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

    Neuronpedia

    INDEX
    Explanations

    connectors, specifically conjunctions and other linking words in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upa
    -0.16
    <?,
    -0.15
    ather
    -0.15
    erland
    -0.14
    erap
    -0.14
    hab
    -0.14
     Worst
    -0.13
    lush
    -0.13
    Ñıг
    -0.13
    arest
    -0.13
    POSITIVE LOGITS
     massaggi
    0.15
    bau
    0.15
    /or
    0.15
    bai
    0.14
    677
    0.14
    ouver
    0.14
     legit
    0.14
    éné
    0.14
    awah
    0.13
    nicos
    0.13
    Act Density 0.202%

    No Known Activations