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

    Neuronpedia

    INDEX
    Explanations

    financial data and measurements related to physical attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hundred
    -1.04
     HUND
    -1.03
     Hundred
    -1.02
    hundred
    -1.02
     hundred
    -1.02
    hundreds
    -1.02
     Hundreds
    -0.96
     hundreds
    -0.95
    Hundreds
    -0.94
    三百
    -0.81
    POSITIVE LOGITS
     ten
    0.97
     eight
    0.84
     nine
    0.78
     seven
    0.78
    ten
    0.71
     eleven
    0.71
     zehn
    0.70
     twelve
    0.69
     zwölf
    0.66
     fourteen
    0.65
    Act Density 1.139%

    No Known Activations