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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     commissioners
    -0.07
    Bus
    -0.06
     BF
    -0.06
    CB
    -0.06
    venile
    -0.06
     حوزه
    -0.06
     discourage
    -0.06
    烟
    -0.06
     Bus
    -0.06
     siguientes
    -0.06
    POSITIVE LOGITS
    력
    0.07
     harek
    0.07
    .close
    0.07
     annoyed
    0.06
    pmat
    0.06
    ails
    0.06
     Driver
    0.06
     Digest
    0.06
    αν
    0.06
     surv
    0.06
    Act Density 0.015%

    No Known Activations