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

    Neuronpedia

    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.21
    ⓧ
    -1.14
    /**
    -1.07
    
    -0.97
    /***
    -0.92
    <?
    -0.87
     springfox
    -0.86
    <?
    -0.83
     gratify
    -0.82
    /*
    -0.81
    POSITIVE LOGITS
     véhic
    0.82
     bandung
    0.79
     déliv
    0.76
     semblables
    0.71
     TextFormField
    0.71
     churrasco
    0.70
     asado
    0.70
     nutella
    0.70
     [''
    0.69
     padang
    0.69
    Act Density 0.128%

    No Known Activations