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

    Neuronpedia

    INDEX
    Explanations

    language that indicates action, promising favors, and evoking politeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lesh
    -0.15
    acier
    -0.15
    iership
    -0.15
    ulous
    -0.15
    eing
    -0.15
     rewritten
    -0.14
    enser
    -0.14
    à¸±à¸Ľ
    -0.14
     preferably
    -0.13
    øy
    -0.13
    POSITIVE LOGITS
    ï¼ĮæĬĬ
    0.19
     indem
    0.18
    ypad
    0.16
    ãģĭãģ®
    0.16
    arak
    0.15
    ä¼¼çļĦ
    0.15
    ï¼Įå°Ĩ
    0.15
    erial
    0.15
     بأÙĨ
    0.15
    алÑĸз
    0.14
    Act Density 0.253%

    No Known Activations