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

    Neuronpedia

    INDEX
    Explanations

    terms related to service roles and provisions

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

    concierge and service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.42
     păr
    -0.40
     vernie
    -0.39
     widerrufen
    -0.39
    heça
    -0.38
    ũng
    -0.38
    lihatkan
    -0.38
    cionais
    -0.37
     weirdly
    -0.37
     zwaar
    -0.37
    POSITIVE LOGITS
    cierge
    0.89
     concierge
    0.87
     concier
    0.71
     ſta
    0.60
    ActionCreators
    0.57
     ſch
    0.54
     service
    0.53
     noDo
    0.52
    TagMode
    0.51
    AddHtmlAttribute
    0.51
    Act Density 0.004%

    No Known Activations