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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of dystopia and its historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orgh
    -0.16
    undler
    -0.15
    digest
    -0.15
    çķĻ
    -0.15
    .crm
    -0.15
    imonials
    -0.15
    ubic
    -0.14
    raq
    -0.14
    ossa
    -0.14
    'gc
    -0.14
    POSITIVE LOGITS
     Dictionary
    0.33
     dictionary
    0.33
    Dictionary
    0.31
     dictionaries
    0.30
     Oxford
    0.29
    dictionary
    0.28
     Webster
    0.28
     Word
    0.25
    (Dictionary
    0.25
     Collins
    0.25
    Act Density 0.135%

    No Known Activations