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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "named" followed by a name or character reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.87
    âķIJ
    -0.82
    âķIJâķIJ
    -0.77
    EMS
    -0.77
    iership
    -0.77
    pling
    -0.76
    qua
    -0.73
    aukee
    -0.73
    pled
    -0.72
    ibraries
    -0.72
    POSITIVE LOGITS
     Sov
    0.87
     Ir
    0.84
     TOM
    0.84
     aliases
    0.79
     surn
    0.79
     Xen
    0.79
     Faw
    0.78
     Watt
    0.77
     Ares
    0.77
     Seymour
    0.77
    Act Density 0.032%

    No Known Activations