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
     quelcon
    -0.75
     dévelo
    -0.74
    DockStyle
    -0.73
     découver
    -0.68
    Hauptartikel
    -0.65
     démocr
    -0.65
     définiti
    -0.64
     normaux
    -0.64
     célè
    -0.64
     réfugi
    -0.63
    POSITIVE LOGITS
     il
    0.76
    Il
    0.70
    Ce
    0.70
     Il
    0.70
     Ce
    0.67
    cela
    0.64
     ce
    0.64
     Ces
    0.64
     Cela
    0.62
    Ceci
    0.62
    Act Density 0.095%

    No Known Activations