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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making processes and voting procedures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     indestru
    -0.73
     pamph
    -0.62
     unwarran
    -0.62
     depic
    -0.60
     liberality
    -0.60
     encomp
    -0.59
     unlaw
    -0.59
     sophistic
    -0.58
     unspeak
    -0.58
     Unto
    -0.58
    POSITIVE LOGITS
     votes
    0.68
     toscana
    0.66
     Hür
    0.66
     minimalis
    0.62
     infrastruktur
    0.62
     silikon
    0.61
     karet
    0.61
     kug
    0.60
     demokra
    0.60
     vote
    0.60
    Act Density 0.271%

    No Known Activations