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

    Neuronpedia

    INDEX
    Explanations

    topics related to government and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.24
    ]--;
    -1.05
     متعلقه
    -0.94
     ModelExpression
    -0.91
    ſelves
    -0.84
     Anſ
    -0.83
    kháu
    -0.81
    tonode
    -0.78
     itſelf
    -0.77
    MessageOf
    -0.77
    POSITIVE LOGITS
     den
    0.56
     de
    0.52
     ut
    0.52
    ↵↵
    0.49
    :
    0.48
     sau
    0.47
    <eos>
    0.47
     hal
    0.47
     op
    0.45
     said
    0.44
    Act Density 0.150%

    No Known Activations