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

    Neuronpedia

    INDEX
    Explanations

    qualities related to size, strength, or scale

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    udder
    -0.85
     Alternatively
    -0.72
    orthy
    -0.71
    yi
    -0.70
    ilaterally
    -0.70
     whichever
    -0.69
    another
    -0.69
    ptives
    -0.68
    utics
    -0.68
    REL
    -0.68
    POSITIVE LOGITS
     nature
    1.34
     popularity
    1.21
     lack
    1.06
     importance
    1.03
     similarities
    1.02
     availability
    1.02
     absence
    1.01
    ness
    1.01
     prevalence
    1.01
     tendency
    1.00
    Act Density 0.228%

    No Known Activations