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

    Neuronpedia

    INDEX
    Explanations

    mentions of social control and manipulation themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tens
    -0.16
     надо
    -0.15
    _parms
    -0.14
     :-)
    -0.14
    oka
    -0.14
    Ùģر
    -0.14
    asyarak
    -0.14
    аÑĪ
    -0.14
    OTO
    -0.14
     lots
    -0.13
    POSITIVE LOGITS
     ëĺIJíķľ
    0.15
    Furthermore
    0.14
     sonst
    0.14
    null
    0.14
    industry
    0.14
     jov
    0.13
    ª
    0.13
     OTHERWISE
    0.13
    -esque
    0.13
     Furthermore
    0.13
    Act Density 2.303%

    No Known Activations