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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistics and data analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.52
    ⓧ
    -0.97
    /***
    -0.97
     endow
    -0.92
    <?
    -0.87
     intersper
    -0.85
    
    -0.78
     rejoin
    -0.78
     aggravate
    -0.73
     endeavoured
    -0.73
    POSITIVE LOGITS
     paradiso
    1.08
     chrysler
    0.99
     tramonto
    0.99
     broderie
    0.98
    pection
    0.98
     pioggia
    0.97
     lamborghini
    0.94
    tionally
    0.92
     eiffel
    0.92
    requently
    0.91
    Act Density 0.372%

    No Known Activations