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

    Neuronpedia

    INDEX
    Explanations

    words related to construction or development projects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Newsletter
    -0.79
    soever
    -0.72
    /-
    -0.70
     viz
    -0.69
    Lear
    -0.67
    usercontent
    -0.65
    âĨij
    -0.63
     Metallic
    -0.62
     {*
    -0.62
     Mechanical
    -0.61
    POSITIVE LOGITS
     finally
    0.87
     unveiled
    0.83
     poised
    0.82
     hailed
    0.78
     gearing
    0.77
     honoured
    0.76
     officially
    0.76
     reinvent
    0.75
     reportedly
    0.75
     thrilled
    0.75
    Act Density 0.553%

    No Known Activations