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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "other."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ")));
    -0.74
     <>",
    -0.68
    MigrationBuilder
    -0.65
     alternative
    -0.65
     ),
    -0.65
    )}</
    -0.63
     other
    -0.62
     jLabel
    -0.62
    ]').
    -0.62
    %")
    -0.61
    POSITIVE LOGITS
     themselves
    0.65
     yourself
    0.65
    Autoritní
    0.60
     himself
    0.59
     herself
    0.58
     Himself
    0.57
    même
    0.55
     judiciaire
    0.55
     lamella
    0.55
     Yourself
    0.54
    Act Density 0.027%

    No Known Activations