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

    Neuronpedia

    INDEX
    Explanations

    informal expressions and conversational markers

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

    humorous interjections and expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.42
    AsUp
    -0.41
    WithIOException
    -0.41
    +#+#
    -0.40
    verwijspagina
    -0.38
    Sinopsis
    -0.38
     clam
    -0.38
    endcsname
    -0.37
    rrggbb
    -0.37
    spesies
    -0.36
    POSITIVE LOGITS
     laugh
    0.70
     laughed
    0.69
     joked
    0.65
     jokes
    0.65
     joke
    0.63
     laughable
    0.63
     laughing
    0.63
     joking
    0.62
     funny
    0.62
     jokingly
    0.60
    Act Density 0.050%

    No Known Activations