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

    Neuronpedia

    INDEX
    Explanations

    references to distances measured in miles and kilometers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //
    -0.71
    ellery
    -0.59
    itory
    -0.58
    OBS
    -0.55
    AAT
    -0.54
    pang
    -0.54
    DotNetBar
    -0.54
     Barbier
    -0.54
    Jeografia
    -0.52
    🏿
    -0.52
    POSITIVE LOGITS
     miles
    1.59
     mile
    1.41
     kilometers
    1.37
    miles
    1.36
     km
    1.36
     kilometres
    1.36
     MILE
    1.28
    mile
    1.27
     kilometer
    1.25
     MILES
    1.20
    Act Density 0.078%

    No Known Activations