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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or rankings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    matter
    -0.91
     Akin
    -0.69
    Stock
    -0.69
    Emb
    -0.68
    Url
    -0.65
    agement
    -0.63
    ptroller
    -0.63
     Quantity
    -0.63
    ighter
    -0.63
    unker
    -0.62
    POSITIVE LOGITS
     finalists
    0.92
     ways
    0.76
    teenth
    0.74
     quir
    0.73
     dozen
    0.72
     possible
    0.71
     factors
    0.70
     siblings
    0.70
     remaining
    0.68
     possibilities
    0.68
    Act Density 0.061%

    No Known Activations