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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    auts
    -0.66
    orters
    -0.65
     "{
    -0.65
    士
    -0.62
    osponsors
    -0.61
     Chef
    -0.61
     MSM
    -0.60
     Marcos
    -0.60
    assadors
    -0.59
    enses
    -0.59
    POSITIVE LOGITS
    hower
    0.85
    Reviewer
    0.72
    nis
    0.70
    orce
    0.68
    ebus
    0.67
    HCR
    0.66
    zsche
    0.65
    lam
    0.64
    vg
    0.64
    =]
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.