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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating surprise or amazement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or amazement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":[{"
    -0.83
    href
    -0.76
     delinqu
    -0.71
    andro
    -0.70
     obligated
    -0.69
    apers
    -0.67
    uting
    -0.65
    pent
    -0.65
     pigeon
    -0.65
     commod
    -0.64
    POSITIVE LOGITS
    zers
    1.05
    orld
    0.99
    ards
    0.95
     Wow
    0.92
    yssey
    0.90
    Wow
    0.85
    herty
    0.84
     wow
    0.82
    wow
    0.81
    pedia
    0.81
    Act Density 0.013%

    No Known Activations