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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating increases or decreases in numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñģли
    -0.17
    ê¹
    -0.17
     Bale
    -0.14
    quent
    -0.14
    achs
    -0.14
    wyn
    -0.14
    achen
    -0.13
    ysis
    -0.13
    aco
    -0.13
    ADED
    -0.13
    POSITIVE LOGITS
     leaps
    0.23
     double
    0.19
     factors
    0.18
     almost
    0.17
     marginal
    0.17
    -double
    0.17
     âĨĴ↵↵
    0.17
     nearly
    0.15
     tw
    0.15
     percentages
    0.15
    Act Density 0.053%

    No Known Activations