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

    Neuronpedia

    INDEX
    Explanations

    expressions related to commentary and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     perfección
    -0.57
     superiori
    -0.50
     kerja
    -0.49
     vinto
    -0.49
    拔
    -0.48
     daire
    -0.47
     Kerja
    -0.46
     ordini
    -0.46
    рованы
    -0.46
     consegna
    -0.46
    POSITIVE LOGITS
     remarks
    1.06
     comments
    1.05
     commentary
    1.02
     COMMENTS
    0.89
    comments
    0.88
     opinions
    0.85
     thoughts
    0.85
     Comments
    0.85
    remarks
    0.84
     reflections
    0.84
    Act Density 0.054%

    No Known Activations