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

    Neuronpedia

    INDEX
    Explanations

    requests and expressions of desire or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    demands, requests, and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MockBean
    -0.40
    AllowAnonymous
    -0.34
    шаем
    -0.33
    égorie
    -0.32
    Trama
    -0.32
     wijk
    -0.31
    ATTR
    -0.31
     prata
    -0.30
     fédé
    -0.30
    amma
    -0.30
    POSITIVE LOGITS
    要求
    0.55
     surla
    0.54
     insisted
    0.54
     demanding
    0.52
     demanded
    0.50
    Chham
    0.50
    autaire
    0.50
     requested
    0.50
    ViewInit
    0.49
     demands
    0.49
    Act Density 0.057%

    No Known Activations