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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    heit
    -0.79
    ablishment
    -0.75
    english
    -0.73
     KH
    -0.73
     reconc
    -0.72
    heter
    -0.67
    20439
    -0.67
    htaking
    -0.66
    iru
    -0.65
    BOOK
    -0.65
    POSITIVE LOGITS
     cac
    0.66
    ONSORED
    0.64
     calib
    0.63
     possession
    0.62
     Flore
    0.60
     nails
    0.60
     mentors
    0.59
     perman
    0.59
     Guer
    0.59
    guards
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.