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
     asisti
    -0.34
     mág
    -0.33
     presentación
    -0.28
     Begleitung
    -0.28
     huelga
    -0.28
    แห่ง
    -0.27
     huella
    -0.27
     stør
    -0.27
     inclusión
    -0.27
    hadiran
    -0.26
    POSITIVE LOGITS
     autorytatywna
    0.90
     يتيمه
    0.84
    Personensuche
    0.82
    <unused14>
    0.76
    <unused43>
    0.75
    <unused41>
    0.75
    <unused52>
    0.75
    <unused74>
    0.75
    [@BOS@]
    0.75
    <unused23>
    0.75
    Act Density 0.001%

    No Known Activations