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

    Neuronpedia

    INDEX
    Explanations

    misprints or errors marked with 'sic'

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "sic," often used to indicate quoted material or to denote something that is intentionally misspelled or awkward

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VIEW
    -0.81
    EVA
    -0.77
    ships
    -0.76
    MQ
    -0.72
    eus
    -0.72
    Winged
    -0.70
    è¦ļéĨĴ
    -0.68
    ĪĴ
    -0.68
    Arm
    -0.68
    eur
    -0.67
    POSITIVE LOGITS
    atin
    0.76
    sic
    0.70
    rano
    0.69
    ername
    0.69
    odynamic
    0.68
     offend
    0.67
    oman
    0.67
     offense
    0.66
     Talent
    0.65
    iban
    0.65
    Act Density 0.018%

    No Known Activations