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

    Neuronpedia

    INDEX
    Explanations

    instances of laughter or expressions of amusement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaz
    -0.71
     Carden
    -0.69
    OrEmpty
    -0.68
     Anand
    -0.62
     quel
    -0.62
    浆
    -0.60
    شود
    -0.60
     ung
    -0.59
    styrelsen
    -0.59
     Jacobsen
    -0.58
    POSITIVE LOGITS
    Ha
    2.00
     Ha
    1.91
     ha
    1.87
     HA
    1.65
    ha
    1.64
    HA
    1.54
     haiku
    1.29
     Haver
    1.27
     Hailey
    1.24
    Hahahahaha
    1.21
    Act Density 0.036%

    No Known Activations