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

    Neuronpedia

    INDEX
    Explanations

    references to a specific person or name, specifically "Kl" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific name or term related to a person

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.91
    ãĥ¼ãĥĨãĤ£
    -0.83
    ãģ®éŃĶ
    -0.79
    CLASSIFIED
    -0.78
    EMENT
    -0.78
     spirited
    -0.73
    TAIN
    -0.72
    ELY
    -0.71
    CEPT
    -0.71
    llah
    -0.69
    POSITIVE LOGITS
    assic
    1.20
     Klux
    1.05
    oser
    1.00
    adium
    0.98
    avier
    0.92
    itsch
    0.90
    utz
    0.88
    osing
    0.88
    appa
    0.87
    atin
    0.86
    Act Density 0.018%

    No Known Activations