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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing gratitude or appreciation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that denote strong emotions or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plaus
    -0.80
     predec
    -0.74
     attrition
    -0.73
    ensibly
    -0.73
     casualty
    -0.73
    iosyncr
    -0.72
     insurgency
    -0.72
     precip
    -0.72
     evade
    -0.72
     defe
    -0.71
    POSITIVE LOGITS
     Thank
    1.81
     THANK
    1.62
     Thanks
    1.52
     Congratulations
    1.52
    Thank
    1.48
     Truly
    1.35
     Hopefully
    1.34
     Especially
    1.30
     Lastly
    1.26
     Highly
    1.25
    Act Density 0.339%

    No Known Activations