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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to Soviet/US space race history

    oai_token-act-pair · gemini-2.0-flash

    proper nouns or names

    np_token-act-pair-logits · gpt-4o-mini

    rocket launches or space

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.66
     gratuites
    -0.65
     culturelles
    -0.64
     pouvoit
    -0.62
     chré
    -0.62
    makeText
    -0.61
    RODUZIONE
    -0.59
     célè
    -0.58
     ")");
    -0.58
    verifyException
    -0.58
    POSITIVE LOGITS
     Bourgoin
    0.50
     esti
    0.48
     Or
    0.47
    Or
    0.45
    oline
    0.45
    igshid
    0.44
     quebra
    0.44
    FailureListener
    0.43
     ser
    0.42
     Mole
    0.42
    Act Density 1.412%

    No Known Activations