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

    Neuronpedia

    INDEX
    Explanations

    references to general objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.05
    ChildScrollView
    -0.99
     uſe
    -0.99
     myſelf
    -0.97
     juſ
    -0.96
     fevere
    -0.96
     juſt
    -0.95
     againſt
    -0.94
     ſever
    -0.94
     themſelves
    -0.93
    POSITIVE LOGITS
     things
    1.89
     thing
    1.82
     Thing
    1.69
    Things
    1.68
     THINGS
    1.68
     Things
    1.66
     THING
    1.61
    Thing
    1.49
    things
    1.48
    THING
    1.38
    Act Density 0.077%

    No Known Activations