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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    il
    0.57
    те
    0.55
    ’.
    0.55
    ’:
    0.52
    at
    0.48
    ’?
    0.48
    あるいは
    0.46
    āj
    0.46
    ’
    0.46
    または
    0.46
    POSITIVE LOGITS
     Corporations
    0.55
    Kappa
    0.53
     Legit
    0.51
     Integrative
    0.48
    Voting
    0.48
     Fokus
    0.47
    socks
    0.47
     Structure
    0.47
     Ansatz
    0.47
    ࿐
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.