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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power or empowerment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.93
    /***
    -0.83
    
    -0.75
    /*!
    -0.74
    <?
    -0.69
    //---
    -0.63
    Vegeu
    -0.62
    /*
    -0.61
    #![
    -0.60
    //~
    -0.59
    POSITIVE LOGITS
     bandung
    1.31
     napoli
    1.25
     chèvre
    1.24
     jaya
    1.23
     frambo
    1.20
     swarovski
    1.18
     broderie
    1.17
     frankfurt
    1.17
     ecru
    1.17
     milano
    1.16
    Act Density 0.118%

    No Known Activations