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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     neighbors
    -0.17
     neighbor
    -0.15
     theater
    -0.15
    eselect
    -0.15
     offense
    -0.15
     colorful
    -0.15
    ighbor
    -0.15
    umberland
    -0.14
    FG
    -0.14
    åķª
    -0.14
    POSITIVE LOGITS
    --↵
    0.20
     Miss
    0.18
    --
    0.18
    ----
    0.17
     conf
    0.15
    ----↵
    0.15
     Conrad
    0.15
    --;
    0.15
     Nat
    0.15
     flavour
    0.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.