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

    Neuronpedia

    INDEX
    Explanations

    terms related to canonical transformations in mathematical or theoretical contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Houſe
    -0.91
     Diſ
    -0.82
    noinspection
    -0.80
    Хьажоргаш
    -0.74
    providedIn
    -0.74
    ſelf
    -0.73
     ſever
    -0.73
    Viited
    -0.72
     Conſ
    -0.71
     Inſ
    -0.71
    POSITIVE LOGITS
    canonical
    1.46
    Canonical
    1.42
     Canon
    1.34
    Canon
    1.31
     Canonical
    1.28
     canonical
    1.20
    canon
    1.15
     canon
    1.14
     canons
    0.99
     cannon
    0.94
    Act Density 0.011%

    No Known Activations