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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ENC
    0.83
    Eng
    0.77
    s
    0.76
    R
    0.76
     ENG
    0.74
    T
    0.73
     Forth
    0.72
    ant
    0.71
    ᴿ
    0.69
    𝙍
    0.69
    POSITIVE LOGITS
    沾
    0.76
     मासिक
    0.73
    цем
    0.73
     staring
    0.72
     doubting
    0.67
     deterred
    0.67
     dopamine
    0.67
    輪
    0.66
     زمان
    0.66
    ቕ
    0.66
    Act Density 0.000%

    No Known Activations