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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or characters within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to legal proceedings or news articles mentioning specific individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    enei
    -0.67
    opian
    -0.65
     Centauri
    -0.64
     zoo
    -0.64
     level
    -0.64
     drain
    -0.64
     indo
    -0.63
     infring
    -0.63
     alley
    -0.62
     lounge
    -0.61
    POSITIVE LOGITS
    particularly
    0.97
    whose
    0.95
    including
    0.95
    especially
    0.92
    perhaps
    0.92
    ————
    0.91
    again
    0.89
    along
    0.87
    pictured
    0.83
    albeit
    0.82
    Act Density 0.200%

    No Known Activations