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

    Neuronpedia

    INDEX
    Explanations

    references to character encoding and formats used in data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .chapter
    -0.17
     kl
    -0.16
     Baker
    -0.14
     OO
    -0.14
    phinx
    -0.14
    iales
    -0.14
    Priv
    -0.14
    еÑģп
    -0.14
    ÑĢаж
    -0.14
    yer
    -0.14
    POSITIVE LOGITS
     Trait
    0.15
    witch
    0.14
     lá»ĩ
    0.14
     Plane
    0.14
    æ²ĸ
    0.14
     planes
    0.14
    alace
    0.14
    YNAM
    0.13
    ahan
    0.13
    artz
    0.13
    Act Density 0.047%

    No Known Activations