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

    Neuronpedia

    INDEX
    Explanations

    references to Marxist concepts and principles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -4.21
     don
    -0.83
     add
    -0.82
     do
    -0.81
    ,
    -0.80
     get
    -0.79
    .
    -0.79
     are
    -0.79
     in
    -0.77
     re
    -0.77
    POSITIVE LOGITS
     napoli
    2.18
     milano
    2.06
     santiago
    1.98
     bandung
    1.97
     lidl
    1.95
     stockholm
    1.94
     ibiza
    1.90
     pican
    1.89
     maroc
    1.83
     ricardo
    1.83
    Act Density 2.964%

    No Known Activations