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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    */(
    -0.85
    ilts
    -0.68
    Appearances
    -0.68
    ential
    -0.67
     protector
    -0.65
     interven
    -0.64
    atever
    -0.63
     Ajax
    -0.62
    abeth
    -0.62
    ucket
    -0.61
    POSITIVE LOGITS
    liga
    0.90
    perm
    0.66
    igrants
    0.65
    igrate
    0.65
    mand
    0.64
    isconsin
    0.64
    wik
    0.62
    atoon
    0.61
    Wiki
    0.60
    sbm
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.