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

    Neuronpedia

    INDEX
    Explanations

    references to rarity or uncommon events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¼ĺ
    -0.15
     loose
    -0.15
    ç²Ĺ
    -0.15
     mrb
    -0.14
     rough
    -0.14
    ä¹ħ
    -0.14
    atures
    -0.14
    esk
    -0.14
     Leer
    -0.13
    hurst
    -0.13
    POSITIVE LOGITS
     Deck
    0.16
    uto
    0.16
    ?type
    0.15
    faction
    0.15
    pedia
    0.14
    åĽł
    0.14
    ìŀ¥
    0.13
    tero
    0.13
    urma
    0.13
    orld
    0.13
    Act Density 0.081%

    No Known Activations