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

    Neuronpedia

    INDEX
    Explanations

    phrases summarizing information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bees
    -0.81
    duct
    -0.78
     charism
    -0.77
    gypt
    -0.75
     Wee
    -0.73
    eno
    -0.69
    enne
    -0.68
    train
    -0.68
    Sea
    -0.67
    ghost
    -0.64
    POSITIVE LOGITS
     summ
    0.88
     summarize
    0.82
     summar
    0.80
     summary
    0.79
    lations
    0.77
     thereof
    0.72
    itious
    0.72
     overview
    0.71
     summarizes
    0.71
    panel
    0.71
    Act Density 0.118%

    No Known Activations