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

    Neuronpedia

    INDEX
    Explanations

    proper names and titles

    oai_token-act-pair · gpt-3.5-turbo

    prominent individuals and their positions or actions in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !.
    -0.64
    .ãĢį
    -0.64
    omatic
    -0.60
    Marginal
    -0.59
    }.
    -0.59
     ().
    -0.59
    .--
    -0.58
    ãĥĩãĤ£
    -0.57
    _>
    -0.56
    ê
    -0.56
    POSITIVE LOGITS
     should
    1.13
     shouldn
    1.08
     lacked
    1.02
     lacks
    0.94
     hadn
    0.93
     owes
    0.93
     had
    0.90
     deserved
    0.89
     could
    0.88
     violated
    0.87
    Act Density 0.636%

    No Known Activations