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

    Neuronpedia

    INDEX
    Explanations

    instances of laughter and amusement

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

    states or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ([
    -0.54
    ()][
    -0.51
    Fuck
    -0.48
     nuke
    -0.47
    chränk
    -0.46
    Sink
    -0.45
     Houſe
    -0.45
    Philipp
    -0.44
    FUCK
    -0.43
    fuck
    -0.43
    POSITIVE LOGITS
     laughter
    1.62
    Laughter
    1.38
     Laughter
    1.38
    laughter
    1.22
    LAUGHTER
    0.81
    UGHTER
    0.72
     applause
    0.70
    Applause
    0.66
     betweenstory
    0.65
     tertawa
    0.64
    Act Density 0.002%

    No Known Activations