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

    Neuronpedia

    INDEX
    Explanations

    commands and information related to software tools or systems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     inder
    -0.87
     glan
    -0.80
     kosme
    -0.79
     fte
    -0.78
     Sted
    -0.77
     secon
    -0.76
     oner
    -0.76
     Ede
    -0.76
     overla
    -0.75
     luf
    -0.75
    POSITIVE LOGITS
     drill
    1.42
     drilling
    1.33
     drilled
    1.29
     drills
    1.24
    drill
    1.23
     Drill
    1.15
    Drill
    1.07
     Drilling
    1.02
    rilled
    0.96
    Drilling
    0.91
    Act Density 0.094%

    No Known Activations