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

    Neuronpedia

    INDEX
    Explanations

    content related to violent protests and associated conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     keber
    -0.60
    AGRAM
    -0.58
    GOTREF
    -0.57
     InputDecoration
    -0.56
    ()]);
    -0.52
    Exists
    -0.49
    ätigung
    -0.47
    delwed
    -0.46
     existir
    -0.46
     sẵn
    -0.46
    POSITIVE LOGITS
     erupted
    0.81
     engulf
    0.76
     broke
    0.73
     erup
    0.73
     unfolding
    0.71
     pitting
    0.70
     sparked
    0.69
     ignited
    0.69
     involving
    0.69
    Spoljašnje
    0.68
    Act Density 0.336%

    No Known Activations