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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    est
    0.77
    ه
    0.68
    δος
    0.68
    o
    0.66
    ached
    0.64
     aj
    0.64
    ясь
    0.58
    ao
    0.58
    sp
    0.57
    цев
    0.57
    POSITIVE LOGITS
    ти
    1.12
     perpetuated
    0.82
     isotherms
    0.81
    Shortly
    0.80
     endow
    0.76
     sexuality
    0.76
     penchant
    0.76
    高級
    0.75
    ম্বা
    0.75
    長時間
    0.75
    Act Density 0.015%

    No Known Activations