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

    Neuronpedia

    INDEX
    Explanations

    references to specific figures in scientific documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    l
    -0.67
    Datuak
    -0.65
    <code>
    -0.62
    rd
    -0.61
     An
    -0.58
     Il
    -0.57
    on
    -0.56
     A
    -0.56
    <h2>
    -0.55
    <i>
    -0.55
    POSITIVE LOGITS
    ConstraintMaker
    0.83
    TypedDataSet
    0.81
    ArrowToggle
    0.78
     <=",
    0.78
    ."],
    0.76
    audiovisuel
    0.75
    .)}
    0.75
    ]";
    0.75
     unknownFields
    0.75
    )";
    0.75
    Act Density 0.012%

    No Known Activations