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

    Neuronpedia

    INDEX
    Explanations

    phrases involving numbers and quantities related to people, events, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Certain
    -0.18
     некоÑĤоÑĢÑĭÑħ
    -0.17
    tem
    -0.16
    Certain
    -0.16
    izik
    -0.15
    eton
    -0.15
    culus
    -0.15
    soever
    -0.15
    rick
    -0.14
    ochen
    -0.14
    POSITIVE LOGITS
     acres
    0.28
     thousands
    0.24
     miles
    0.24
     pages
    0.22
     dollars
    0.22
     gallons
    0.21
     them
    0.21
     others
    0.21
     hectares
    0.21
     tons
    0.20
    Act Density 0.049%

    No Known Activations