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

    Neuronpedia

    INDEX
    Explanations

    Python-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages and associated terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rss
    -0.75
    lain
    -0.73
    laus
    -0.71
    osaurs
    -0.70
    Ó
    -0.70
    recent
    -0.68
    âĢİ
    -0.68
    hig
    -0.68
    ̶
    -0.68
    xon
    -0.67
    POSITIVE LOGITS
     equivalent
    0.84
     counterpart
    0.83
     equivalents
    0.73
     identity
    0.72
     version
    0.71
     contribution
    0.70
     lover
    0.70
     sphere
    0.69
     entity
    0.69
     pointer
    0.69
    Act Density 0.416%

    No Known Activations