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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     spoilers
    -0.72
     WATCHED
    -0.69
    DAQ
    -0.68
    IES
    -0.67
    aire
    -0.66
     Consent
    -0.65
    ORS
    -0.65
    BIT
    -0.63
    ARS
    -0.63
    BER
    -0.63
    POSITIVE LOGITS
    iate
    0.73
    lift
    0.71
    illes
    0.70
    nesday
    0.69
    ascus
    0.69
     Lazarus
    0.65
    getic
    0.63
     Yel
    0.62
    lasting
    0.61
    eln
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.