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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    👉
    0.59
    Honestly
    0.54
    💎
    0.54
    koliko
    0.53
    Definitely
    0.53
    f
    0.53
    Plaintiff
    0.52
    ństwo
    0.51
    Probably
    0.50
    fuck
    0.49
    POSITIVE LOGITS
    喃
    0.59
    ようになる
    0.59
    ד
    0.58
    র
    0.56
    री
    0.54
     hostilities
    0.54
    ir
    0.54
    諫
    0.53
     coincident
    0.53
    ęp
    0.52
    Act Density 0.188%

    No Known Activations