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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efer
    -0.65
    gart
    -0.61
    chart
    -0.61
    wav
    -0.60
    ĨĴ
    -0.59
    Dest
    -0.58
    conserv
    -0.58
    ãĥĥãĥī
    -0.58
    ingu
    -0.58
     displ
    -0.57
    POSITIVE LOGITS
     kindly
    1.02
     sir
    0.93
     welcome
    0.85
     guys
    0.82
    giving
    0.79
     gracious
    0.78
     gentlemen
    0.69
    ा
    0.69
     congratulations
    0.68
     diligence
    0.67
    Act Density 0.030%

    No Known Activations