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

    Neuronpedia

    INDEX
    Explanations

    the word "Just" repeated frequently

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "just."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouse
    -0.61
    gard
    -0.59
    onde
    -0.58
     expire
    -0.57
     coupling
    -0.57
    SI
    -0.56
    oe
    -0.56
     guiActiveUnfocused
    -0.56
    quart
    -0.56
     bil
    -0.56
    POSITIVE LOGITS
     Just
    3.13
    Just
    2.30
     JUST
    1.89
    just
    1.89
     Simply
    1.80
     just
    1.38
    Simply
    1.30
    JUST
    1.29
     Exactly
    1.22
     Nothing
    1.21
    Act Density 0.023%

    No Known Activations