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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ylated
    0.82
    rencies
    0.77
     metavar
    0.69
    cess
    0.68
    de
    0.66
    piano
    0.66
    علم
    0.65
    vidia
    0.65
    말로
    0.65
    kita
    0.64
    POSITIVE LOGITS
    Л
    0.83
    л
    0.81
     trolling
    0.80
    на
    0.74
    Σ
    0.73
     quarrels
    0.72
    یثیت
    0.71
    নারায়ণ
    0.70
     mediation
    0.69
     verwend
    0.68
    Act Density 0.005%

    No Known Activations