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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     instalment
    1.70
     unes
    1.64
    にか
    1.62
     strategist
    1.57
    ………….
    1.54
    ouncement
    1.51
     campaigner
    1.47
     pensioner
    1.47
    จุ
    1.47
     instalments
    1.47
    POSITIVE LOGITS
     Ideally
    3.19
    7
    2.92
    Diffuse
    2.83
    8
    2.79
    Ideally
    2.76
    6
    2.74
     Avoid
    2.70
     lugar
    2.61
     Permits
    2.60
    3
    2.59
    Act Density 2.644%

    No Known Activations