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

    Neuronpedia

    INDEX
    Explanations

    phrases surrounded by quotation marks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.69
    ⓧ
    -1.13
    
    -1.01
    <?
    -0.99
    /**
    -0.93
     дописавши
    -0.80
    /*
    -0.77
    /***
    -0.72
     springfox
    -0.70
    ohist
    -0.69
    POSITIVE LOGITS
     unlaw
    1.21
     impractica
    1.20
     Jambi
    1.12
     sovere
    1.12
     santiago
    1.11
     valencia
    1.10
    dison
    1.10
     practition
    1.09
     Portugu
    1.08
     Juf
    1.08
    Act Density 0.311%

    No Known Activations