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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     recons
    -0.73
    pmwiki
    -0.70
    gyn
    -0.67
     salesman
    -0.64
    forth
    -0.64
     depot
    -0.64
     instr
    -0.63
    gap
    -0.63
    senal
    -0.63
    conservancy
    -0.62
    POSITIVE LOGITS
     Piet
    0.72
    isation
    0.71
     Riot
    0.71
    romeda
    0.70
    iets
    0.63
     Batt
    0.63
     Ble
    0.60
    atta
    0.60
     IPM
    0.60
    eenth
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.