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

    Neuronpedia

    INDEX
    Explanations

    organizations, projects, and specific terms related to technology or security

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.64
    eters
    -0.62
    alde
    -0.62
    ographies
    -0.61
    EngineDebug
    -0.61
    joy
    -0.60
    itures
    -0.60
    ocalypse
    -0.60
    igne
    -0.59
    ocations
    -0.58
    POSITIVE LOGITS
     aka
    1.18
     which
    1.02
    another
    0.96
     whereby
    0.89
    which
    0.87
     formerly
    0.83
    formerly
    0.83
     another
    0.81
     whose
    0.80
     meaning
    0.78
    Act Density 0.344%

    No Known Activations