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

    Neuronpedia

    INDEX
    Explanations

    words related to technical issues or problems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vogli
    -0.89
     sappi
    -0.86
     voleva
    -0.80
     ognuno
    -0.77
     felipe
    -0.73
     sergio
    -0.73
     alberto
    -0.71
     roberto
    -0.71
     poteva
    -0.70
     peines
    -0.69
    POSITIVE LOGITS
     queryParams
    0.57
     gaily
    0.56
     Transylvania
    0.56
     nobly
    0.55
     Nobles
    0.54
     Frankfort
    0.54
     Grenville
    0.54
     חיצוניים
    0.53
     Broughton
    0.53
     Whig
    0.53
    Act Density 0.495%

    No Known Activations