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

    Neuronpedia

    INDEX
    Explanations

    elements related to community events and educational information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disg
    -0.18
    orm
    -0.17
     Juliet
    -0.14
    orman
    -0.14
     tens
    -0.14
     Pee
    -0.14
     Rud
    -0.14
    qs
    -0.14
     Rush
    -0.13
     norm
    -0.13
    POSITIVE LOGITS
    insula
    0.18
    oke
    0.15
    olumn
    0.15
    島
    0.15
    abra
    0.15
    juana
    0.15
    igy
    0.15
    олÑĮно
    0.15
    swer
    0.14
    oren
    0.14
    Act Density 0.464%

    No Known Activations