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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing past experiences and learning from mistakes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Вікі
    -0.49
    Aujourd
    -0.45
     CommonModule
    -0.44
    نیم
    -0.44
     Scienti
    -0.43
    hon
    -0.41
    lgari
    -0.41
    开
    -0.40
     Miele
    -0.40
    废话
    -0.40
    POSITIVE LOGITS
     فريبيس
    0.95
    Autoritní
    0.76
    RenderAtEndOf
    0.68
     future
    0.65
     المعيارى
    0.63
    abestanden
    0.63
    ]")]
    0.63
     Lordships
    0.57
     prossima
    0.56
     linkovi
    0.56
    Act Density 0.138%

    No Known Activations