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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     greatly
    0.38
     guess
    0.38
    嗇
    0.37
     dunk
    0.37
    ;%%
    0.36
     dips
    0.36
     scald
    0.36
     vastly
    0.36
    ⏭
    0.36
     evol
    0.36
    POSITIVE LOGITS
    Cock
    1.11
     Cock
    0.96
     cock
    0.95
    cock
    0.93
     kok
    0.72
     cockpit
    0.70
     Cocker
    0.70
    Kok
    0.68
     кок
    0.68
     cocker
    0.64
    Act Density 0.005%

    No Known Activations