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

    Neuronpedia

    INDEX
    Explanations

    references to reports and journals in the context of news and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oci
    -0.15
    úc
    -0.15
    azon
    -0.15
     maduras
    -0.14
     Ä°z
    -0.14
    ultz
    -0.14
    ken
    -0.13
    assin
    -0.13
    í
    -0.13
    quare
    -0.13
    POSITIVE LOGITS
    ertime
    0.16
     scre
    0.14
    ereo
    0.13
    IQ
    0.13
    heiro
    0.13
    soever
    0.13
     Ryder
    0.13
     Alam
    0.12
    earable
    0.12
    Ñħов
    0.12
    Act Density 0.200%

    No Known Activations