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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "thing" or "things" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     againſt
    -0.99
    structor
    -0.97
     Monfieur
    -0.95
     itſelf
    -0.94
     leſs
    -0.92
     myſelf
    -0.90
     muſt
    -0.90
     Eſ
    -0.90
     uſ
    -0.89
    therosclerosis
    -0.88
    POSITIVE LOGITS
     Thing
    1.01
     thing
    0.88
     THING
    0.88
     things
    0.86
     THINGS
    0.84
    Thing
    0.84
    Things
    0.82
     Things
    0.80
     Dinge
    0.80
    i
    0.77
    Act Density 0.040%

    No Known Activations