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

    Neuronpedia

    INDEX
    Explanations

    names of famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.91
    ULAR
    -0.68
    BILITY
    -0.65
    channelAvailability
    -0.65
    inarily
    -0.64
    malink
    -0.63
    rency
    -0.61
    itionally
    -0.60
    alyses
    -0.60
    RIPT
    -0.60
    POSITIVE LOGITS
     Kardash
    0.96
     Klux
    0.94
     Oprah
    0.82
     Barbie
    0.80
     Kardashian
    0.78
     Coke
    0.77
     Beatles
    0.76
    infeld
    0.75
    opoly
    0.74
     Einstein
    0.74
    Act Density 0.348%

    No Known Activations