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

    Neuronpedia

    INDEX
    Explanations

    references to different types of memberships

    oai_token-act-pair · gpt-3.5-turbo

    references to membership in various organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Verb
    -0.61
     Mane
    -0.61
    apple
    -0.60
     Perse
    -0.59
     Hurricanes
    -0.58
     Oo
    -0.58
     Tiger
    -0.58
     Spo
    -0.57
    rup
    -0.57
     Veh
    -0.57
    POSITIVE LOGITS
     membership
    1.24
     dues
    1.19
     subscriptions
    1.01
     Membership
    0.97
    holder
    0.93
    holders
    0.91
    members
    0.87
    cius
    0.86
    ession
    0.83
     guiActiveUn
    0.82
    Act Density 0.009%

    No Known Activations