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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant involvement or roles in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    iy
    -0.52
    yntaxException
    -0.52
    steamcommunity
    -0.51
    </table>
    -0.50
     selera
    -0.49
     sh
    -0.47
    ższy
    -0.47
    дження
    -0.46
     Free
    -0.46
    時
    -0.46
    POSITIVE LOGITS
    StructEnd
    0.85
     виправивши
    0.84
     >=",
    0.81
    IntoConstraints
    0.81
    ftagPool
    0.76
     rôle
    0.75
     ModelExpression
    0.73
     MainAxisSize
    0.73
    expandindo
    0.72
     BoxDecoration
    0.71
    Act Density 0.015%

    No Known Activations