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

    Neuronpedia

    INDEX
    Explanations

    terms related to exchanges or mutual benefits between different entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     emphat
    -0.94
     effe
    -0.92
     ftu
    -0.90
     suspic
    -0.87
     desir
    -0.87
     fup
    -0.86
     inconce
    -0.85
     peculi
    -0.84
     fays
    -0.83
     fatis
    -0.83
    POSITIVE LOGITS
    <bos>
    0.80
     cser
    0.54
     desertcart
    0.51
    AndEndTag
    0.50
     Italijani
    0.48
     promise
    0.47
    ற்
    0.45
    ьаж
    0.45
    DeleteBehavior
    0.45
     reward
    0.45
    Act Density 0.106%

    No Known Activations