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

    Neuronpedia

    INDEX
    Explanations

    phrases related to protest and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -1.62
    “
    -1.51
     "
    -1.39
    ，“
    -1.30
    。“
    -1.15
    —“
    -1.14
    -“
    -1.12
    ：“
    -1.09
    {"
    -1.08
     (“
    -1.08
    POSITIVE LOGITS
     '
    2.23
     ‘
    1.93
    『
    1.61
    -'
    1.59
    、『
    1.57
     ('
    1.56
     (‘
    1.52
    ,'
    1.50
    。『
    1.48
    ='
    1.46
    Act Density 4.265%

    No Known Activations