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

    Neuronpedia

    INDEX
    Explanations

    references to specific films, awards, and individuals in the entertainment industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Antoine
    -0.15
    ụ
    -0.14
    æĶ¯
    -0.14
    åħį
    -0.14
    ICLE
    -0.14
     Hud
    -0.14
    ัวร
    -0.13
    iage
    -0.13
     Bene
    -0.13
    itage
    -0.13
    POSITIVE LOGITS
    ayar
    0.20
    imar
    0.18
    ाà¤ĸ
    0.18
    åºľ
    0.17
    ahead
    0.16
    ikit
    0.16
    KF
    0.15
    äºŃ
    0.15
     correct
    0.15
    ós
    0.15
    Act Density 0.037%

    No Known Activations