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

    Neuronpedia

    INDEX
    Explanations

    instances where the document instructs or suggests sending an email to a friend

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    wagen
    -0.64
    tions
    -0.64
    cipline
    -0.62
    vernment
    -0.62
    gew
    -0.61
    autical
    -0.60
    jriwal
    -0.60
    rency
    -0.60
    ibilities
    -0.60
    uthor
    -0.59
    POSITIVE LOGITS
     subscribers
    0.78
     recipients
    0.77
    friends
    0.73
     inbox
    0.70
     readers
    0.67
     reader
    0.65
    users
    0.64
     recipient
    0.62
     friends
    0.62
     relevant
    0.62
    Act Density 0.089%

    No Known Activations