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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns related to individuals or groups

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Finish
    -0.72
     recess
    -0.71
    Closure
    -0.66
     commission
    -0.65
     rhy
    -0.65
     Sacrament
    -0.62
     Congo
    -0.60
     Angola
    -0.57
     FX
    -0.56
    ulton
    -0.56
    POSITIVE LOGITS
    adow
    1.15
    hers
    1.10
    atically
    1.05
    imei
    1.04
    aning
    1.00
    adows
    0.97
    andering
    0.96
    asuring
    0.93
    selves
    0.92
    ubi
    0.91
    Act Density 0.145%

    No Known Activations