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

    Neuronpedia

    INDEX
    Explanations

    the name "Jacobs" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Jacobs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anguage
    -0.98
    achev
    -0.83
    gement
    -0.77
    ged
    -0.76
    itaire
    -0.76
    mberg
    -0.76
    atively
    -0.75
    etheless
    -0.74
    otypes
    -0.73
    vironment
    -0.72
    POSITIVE LOGITS
    aign
    0.98
     Jacobs
    0.84
    quet
    0.79
    enter
    0.77
    keye
    0.75
    hma
    0.73
    agne
    0.72
    robe
    0.71
    xon
    0.71
    eries
    0.71
    Act Density 0.032%

    No Known Activations