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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    8
    0.54
    ERIC
    0.49
    ken
    0.45
    9
    0.44
    GL
    0.43
    gs
    0.43
    6
    0.43
    esco
    0.42
    end
    0.41
    zeta
    0.41
    POSITIVE LOGITS
     repent
    0.55
     regrett
    0.55
     penit
    0.51
     convid
    0.51
     repudi
    0.49
     trebuie
    0.49
    ᄄ
    0.49
     deus
    0.47
     трябва
    0.47
     totem
    0.46
    Act Density 0.000%

    No Known Activations