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

    Neuronpedia

    INDEX
    Explanations

    terms related to indulgence and self-care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baiki
    -0.61
     salv
    -0.56
    Demografia
    -0.52
    ])):
    -0.52
    sober
    -0.52
    sleeve
    -0.51
     intptr
    -0.51
    ménage
    -0.50
     vastaan
    -0.49
    operatives
    -0.49
    POSITIVE LOGITS
     indulgence
    1.24
     indulged
    1.23
     indulge
    1.21
     Indul
    1.17
     indulging
    1.13
     indulgent
    1.10
     indul
    1.01
    indul
    0.96
     cravings
    0.80
     fantasies
    0.76
    Act Density 0.216%

    No Known Activations