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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government policies and decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nicolas
    -0.74
     roberto
    -0.74
     ricardo
    -0.74
     purcha
    -0.70
     aen
    -0.69
     jorge
    -0.69
     eduardo
    -0.69
     alberto
    -0.68
     discogs
    -0.67
     sergio
    -0.67
    POSITIVE LOGITS
     unless
    0.75
     until
    0.74
    unless
    0.72
    until
    0.69
     except
    0.63
    except
    0.62
    RTLR
    0.60
    逅
    0.56
    putAll
    0.55
    Until
    0.54
    Act Density 0.445%

    No Known Activations