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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating enjoyment or recommendation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     scrimmage
    -0.70
    quickShipAvailable
    -0.70
    ©¶æ
    -0.65
    staff
    -0.63
    Enlarge
    -0.63
    DragonMagazine
    -0.60
    gemony
    -0.59
     promoter
    -0.59
    nexus
    -0.57
    mith
    -0.56
    POSITIVE LOGITS
    ably
    0.94
    ances
    0.84
    nels
    0.81
     enjoyment
    0.80
     watching
    0.78
     Enjoy
    0.76
    anced
    0.74
    ables
    0.74
    orable
    0.74
    joy
    0.74
    Act Density 0.025%

    No Known Activations