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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "human rights."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.55
    }
    -0.53
    ↵↵
    -0.51
    {
    -0.50
    .
    -0.49
    //
    -0.45
    <strong>
    -0.44
    )
    -0.44
    नि
    -0.44
    #
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.98
     GenerationType
    0.87
    RegressionTest
    0.84
    Parcelize
    0.80
    BeginContext
    0.76
    hassee
    0.75
     Biôgrafia
    0.75
    OrBuilder
    0.74
     Lighter
    0.74
    MessageOf
    0.71
    Act Density 0.152%

    No Known Activations