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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions that indicate frequency or approximation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺìĿ´
    -0.16
    urb
    -0.15
    ây
    -0.15
    intColor
    -0.15
    arp
    -0.14
    edBy
    -0.14
    053
    -0.14
     Macros
    -0.14
    å±ħ
    -0.14
    ê¶Į
    -0.13
    POSITIVE LOGITS
     thousands
    0.21
     half
    0.19
     million
    0.19
     thousand
    0.18
     millions
    0.18
     dozen
    0.17
    0.17
     $
    0.15
     thous
    0.15
     nearly
    0.15
    Act Density 0.055%

    No Known Activations