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

    Neuronpedia

    INDEX
    Explanations

    specific government positions and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to ambassadors and diplomatic roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilogy
    -0.67
    entimes
    -0.67
     snowball
    -0.66
    empt
    -0.66
    atown
    -0.64
     Marketable
    -0.63
    angled
    -0.60
    castle
    -0.59
    arbon
    -0.58
    odes
    -0.58
    POSITIVE LOGITS
     Daniel
    1.59
     Jonathan
    1.58
     Patrick
    1.57
     David
    1.56
     Andrew
    1.54
     Kevin
    1.54
     Richard
    1.53
     Brian
    1.53
     Philippe
    1.52
     Joel
    1.52
    Act Density 1.016%

    No Known Activations