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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns indicating the self or others

    oai_token-act-pair · gpt-3.5-turbo

    references to self-identity and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Finish
    -0.79
     recess
    -0.64
    ulton
    -0.63
     Doors
    -0.60
     FX
    -0.60
    Closure
    -0.57
     Sacrament
    -0.56
     commission
    -0.56
     Equality
    -0.55
     rhy
    -0.55
    POSITIVE LOGITS
    adow
    1.20
    atically
    1.15
    imei
    1.12
    atic
    1.05
    adows
    1.05
    andering
    1.03
    atics
    0.98
    aning
    0.97
    asure
    0.96
    eting
    0.96
    Act Density 0.098%

    No Known Activations