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

    Neuronpedia

    INDEX
    Explanations

    mentions of the English language

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the English language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enges
    -0.74
    psy
    -0.74
    ĸļ
    -0.70
    eus
    -0.70
    onies
    -0.69
    usky
    -0.68
    achine
    -0.68
    vati
    -0.68
    Downloadha
    -0.67
    pty
    -0.67
    POSITIVE LOGITS
     translation
    1.03
    language
    0.97
    speaking
    0.96
    shire
    0.96
     muff
    0.94
     translations
    0.91
     subtitles
    0.89
    man
    0.88
    men
    0.86
    spe
    0.82
    Act Density 0.031%

    No Known Activations