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

    Neuronpedia

    INDEX
    Explanations

    mentions of pre-orders and purchasing products

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    yah
    -0.67
    nel
    -0.66
    plom
    -0.65
    iferation
    -0.63
    lia
    -0.63
     Cosponsors
    -0.62
    abet
    -0.61
     pressures
    -0.61
     theoret
    -0.60
    ilic
    -0.60
    POSITIVE LOGITS
     tickets
    0.90
     discounted
    0.89
     DVDs
    0.88
     premium
    0.88
     refunds
    0.86
     Premium
    0.86
     CDs
    0.85
     unlimited
    0.83
     extras
    0.82
     DRM
    0.82
    Act Density 0.482%

    No Known Activations