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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize a sense of exclusivity or limitation

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idon
    -0.76
    insula
    -0.75
    Nev
    -0.71
    finder
    -0.65
    multipl
    -0.62
    arted
    -0.61
    raught
    -0.59
     Everest
    -0.58
    cent
    -0.58
    ordering
    -0.57
    POSITIVE LOGITS
     marginally
    1.02
     incidentally
    0.78
     lasted
    0.75
     scratches
    0.74
     scratched
    0.73
     sparing
    0.72
     rarely
    0.72
     limited
    0.71
     kidding
    0.70
    isons
    0.69
    Act Density 0.066%

    No Known Activations