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

    Neuronpedia

    INDEX
    Explanations

    measurements and quantities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrinth
    -0.73
     dearly
    -0.67
     unmist
    -0.62
     prominently
    -0.60
     strangely
    -0.60
    apego
    -0.59
    wagon
    -0.59
    raltar
    -0.58
     vividly
    -0.58
     extensively
    -0.58
    POSITIVE LOGITS
     percent
    1.05
     cents
    1.00
    %.
    0.91
     anymore
    0.82
    percent
    0.78
     fraction
    0.78
    %
    0.78
     ounces
    0.77
     degree
    0.75
     ounce
    0.74
    Act Density 0.092%

    No Known Activations