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

    Neuronpedia

    INDEX
    Explanations

    key aspects related to updates or announcements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amburger
    -0.17
    yster
    -0.16
     odds
    -0.16
    alar
    -0.15
    offee
    -0.14
    ãĥ¼ãĥĪ
    -0.14
    nave
    -0.14
     lá»ĩ
    -0.14
     nog
    -0.13
    Ø®Ùħ
    -0.13
    POSITIVE LOGITS
    esen
    0.14
     Rams
    0.14
    zl
    0.14
    inear
    0.14
    Protected
    0.13
    zin
    0.13
    airo
    0.13
     reconstruct
    0.13
    tg
    0.13
    isclosed
    0.13
    Act Density 0.146%

    No Known Activations