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

    Neuronpedia

    INDEX
    Explanations

    words related to happiness and unhappiness

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to happiness and emotional well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sk
    -0.78
    Ry
    -0.72
    heit
    -0.72
    books
    -0.71
    Vs
    -0.70
    UAL
    -0.67
    adr
    -0.66
    Maps
    -0.65
    armor
    -0.65
    DoS
    -0.65
    POSITIVE LOGITS
     happier
    0.98
     happiest
    0.87
     happy
    0.82
     unhappy
    0.81
     adolesc
    0.80
    ishers
    0.73
     mosqu
    0.73
    iated
    0.72
     experien
    0.71
    iliate
    0.71
    Act Density 0.008%

    No Known Activations