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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names, particularly those related to projects or individuals involved in various developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ker
    -0.85
    ariat
    -0.80
    oxide
    -0.77
    ku
    -0.76
    ãĥł
    -0.75
    itored
    -0.75
    umar
    -0.75
    opic
    -0.75
    ures
    -0.75
    lex
    -0.74
    POSITIVE LOGITS
     McAuliffe
    1.31
     gubernatorial
    0.94
    uliffe
    0.91
     Gillespie
    0.90
    espie
    0.87
    inelli
    0.79
     Eag
    0.73
     McDonnell
    0.70
    iances
    0.69
    ermott
    0.69
    Act Density 0.012%

    No Known Activations