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

    Neuronpedia

    INDEX
    Explanations

    references to things described as "high" or as having a notable level of something, such as "high-level," "high-profile," "high-growth," and "high-school."

    oai_token-act-pair · gpt-3.5-turbo

    references to "high" followed by any quality or characteristic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.81
    tnc
    -0.80
     Barg
    -0.72
     Doct
    -0.71
     Canaver
    -0.69
     Canad
    -0.69
     rall
    -0.68
     Dare
    -0.66
     Guang
    -0.65
    zag
    -0.65
    POSITIVE LOGITS
    rise
    0.93
    rises
    0.90
    lighting
    0.89
     enough
    0.87
    school
    0.85
    enough
    0.81
    ened
    0.81
    wind
    0.80
     school
    0.79
     altitude
    0.78
    Act Density 0.058%

    No Known Activations