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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugar
    -0.17
    gere
    -0.16
    asse
    -0.15
    odore
    -0.14
    922
    -0.13
    aille
    -0.13
    骨
    -0.13
    una
    -0.13
    utar
    -0.13
    ivant
    -0.13
    POSITIVE LOGITS
    /or
    0.22
    amp
    0.18
    rew
    0.17
    REW
    0.16
     amp
    0.16
    /of
    0.15
    rzy
    0.14
    quot
    0.14
    readcr
    0.14
    erson
    0.14
    Act Density 0.098%

    No Known Activations