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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the character "ñ" or similar diacritical marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipp
    -0.17
    ies
    -0.16
    ron
    -0.16
    à¤Ŀ
    -0.16
    enco
    -0.15
    orsche
    -0.15
    .scalablytyped
    -0.15
    olest
    -0.15
    wald
    -0.15
    ĵ
    -0.14
    POSITIVE LOGITS
    ergy
    0.14
    olta
    0.14
    chos
    0.14
    acers
    0.14
     Hunter
    0.13
     Morales
    0.13
    anan
    0.13
    Hunter
    0.13
     Yates
    0.13
    mph
    0.13
    Act Density 0.001%

    No Known Activations