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

    Neuronpedia

    INDEX
    Explanations

    references to formal processes and protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubb
    -0.16
    365
    -0.15
    argon
    -0.15
    ænd
    -0.15
    ovat
    -0.14
    mdl
    -0.14
    QUIRE
    -0.14
    562
    -0.14
    _idle
    -0.14
    ôi
    -0.14
    POSITIVE LOGITS
     circular
    0.19
     begs
    0.19
     Transmit
    0.18
     Circular
    0.17
     Desired
    0.17
     Mess
    0.16
     favor
    0.16
     transmit
    0.16
    uyết
    0.15
    -request
    0.15
    Act Density 0.064%

    No Known Activations