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

    Neuronpedia

    INDEX
    Explanations

    legal and political terms and situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     disemb
    -0.83
     handmade
    -0.81
     workspace
    -0.79
     glim
    -0.79
     paddle
    -0.79
     corrid
    -0.77
     quir
    -0.77
     hatch
    -0.77
     helper
    -0.76
     solo
    -0.76
    POSITIVE LOGITS
     Worse
    1.59
     Shame
    1.41
     Surely
    1.39
     Moreover
    1.38
     Furthermore
    1.36
     Instead
    1.33
     Needless
    1.29
     Therefore
    1.27
     Meanwhile
    1.26
     Hence
    1.26
    Act Density 0.565%

    No Known Activations