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

    Neuronpedia

    INDEX
    Explanations

    references to identity, production, and the ability to achieve goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.17
    rupa
    -0.15
    (æľĪ
    -0.14
    ваÑĢ
    -0.14
     Its
    -0.13
     Their
    -0.13
    aign
    -0.13
    arend
    -0.13
    agi
    -0.13
    aru
    -0.13
    POSITIVE LOGITS
     them
    1.17
    them
    0.96
     Them
    0.74
     ниÑħ
    0.68
    Them
    0.66
    å®ĥ们
    0.63
     ellas
    0.60
     ihnen
    0.60
     chúng
    0.57
     THEM
    0.57
    Act Density 0.978%

    No Known Activations