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

    Neuronpedia

    INDEX
    Explanations

    expressions of friendliness and politeness in communication

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

    associated with friendliness or kindness

    np_acts-logits-general · gemini-2.0-flash

    friendly demeanor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.62
    UnsafeEnabled
    -0.61
     VIAF
    -0.58
     NSCoder
    -0.57
    +#+#
    -0.55
    ⓧ
    -0.54
     posiblemente
    -0.52
     Legit
    -0.51
    jboss
    -0.51
    /*---
    -0.51
    POSITIVE LOGITS
    kindness
    0.69
     warm
    0.65
     friendly
    0.62
     Reminder
    0.62
     gentler
    0.62
     kindly
    0.61
     reminder
    0.59
    reminder
    0.58
     condescending
    0.58
     warmed
    0.57
    Act Density 0.169%

    No Known Activations