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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinions or feelings by individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotions, sentiments, and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helicop
    -0.73
    oby
    -0.70
    cade
    -0.70
    batch
    -0.70
    bsite
    -0.68
     prominently
    -0.67
    oldown
    -0.66
     Produ
    -0.66
     Wrest
    -0.66
    uters
    -0.66
    POSITIVE LOGITS
     desire
    1.73
     belief
    1.70
     admiration
    1.67
     dislike
    1.60
     feelings
    1.51
     displeasure
    1.50
     dissatisfaction
    1.49
     hatred
    1.49
     resentment
    1.48
     frustration
    1.43
    Act Density 0.524%

    No Known Activations