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

    Neuronpedia

    INDEX
    Explanations

    assertive language indicating beliefs or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endblock
    -0.49
    存于互联网档案馆
    -0.45
     Foreman
    -0.44
    、《
    -0.42
     AssemblyCompany
    -0.40
    Angola
    -0.40
     Unexpected
    -0.39
    uspiel
    -0.39
    casm
    -0.38
     BnF
    -0.38
    POSITIVE LOGITS
     AssemblyCulture
    0.63
     nonUne
    0.47
     that
    0.47
    Tembelea
    0.46
     Daß
    0.45
     bahwa
    0.45
    pośred
    0.45
     désolés
    0.44
     daß
    0.44
    jména
    0.43
    Act Density 0.749%

    No Known Activations