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

    Neuronpedia

    INDEX
    Explanations

    numerical amounts associated with various statistics or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numbers and statistics related to quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jo
    -0.64
     bedrock
    -0.61
     matt
    -0.60
    lication
    -0.60
    =/
    -0.59
    ACTED
    -0.57
    ↵Âł
    -0.55
     Duo
    -0.55
    ESA
    -0.55
     Deng
    -0.54
    POSITIVE LOGITS
    dozen
    1.08
    ousand
    1.02
    yip
    0.95
     dozen
    0.89
    undred
    0.88
     lakh
    0.87
    illion
    0.80
     thousands
    0.79
    illions
    0.75
    undreds
    0.75
    Act Density 0.189%

    No Known Activations