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

    Neuronpedia

    INDEX
    Explanations

    expressions of joy and happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.70
     Hombre
    -0.68
     bada
    -0.63
     Pennington
    -0.62
     Martens
    -0.62
    __":
    -0.62
    ranslated
    -0.61
    Kanpo
    -0.60
     Samuels
    -0.60
    findpost
    -0.60
    POSITIVE LOGITS
     joy
    3.42
     Joy
    2.88
    joy
    2.79
     JOY
    2.79
    Joy
    2.76
     joys
    2.43
    JOY
    2.29
    joys
    1.90
     joyful
    1.83
     gioia
    1.75
    Act Density 0.039%

    No Known Activations