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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names of people or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     metic
    -0.54
    Reviewer
    -0.52
    ãĥ´ãĤ¡
    -0.50
    DonaldTrump
    -0.49
     incredibly
    -0.49
     upfront
    -0.48
     unbelievably
    -0.48
     mathemat
    -0.47
     amazingly
    -0.47
     looph
    -0.46
    POSITIVE LOGITS
     respectively
    1.13
     etc
    0.77
     Jr
    0.67
    ))))
    0.65
    )).
    0.64
    )))
    0.61
     attRot
    0.61
    ]).
    0.59
    *.
    0.58
     thereto
    0.57
    Act Density 1.182%

    No Known Activations