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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    chens
    -0.70
    cknow
    -0.69
    anan
    -0.66
    ollah
    -0.65
    chen
    -0.63
    enko
    -0.62
    kamp
    -0.60
     coerc
    -0.60
    rha
    -0.59
    kin
    -0.59
    POSITIVE LOGITS
    ocrates
    0.73
     tides
    0.69
    Availability
    0.68
    ards
    0.67
    ship
    0.66
    ALSE
    0.65
    abl
    0.64
    ARDIS
    0.63
    STR
    0.63
    Quantity
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.