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

    Neuronpedia

    INDEX
    Explanations

    themes related to humor in storytelling and characterization

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

    humor and comedy

    np_acts-logits-general · gemini-2.0-flash

    darkly humorous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.95
    Personendaten
    -0.85
    StoryboardSegue
    -0.82
    OwnProperty
    -0.76
    ंदीखरीदारी
    -0.73
     SwitchCompat
    -0.72
    ArrowToggle
    -0.72
    IUrlHelper
    -0.71
    ResponseWriter
    -0.69
    قایناق‌لار
    -0.69
    POSITIVE LOGITS
     hilarious
    0.94
     wacky
    0.77
     hilar
    0.75
     ridiculous
    0.72
     parody
    0.71
     silly
    0.69
     hil
    0.69
     comical
    0.68
     hapless
    0.64
     absurd
    0.62
    Act Density 0.356%

    No Known Activations