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

    Neuronpedia

    INDEX
    Explanations

    phrases that express various forms of capability or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seau
    -0.18
    adr
    -0.15
    bond
    -0.15
    uttle
    -0.14
    AdapterFactory
    -0.14
    utex
    -0.14
    bots
    -0.14
    ια
    -0.14
    568
    -0.14
    alt
    -0.14
    POSITIVE LOGITS
    egasus
    0.17
    Fc
    0.17
    Č↵
    0.15
     humili
    0.14
    __.__
    0.14
    iley
    0.14
    xDB
    0.14
    ColumnsMode
    0.14
    eller
    0.14
    æIJŃ
    0.13
    Act Density 0.149%

    No Known Activations