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

    Neuronpedia

    INDEX
    Explanations

    affective language concerning collective identity and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unsplash
    -0.51
    きましょう
    -0.43
    NoError
    -0.43
     nämlich
    -0.42
    formazione
    -0.42
     tersebut
    -0.42
    ]='\
    -0.41
    SuppressWarnings
    -0.41
    tersebut
    -0.41
    ittarius
    -0.41
    POSITIVE LOGITS
     our
    1.09
     ourselves
    1.06
     nossas
    0.92
     nossa
    0.91
     nosso
    0.90
    我们的
    0.89
     nossos
    0.89
    our
    0.87
    Our
    0.87
     naše
    0.87
    Act Density 0.830%

    No Known Activations