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

    Neuronpedia

    INDEX
    Explanations

    references to products or services in a corporate context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     inev
    -1.79
     unlaw
    -1.70
     desir
    -1.69
     volunte
    -1.69
     fep
    -1.67
     depic
    -1.66
     reluct
    -1.66
     ftu
    -1.64
     accla
    -1.64
     thut
    -1.64
    POSITIVE LOGITS
    .
    0.94
    ;
    0.82
    <bos>
    0.76
    :
    0.75
    。
    0.74
    ,
    0.73
     properly
    0.70
     without
    0.70
    ；
    0.69
    ↵↵
    0.69
    Act Density 0.706%

    No Known Activations