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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions related to large numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.71
    Personensuche
    -0.70
     Sept
    -0.70
    ing
    -0.68
    Sept
    -0.61
    ς
    -0.59
     midnight
    -0.58
    midnight
    -0.57
    Fig
    -0.57
     Aug
    -0.57
    POSITIVE LOGITS
     seventeenth
    1.49
     seventeen
    1.48
     eighteenth
    1.43
     nineteenth
    1.42
     thirteen
    1.42
     nineteen
    1.41
     sixteen
    1.36
     eighteen
    1.34
     fourteen
    1.30
     seventy
    1.30
    Act Density 0.265%

    No Known Activations