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

    Neuronpedia

    INDEX
    Explanations

    the word "under" and its variations, indicating a focus on conditions or situations that are subordinate or dependent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pingback
    -0.77
    djangoproject
    -0.75
     Carlin
    -0.75
    pyplot
    -0.73
     Frieden
    -0.68
    RSpec
    -0.68
    ethnicity
    -0.67
     Spartans
    -0.67
    Mapp
    -0.66
    ifera
    -0.65
    POSITIVE LOGITS
    Under
    1.88
     Under
    1.88
    under
    1.84
     under
    1.83
    UNDER
    1.78
     UNDER
    1.73
    neath
    1.41
     unter
    1.32
     Underwood
    1.31
    nder
    1.26
    Act Density 0.101%

    No Known Activations