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

    Neuronpedia

    INDEX
    Explanations

    individuals mentioned in news articles or other media

    oai_token-act-pair · gpt-3.5-turbo

    the word "who" as it relates to identifying individuals in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bound
    -0.72
    ulp
    -0.69
    ³³³³
    -0.66
    BACK
    -0.64
     Delicious
    -0.62
    interstitial
    -0.62
    Georg
    -0.61
     Messages
    -0.60
    utable
    -0.60
     Nec
    -0.60
    POSITIVE LOGITS
    soever
    0.98
    ophon
    0.96
    raltar
    0.89
     oversees
    0.85
     resided
    0.85
     oversaw
    0.85
     accompanies
    0.85
     attended
    0.84
     redes
    0.83
     presided
    0.82
    Act Density 0.079%

    No Known Activations