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

    Neuronpedia

    INDEX
    Explanations

    expressions that reflect gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <=",
    -0.60
    WriteBarrier
    -0.51
     gynhyrchwyd
    -0.51
    amse
    -0.51
    OrNil
    -0.49
     Приступљено
    -0.48
     chain
    -0.47
    новништво
    -0.46
     an
    -0.46
    catching
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.71
    參考資料
    0.52
    sitis
    0.52
    ="
    0.52
    complexContent
    0.52
     apologised
    0.51
     desorption
    0.51
     nakalista
    0.49
    ovács
    0.49
    amaño
    0.49
    Act Density 0.092%

    No Known Activations