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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    different forms of verbs or verb endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.80
     Janeiro
    -0.78
     Siren
    -0.74
    ģ«
    -0.74
     plun
    -0.72
    Trend
    -0.69
    Unix
    -0.67
    ï¸
    -0.67
    Priv
    -0.64
     Azerbai
    -0.63
    POSITIVE LOGITS
    eston
    0.77
    hof
    0.75
    igans
    0.74
    aum
    0.73
    eday
    0.73
    loe
    0.70
     AFB
    0.69
    jee
    0.68
    »Ĵ
    0.67
    oe
    0.66
    Act Density 0.216%

    No Known Activations