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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusivity or limitation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nowhere
    -0.72
    pipe
    -0.66
    rary
    -0.66
    phen
    -0.66
    idon
    -0.66
    insula
    -0.65
    zin
    -0.64
    hement
    -0.63
    cent
    -0.61
    ducers
    -0.61
    POSITIVE LOGITS
     marginally
    1.05
     lasted
    1.00
     ever
    0.90
     scratched
    0.89
     cares
    0.87
     lasts
    0.86
     spor
    0.85
     cared
    0.81
     existed
    0.77
     pretended
    0.74
    Act Density 0.059%

    No Known Activations