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

    Neuronpedia

    INDEX
    Explanations

    terms related to foundational structures or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atz
    -0.16
     Brass
    -0.15
    ize
    -0.15
    urm
    -0.15
    ut
    -0.14
     Franken
    -0.14
    ude
    -0.14
     Bang
    -0.14
    leet
    -0.14
    jug
    -0.14
    POSITIVE LOGITS
    onian
    0.16
     grátis
    0.16
    dere
    0.15
    azo
    0.14
     Gir
    0.14
    rones
    0.14
    rvé
    0.14
    enger
    0.14
     gezocht
    0.14
    witter
    0.14
    Act Density 0.001%

    No Known Activations