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

    Neuronpedia

    INDEX
    Explanations

    references to the word "unique" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isher
    -0.16
    ÏĥÏĦα
    -0.15
    anas
    -0.15
    istes
    -0.14
    øy
    -0.14
    cher
    -0.14
    wright
    -0.14
    quet
    -0.14
    FTA
    -0.14
    anel
    -0.14
    POSITIVE LOGITS
    ucas
    0.16
     ÑĢаÑģÑĩ
    0.16
    icone
    0.15
     ÄĮer
    0.15
    quipment
    0.15
    ema
    0.14
    otte
    0.14
    obutton
    0.14
    urette
    0.14
    {text
    0.14
    Act Density 0.016%

    No Known Activations