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

    Neuronpedia

    INDEX
    Explanations

    language-related concepts, including standards, education, and multilingualism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unn
    -0.15
    .scalablytyped
    -0.15
    undry
    -0.15
    edi
    -0.14
     Jaune
    -0.14
     escort
    -0.14
    arden
    -0.13
    arParams
    -0.13
    insn
    -0.13
    Compression
    -0.13
    POSITIVE LOGITS
     English
    0.81
    English
    0.73
     Eng
    0.71
     english
    0.71
     eng
    0.63
    english
    0.63
     Engl
    0.62
    Eng
    0.60
     England
    0.60
     ENG
    0.60
    Act Density 0.160%

    No Known Activations