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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to emotional states (especially happiness and unhappiness)

    oai_token-act-pair · gpt-3.5-turbo

    references to happiness and contentment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciplinary
    -0.75
    DoS
    -0.75
    ngth
    -0.74
    soDeliveryDate
    -0.71
    sites
    -0.70
    Downloadha
    -0.70
    atum
    -0.67
    Ranked
    -0.67
    heat
    -0.67
    interstitial
    -0.66
    POSITIVE LOGITS
    joy
    0.87
    vale
    0.81
     birthday
    0.79
     happy
    0.75
    istic
    0.73
     happily
    0.68
     Meal
    0.64
    omas
    0.63
     endings
    0.62
     âĶľ
    0.62
    Act Density 0.021%

    No Known Activations