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

    Neuronpedia

    INDEX
    Explanations

    expressions and references related to laughter and humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.51
    setopt
    -0.51
     Gore
    -0.50
     Pledge
    -0.50
     hvilken
    -0.48
     Ezra
    -0.48
     pledge
    -0.47
     colspan
    -0.47
    นู
    -0.46
    isissez
    -0.46
    POSITIVE LOGITS
     laugh
    1.71
     laughter
    1.64
     laughing
    1.57
     Laughter
    1.55
     laughs
    1.50
     Laughing
    1.45
     Laugh
    1.44
     laughed
    1.42
    Laughing
    1.34
    laughing
    1.29
    Act Density 0.100%

    No Known Activations