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

    Neuronpedia

    INDEX
    Explanations

    words related to proper names, specifically names ending with "hn" and "nick"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names, particularly related to individuals involved in notable cases or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.79
     Leban
    -0.76
    inav
    -0.75
    mine
    -0.74
     Kuwait
    -0.69
     Cyp
    -0.68
     Kurd
    -0.68
    rera
    -0.65
     MIA
    -0.64
    ÄŁ
    -0.64
    POSITIVE LOGITS
    vironment
    1.04
    umber
    1.02
    atural
    0.97
    swer
    0.95
    aturally
    0.94
    nect
    0.94
    emonic
    0.90
    eman
    0.89
    iversary
    0.87
    hak
    0.83
    Act Density 0.044%

    No Known Activations