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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific objects or tools, particularly bowls

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.78
    kson
    -0.72
    apse
    -0.70
     Assass
    -0.67
    bourg
    -0.66
     Hugo
    -0.66
     Bundes
    -0.65
     Phantom
    -0.64
     Draper
    -0.64
     Monarch
    -0.63
    POSITIVE LOGITS
    pipe
    1.04
    ers
    0.96
    cup
    0.91
    bowl
    0.90
    hend
    0.88
     bowl
    0.87
    halla
    0.84
    waters
    0.83
    pour
    0.82
    gary
    0.82
    Act Density 0.015%

    No Known Activations