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

    Neuronpedia

    INDEX
    Explanations

    titles and references to book series and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eman
    -0.19
    uest
    -0.16
     Fell
    -0.15
     Eisen
    -0.15
    ula
    -0.14
    uler
    -0.14
    etik
    -0.14
    hek
    -0.14
     Widow
    -0.14
    elin
    -0.14
    POSITIVE LOGITS
     dil
    0.16
    affles
    0.14
    ongs
    0.14
    eceÄŁi
    0.14
    ivec
    0.14
    ynos
    0.14
    Tpl
    0.14
    osten
    0.14
    athon
    0.13
    .cg
    0.13
    Act Density 0.020%

    No Known Activations