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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    EMENT
    -0.76
    èª
    -0.73
    ment
    -0.68
    天
    -0.65
    inav
    -0.65
    uggest
    -0.65
    ments
    -0.64
     stupidity
    -0.62
    åĬ
    -0.61
    isms
    -0.61
    POSITIVE LOGITS
    jri
    0.72
    stairs
    0.69
     Flo
    0.69
     Rollins
    0.66
     Carbuncle
    0.66
    tip
    0.66
    vere
    0.66
     dexter
    0.65
     helicop
    0.65
     IMAGES
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.