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

    Neuronpedia

    INDEX
    Explanations

    numerical values and codes within a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.74
    anooga
    -0.71
    inery
    -0.70
     compan
    -0.66
     prem
    -0.66
     explanatory
    -0.65
     tragedies
    -0.63
    ifice
    -0.63
     suprem
    -0.63
     tremend
    -0.63
    POSITIVE LOGITS
    .............
    0.97
    608
    0.94
    807
    0.93
    703
    0.91
    504
    0.90
    806
    0.90
    GMT
    0.90
    0100
    0.89
    607
    0.88
    458
    0.88
    Act Density 0.088%

    No Known Activations