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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, including names of people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and organizations involved in events or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arlington
    -0.85
     Stall
    -0.82
     Allan
    -0.81
    582
    -0.80
    585
    -0.80
    tan
    -0.77
     Burgess
    -0.76
     Fairfax
    -0.75
     Ambrose
    -0.74
    575
    -0.72
    POSITIVE LOGITS
    J
    1.61
    j
    1.59
    JD
    1.41
    JA
    1.35
    Js
    1.33
    ja
    1.33
     J
    1.33
    IJ
    1.30
    jc
    1.30
    jo
    1.29
    Act Density 0.407%

    No Known Activations