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

    Neuronpedia

    INDEX
    Explanations

    proper nouns with additional symbols or characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     crush
    -0.65
    INT
    -0.61
    place
    -0.61
    IPS
    -0.61
    ulate
    -0.60
     gist
    -0.59
    DonaldTrump
    -0.59
    iph
    -0.59
     Cobra
    -0.59
    itutional
    -0.58
    POSITIVE LOGITS
    ø
    1.34
     Andersen
    0.98
    å
    0.91
    hett
    0.89
    ĨĴ
    0.87
    ð
    0.86
    æ
    0.85
    borg
    0.85
     Bok
    0.83
    ö
    0.83
    Act Density 0.004%

    No Known Activations