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

    Neuronpedia

    INDEX
    Explanations

    phrases related to membership cards and associations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     poetic
    -0.69
    enegger
    -0.66
     Siem
    -0.65
     Pharaoh
    -0.63
     curv
    -0.62
     Irma
    -0.61
    borgh
    -0.59
     earthqu
    -0.59
     DF
    -0.59
     maternal
    -0.59
    POSITIVE LOGITS
     dues
    1.31
     membership
    1.05
    hips
    1.01
     Membership
    0.95
     subscriptions
    0.93
    holder
    0.92
    holders
    0.91
     holders
    0.88
    cius
    0.83
    member
    0.82
    Act Density 0.023%

    No Known Activations