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
     Efq
    -0.86
    geslacht
    -0.75
     houſe
    -0.73
     myſelf
    -0.73
     Monfieur
    -0.73
    endphp
    -0.69
     Majefty
    -0.68
     שוליים
    -0.68
    ſelf
    -0.68
    irage
    -0.66
    POSITIVE LOGITS
     thankful
    0.93
     gratitude
    0.90
     grateful
    0.90
     Gratitude
    0.84
     dankbar
    0.83
     gratefully
    0.75
     thanksgiving
    0.71
     thanking
    0.70
     agradec
    0.69
     agrade
    0.66
    Act Density 0.114%

    No Known Activations