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

    Neuronpedia

    INDEX
    Explanations

    phrases related to writing and publications

    oai_token-act-pair · gpt-3.5-turbo

    references to academic work or papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.70
    Layer
    -0.69
    Iterator
    -0.67
    äºĶ
    -0.65
    aurus
    -0.65
    bear
    -0.63
     sucks
    -0.63
    Bi
    -0.61
    LOG
    -0.61
    beard
    -0.61
    POSITIVE LOGITS
     behalf
    1.17
     basis
    1.11
     eve
    1.01
     topic
    0.99
     occasion
    0.98
     outskirts
    0.96
     aforementioned
    0.94
     sidelines
    0.91
     occasions
    0.88
     merits
    0.87
    Act Density 0.181%

    No Known Activations