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

    Neuronpedia

    INDEX
    Explanations

    references to signs and signage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .metamodel
    -0.15
    OUCH
    -0.14
    วย
    -0.14
    Ĺi
    -0.14
    assin
    -0.14
    acer
    -0.13
    anko
    -0.13
    edik
    -0.13
    ouch
    -0.13
    adders
    -0.13
    POSITIVE LOGITS
    Ưá»
    0.15
    rase
    0.15
    овÑĸ
    0.14
    ottage
    0.14
    abet
    0.14
    ÑģÑĤи
    0.14
    ynn
    0.14
    Launcher
    0.14
    nie
    0.13
    arna
    0.13
    Act Density 0.012%

    No Known Activations