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

    Neuronpedia

    INDEX
    Explanations

    phrases related to freedom, liberation, and widening compassion

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oubted
    -0.67
    <bos>
    -0.66
     EconPapers
    -0.59
    ometrial
    -0.55
    asantry
    -0.52
     firebaseConfig
    -0.50
    InstrumentedTest
    -0.50
    DoubleQuotes
    -0.50
     getSource
    -0.49
    oneofs
    -0.49
    POSITIVE LOGITS
    atguigu
    0.68
     Apesar
    0.54
     logis
    0.51
    <?
    0.51
     conforman
    0.50
     pama
    0.50
     katun
    0.49
     Mesmo
    0.49
    Visión
    0.48
    Inoltre
    0.48
    Act Density 0.261%

    No Known Activations