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

    references to personal identifiers or notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efe
    -0.66
     Canaver
    -0.64
    CIA
    -0.62
    ESCO
    -0.60
    NRS
    -0.58
     modifiers
    -0.57
    rogens
    -0.57
    rav
    -0.57
     UNESCO
    -0.57
    BBC
    -0.54
    POSITIVE LOGITS
     residents
    0.60
     Residents
    0.58
     plaintiffs
    0.58
     complainant
    0.56
    ulia
    0.55
     plaintiff
    0.55
     citizens
    0.55
     Smartstocks
    0.54
    oples
    0.54
     passenger
    0.52
    Act Density 1.454%

    No Known Activations