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

    Neuronpedia

    INDEX
    Explanations

    locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the pronoun "you" and phrases that indicate personal perspectives or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uthor
    -0.65
    advertisement
    -0.64
    yss
    -0.63
    avage
    -0.62
     Hacker
    -0.59
     Leilan
    -0.59
    chan
    -0.58
    naires
    -0.58
    ienne
    -0.58
    429
    -0.56
    POSITIVE LOGITS
     weakest
    0.93
     reside
    0.93
     resided
    0.91
     resides
    0.91
     originated
    0.80
     originate
    0.79
     belong
    0.79
     happiest
    0.78
    ezvous
    0.76
     LIVE
    0.75
    Act Density 0.265%

    No Known Activations