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

    Neuronpedia

    INDEX
    Explanations

    words related to languages or translations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of languages and subtitles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndra
    -0.93
    urion
    -0.86
    olicy
    -0.84
    gaard
    -0.81
    hardt
    -0.76
    anmar
    -0.75
    seeking
    -0.75
    ilitarian
    -0.74
    achine
    -0.74
    ividual
    -0.72
    POSITIVE LOGITS
     translation
    1.47
     pronunciation
    1.38
     subtitles
    1.36
     translations
    1.33
     language
    1.30
     diction
    1.24
     dictionary
    1.22
     spelling
    1.18
    language
    1.14
     speakers
    1.14
    Act Density 0.078%

    No Known Activations