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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hierarchy or leadership levels

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    lez
    -0.77
     Andromeda
    -0.77
     Canaver
    -0.74
    Sund
    -0.73
    pload
    -0.72
    wolves
    -0.71
    ELY
    -0.69
    Thor
    -0.69
    STAR
    -0.69
    rower
    -0.68
    POSITIVE LOGITS
     certific
    0.77
    xual
    0.77
     crossings
    0.70
     administrative
    0.69
    chart
    0.68
     advancement
    0.67
    ropri
    0.67
     enrichment
    0.67
    level
    0.67
     elevation
    0.66
    Act Density 0.027%

    No Known Activations