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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "toll" or tolling-related terminology

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    konomi
    -0.71
    hloromethane
    -0.69
     verksamhet
    -0.68
     vegeta
    -0.66
    queline
    -0.66
    phorbia
    -0.65
     McNamara
    -0.64
    myapplication
    -0.63
    Bibliografía
    -0.61
    lectricité
    -0.61
    POSITIVE LOGITS
     Toll
    2.02
     toll
    1.81
    Toll
    1.77
     tolls
    1.60
    toll
    1.47
     tol
    1.11
     Tol
    1.04
    Tol
    0.97
    tol
    0.91
     TOL
    0.90
    Act Density 0.005%

    No Known Activations