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

    Neuronpedia

    INDEX
    Explanations

    expressions related to governmental or institutional critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     udah
    -0.72
     kinda
    -0.71
     чтоб
    -0.70
     eachother
    -0.66
    ज़
    -0.64
     youll
    -0.64
    ”…
    -0.62
    …’
    -0.60
     loosing
    -0.60
     sorta
    -0.60
    POSITIVE LOGITS
     hon
    0.70
    Хочу
    0.67
     Column
    0.63
    -[
    0.62
     Government
    0.61
     ◄
    0.60
     SHRI
    0.60
     Parliament
    0.58
     Mr
    0.57
     """
    0.56
    Act Density 0.068%

    No Known Activations