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

    Neuronpedia

    INDEX
    Explanations

    phrases describing attributes or characteristics of people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is," indicating traits or characteristics of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ð
    -0.70
    andise
    -0.68
    inav
    -0.68
    udeau
    -0.68
     congr
    -0.66
     Colleges
    -0.65
     Telesc
    -0.64
     Apart
    -0.63
    iere
    -0.63
     Ensure
    -0.62
    POSITIVE LOGITS
    nt
    1.03
     obligated
    0.94
     supposed
    0.92
    omorphic
    0.92
     definitely
    0.88
     hereby
    0.87
     NOT
    0.87
     bound
    0.87
     not
    0.87
     currently
    0.86
    Act Density 0.386%

    No Known Activations