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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ∇
    -0.07
     sû
    -0.07
     plead
    -0.07
    談
    -0.06
    osemite
    -0.06
     Right
    -0.06
    alles
    -0.06
     acknowledging
    -0.06
     pratic
    -0.06
    뺃
    -0.06
    POSITIVE LOGITS
    opause
    0.08
    rollo
    0.07
    汚れ
    0.07
    مون
    0.07
     moo
    0.07
    бой
    0.07
    high
    0.07
    imals
    0.07
    кая
    0.07
    directory
    0.07
    Act Density 0.032%

    No Known Activations