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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -exc
    -0.06
     blinded
    -0.06
     Jerseys
    -0.06
     Liberals
    -0.06
     pointing
    -0.06
     ESL
    -0.06
     tls
    -0.06
     acceler
    -0.06
     bank
    -0.06
    ileceği
    -0.06
    POSITIVE LOGITS
    قلال
    0.07
    ést
    0.07
    INE
    0.06
    .Promise
    0.06
    ERA
    0.06
     θε
    0.06
    medi
    0.06
    ambre
    0.06
    その他
    0.06
     Україн
    0.06
    Act Density 0.006%

    No Known Activations