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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     destined
    0.53
    rom
    0.52
    ig
    0.51
    ase
    0.50
     Er
    0.50
     appar
    0.49
     fell
    0.48
     reminisc
    0.46
     profess
    0.46
     men
    0.46
    POSITIVE LOGITS
    ﻢ
    0.50
    ﻜ
    0.48
    юсь
    0.46
    OTT
    0.45
    Consistency
    0.45
    торе
    0.44
    রাজ
    0.44
     Дан
    0.43
    ECTOR
    0.42
     Luật
    0.42
    Act Density 0.000%

    No Known Activations