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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific entities, possibly organizations or companies

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and entities related to sports and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ''.
    -0.63
    )).
    -0.54
    ungle
    -0.51
    ĸļ
    -0.50
     ......
    -0.49
    $$$$
    -0.48
    .''
    -0.48
    gdala
    -0.48
    imar
    -0.47
    .�
    -0.47
    POSITIVE LOGITS
    udos
    0.56
     planners
    0.51
    pires
    0.51
     Decay
    0.51
     isn
    0.51
     advocates
    0.50
     refers
    0.50
     hasn
    0.50
     hadn
    0.50
    law
    0.50
    Act Density 0.991%

    No Known Activations