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

    Neuronpedia

    INDEX
    Explanations

    comments indicating enjoyment or positive experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to enjoyment and positive experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -1.28
    isSpecialOrderable
    -0.72
     Croat
    -0.69
     coordin
    -0.68
     Cree
    -0.67
    ARE
    -0.63
    Wr
    -0.62
     Herrera
    -0.62
    McC
    -0.61
    channelAvailability
    -0.60
    POSITIVE LOGITS
     leisure
    0.86
     pleasures
    0.83
     newfound
    0.81
    noon
    0.79
     solitude
    0.78
     anonymity
    0.78
     enjoyment
    0.76
     privileges
    0.76
     downtime
    0.74
     fruits
    0.71
    Act Density 0.139%

    No Known Activations