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

    Neuronpedia

    INDEX
    Explanations

    the word "who" and its variations, indicating a focus on identifying subjects or entities within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anything
    -0.73
     Anyway
    -0.73
     VIDEOS
    -0.71
     Delicious
    -0.68
     Trop
    -0.63
    Okay
    -0.61
     Done
    -0.59
     Viper
    -0.59
     Seah
    -0.59
    BACK
    -0.59
    POSITIVE LOGITS
     specialize
    1.23
     were
    1.12
     weren
    1.11
     migrated
    1.10
     reside
    1.10
     comprise
    1.08
     are
    1.07
     resided
    1.04
    oping
    1.03
     aren
    1.03
    Act Density 0.108%

    No Known Activations