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

    Neuronpedia

    INDEX
    Explanations

    mentions of celebrations or well wishes

    oai_token-act-pair · gpt-3.5-turbo

    the word "Happy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arin
    -0.79
    rovers
    -0.72
    ij
    -0.72
    IDER
    -0.72
    uing
    -0.71
    ickr
    -0.68
    urally
    -0.68
    aeda
    -0.68
    urer
    -0.68
    enses
    -0.67
    POSITIVE LOGITS
    ness
    0.90
     Birthday
    0.86
     birthday
    0.81
     Gilmore
    0.80
     Happy
    0.79
    joy
    0.78
    Happy
    0.76
     Meal
    0.76
    bies
    0.72
     happy
    0.69
    Act Density 0.023%

    No Known Activations