    0.76
     Protest
    0.75
     anarchist
    0.74
     Marxist
    0.74
    protest
    0.73
    Radical
    0.72
     communist
    0.71
    Act Density 0.197%

    No Known Activations