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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quæ
    -0.96
     Diſ
    -0.82
     ſtate
    -0.78
     Majefty
    -0.77
     ſever
    -0.76
     Reſ
    -0.75
     ſta
    -0.74
     Jefus
    -0.72
     Anſ
    -0.72
     miſ
    -0.72
    POSITIVE LOGITS
     appreciation
    0.81
     appreciate
    0.73
     appreci
    0.73
     Appreciate
    0.72
     appreciated
    0.68
     appreciative
    0.66
     apreciar
    0.63
    reciate
    0.62
     cuenta
    0.61
     whatsoever
    0.60
    Act Density 0.116%

    No Known Activations