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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Served
    0.50
     scenarios
    0.46
     stoichiometric
    0.45
     friction
    0.44
     сцена
    0.44
     War
    0.44
     wrong
    0.44
     அவ
    0.44
     Conditions
    0.44
     dwellings
    0.43
    POSITIVE LOGITS
    rs
    0.50
    어
    0.50
    pergillus
    0.50
    rd
    0.49
    glightbox
    0.48
    бло
    0.48
    र
    0.48
    rb
    0.48
    س
    0.47
    سٹم
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.