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

    Neuronpedia

    INDEX
    Explanations

    customer service-related phrases and expressions of dissatisfaction or expectation

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

    after titles or roles

    np_acts-logits-general · gemini-2.0-flash

    roles and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NgModule
    -0.51
    ulam
    -0.45
    υνα
    -0.44
    ellschaft
    -0.44
    teryx
    -0.44
     thập
    -0.42
    setOpen
    -0.42
    kező
    -0.41
     saa
    -0.41
    xffffffff
    -0.41
    POSITIVE LOGITS
     manager
    0.88
     Manager
    0.87
    complexContent
    0.83
    AddTagHelper
    0.81
     estekak
    0.77
     MANAGER
    0.74
     <=",
    0.73
     الحره
    0.72
     supervisor
    0.71
     managers
    0.70
    Act Density 0.056%

    No Known Activations