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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with personal beliefs or convictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating interpersonal relationships and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endiary
    -0.83
    interstitial
    -0.76
     prepar
    -0.76
    ancial
    -0.73
    urgical
    -0.72
    PDF
    -0.69
    everal
    -0.68
    earchers
    -0.68
    umerous
    -0.67
    urst
    -0.67
    POSITIVE LOGITS
     me
    1.56
     yourself
    1.51
     yourselves
    1.51
     him
    1.48
     myself
    1.33
     us
    1.31
     HIM
    1.29
     ya
    1.28
     somebody
    1.26
     thee
    1.25
    Act Density 0.725%

    No Known Activations