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

    Neuronpedia

    INDEX
    Explanations

    phrases related to requests for comments or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    airy
    -0.14
    leck
    -0.14
     Tunnel
    -0.14
    thinkable
    -0.14
    es
    -0.14
     grand
    -0.14
    ners
    -0.13
    Ñģка
    -0.13
    ĥģ
    -0.13
     Strings
    -0.13
    POSITIVE LOGITS
     hood
    0.17
    UTO
    0.16
    ADDE
    0.15
    morgan
    0.15
     Hood
    0.14
    à¥Įन
    0.14
    Charsets
    0.14
    ocos
    0.14
     Charm
    0.14
    AFX
    0.14
    Act Density 0.017%

    No Known Activations