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

    Neuronpedia

    INDEX
    Explanations

    references to humor and comedic elements

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

    humor and wit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.47
     ListTile
    -0.44
     Eagle
    -0.40
     informée
    -0.39
    contentLoaded
    -0.38
     JAXBElement
    -0.37
     Ruta
    -0.37
     thrice
    -0.36
    _;
    -0.35
    ↵
    -0.35
    POSITIVE LOGITS
     humor
    0.81
    humor
    0.77
     Humor
    0.74
    humour
    0.68
     humour
    0.67
    Humor
    0.66
    humidité
    0.62
     paciencia
    0.54
     selera
    0.53
     humeur
    0.52
    Act Density 0.007%

    No Known Activations