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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research activities and funding sources

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating research activities and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.94
    nob
    -0.68
     creeps
    -0.67
     sugars
    -0.66
     sucks
    -0.66
    emo
    -0.64
     contrace
    -0.63
    å¥
    -0.63
     wizard
    -0.63
     sucked
    -0.63
    POSITIVE LOGITS
     Mub
    0.80
     Naval
    0.76
     Canon
    0.69
     Kens
    0.67
     Allison
    0.67
     Interstate
    0.66
     Lockheed
    0.66
     Markus
    0.65
     CVE
    0.65
     Operation
    0.65
    Act Density 0.531%

    No Known Activations