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

    Neuronpedia

    INDEX
    Explanations

    expressions of pleasure and enjoyment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.54
    Autoritní
    -0.53
     dévelo
    -0.52
     vectorielle
    -0.51
    tvguidetime
    -0.50
     leyenda
    -0.50
     vectorielles
    -0.50
     nahilalakip
    -0.49
    tidaknya
    -0.49
     protoimpl
    -0.49
    POSITIVE LOGITS
     pleasure
    1.16
     Pleasure
    1.05
     joy
    1.05
     pleasures
    1.02
    pleasure
    0.97
     delight
    0.96
     enjoyment
    0.96
     plaisir
    0.93
     joys
    0.93
     delights
    0.84
    Act Density 0.321%

    No Known Activations