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

    Neuronpedia

    INDEX
    Explanations

    references to columns in data structures or tables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Socorro
    -0.92
     Colla
    -0.85
    colla
    -0.84
    col
    -0.80
     Chel
    -0.74
     COLL
    -0.73
     Colo
    -0.71
    ,$_
    -0.71
     Koll
    -0.70
     colli
    -0.70
    POSITIVE LOGITS
     Column
    0.82
     Andersen
    0.78
     Zorn
    0.77
    Hansen
    0.76
    bonucle
    0.75
     Hansen
    0.75
    0.74
    xq
    0.73
     Varela
    0.73
    uncu
    0.73
    Act Density 0.008%

    No Known Activations