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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     transférez
    -0.57
     ſch
    -0.53
    virano
    -0.53
     ſeveral
    -0.53
     houſe
    -0.52
     rilev
    -0.51
     Houſe
    -0.51
     createState
    -0.50
    aarrggbb
    -0.49
     ſever
    -0.49
    POSITIVE LOGITS
     gratitude
    0.82
     Gratitude
    0.72
     grateful
    0.53
     appreciation
    0.52
     thanking
    0.52
     agradecimiento
    0.50
     thanked
    0.50
    thank
    0.49
     thankful
    0.48
     thanksgiving
    0.48
    Act Density 0.010%

    No Known Activations