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

    Neuronpedia

    INDEX
    Explanations

    color names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.00
    
    -0.67
    /**
    -0.56
    desertcart
    -0.54
     seem
    -0.54
    州市
    -0.54
    在一
    -0.54
    러한
    -0.52
    ляє
    -0.52
     carried
    -0.51
    POSITIVE LOGITS
     franz
    1.36
     bloss
    1.35
     blos
    1.32
     ordina
    1.31
     dora
    1.31
     haup
    1.30
     bordeaux
    1.30
     nutr
    1.27
     ciga
    1.26
     meis
    1.25
    Act Density 0.313%

    No Known Activations