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

    Neuronpedia

    INDEX
    Explanations

    measurements related to length, especially in inches

    oai_token-act-pair · gpt-3.5-turbo

    measurements related to length or height

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -1.04
     Purpose
    -0.80
     Mothers
    -0.78
    ggies
    -0.73
    eer
    -0.72
    eem
    -0.70
     Voc
    -0.68
    ctors
    -0.65
     Byrne
    -0.64
    CAST
    -0.64
    POSITIVE LOGITS
     inches
    0.89
    terness
    0.87
     inch
    0.79
    hops
    0.79
    hooting
    0.76
    peed
    0.74
    !/
    0.71
    hip
    0.70
     tall
    0.69
     "$:/
    0.68
    Act Density 0.010%

    No Known Activations