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

    Neuronpedia

    INDEX
    Explanations

    numerical values indicating age or quantities related to years and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    0
    -0.79
    amp
    -0.78
    5
    -0.71
    2
    -0.70
    1
    -0.69
     onPage
    -0.67
    3
    -0.67
    9
    -0.67
     BoxFit
    -0.62
    6
    -0.60
    POSITIVE LOGITS
     hundred
    0.92
    tieth
    0.81
     thousand
    0.77
    fold
    0.75
      (
    0.70
     rhestr
    0.69
     times
    0.68
    )))));
    0.66
    ))){
    0.64
     dollars
    0.63
    Act Density 0.336%

    No Known Activations