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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing positive feelings or sentiments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ume
    -0.69
     improperly
    -0.68
    omy
    -0.65
     inappropriately
    -0.65
    uyomi
    -0.65
    Downloadha
    -0.65
     detrimental
    -0.64
     unworthy
    -0.63
    bands
    -0.62
    cessive
    -0.62
    POSITIVE LOGITS
     comrade
    0.79
    Congratulations
    0.78
     congr
    0.77
     reassured
    0.75
     Announce
    0.73
     tid
    0.71
     finally
    0.70
     luck
    0.70
    noon
    0.70
    reen
    0.68
    Act Density 0.262%

    No Known Activations