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

    Neuronpedia

    INDEX
    Explanations

    language that indicates the beginning or end of a paragraph or section

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'performance.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.81
    SpaceEngineers
    -0.79
    å¸
    -0.75
    aries
    -0.72
    76561
    -0.71
    EStreamFrame
    -0.70
    éļ
    -0.70
    ãģĭ
    -0.68
    çĶ
    -0.68
    ãģı
    -0.68
    POSITIVE LOGITS
    iod
    1.02
    secut
    0.97
     capita
    0.94
    ipher
    0.92
    pend
    0.89
    secution
    0.89
    ceptions
    0.89
    jury
    0.86
    missions
    0.85
    ience
    0.85
    Act Density 0.009%

    No Known Activations