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

    Neuronpedia

    INDEX
    Explanations

    instances of humor or laughter in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascar
    -0.15
    erus
    -0.15
    ivre
    -0.14
    еÑĦ
    -0.14
    ÙĦÙĥ
    -0.14
    说è¯Ŀ
    -0.13
    iado
    -0.13
    posable
    -0.13
     letra
    -0.13
    ãģ£ãģ
    -0.13
    POSITIVE LOGITS
     pause
    0.37
    pause
    0.32
     Pause
    0.30
    Pause
    0.29
    _pause
    0.24
     pa
    0.24
    .pause
    0.24
     paused
    0.23
     pauses
    0.23
    _PAUSE
    0.21
    Act Density 0.099%

    No Known Activations