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

    Neuronpedia

    INDEX
    Explanations

    percentages and numerical data related to research statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategy
    -0.15
    еÑĢж
    -0.15
    arts
    -0.14
     franca
    -0.14
    iele
    -0.14
    ubat
    -0.14
    ãĤĩ
    -0.14
    Grammar
    -0.14
    andom
    -0.14
    го
    -0.14
    POSITIVE LOGITS
    µ
    0.14
    è©
    0.14
     Starting
    0.14
    æı
    0.14
     nas
    0.13
    rak
    0.13
     è©
    0.13
     twice
    0.13
     punt
    0.13
    ãģķãģĦ
    0.13
    Act Density 0.002%

    No Known Activations