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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    oai_token-act-pair · gpt-3.5-turbo

    references to the speaker and the collective, emphasizing personal and shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Finish
    -0.78
    ulton
    -0.73
    REP
    -0.66
     HRC
    -0.62
    CLOSE
    -0.60
    Construction
    -0.60
     instituted
    -0.59
    Record
    -0.59
     Sind
    -0.58
    Finish
    -0.57
    POSITIVE LOGITS
    adow
    1.13
    imei
    0.99
    adows
    0.99
    erent
    0.90
    andering
    0.89
    ern
    0.84
    usal
    0.83
    hers
    0.82
    uf
    0.80
    asured
    0.79
    Act Density 0.084%

    No Known Activations