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

    Neuronpedia

    INDEX
    Explanations

    expressions of 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
    icipated
    -0.71
     redress
    -0.67
    rive
    -0.65
     alternate
    -0.63
    epend
    -0.62
     externalToEVAOnly
    -0.62
     obligated
    -0.62
    atum
    -0.60
    rift
    -0.60
    actionDate
    -0.59
    POSITIVE LOGITS
    zers
    1.31
     wow
    1.04
     Wow
    1.00
    !:
    0.99
    !
    0.97
    !!!
    0.97
    !!
    0.94
    !!!!
    0.94
    pedia
    0.92
    wow
    0.91
    Act Density 0.032%

    No Known Activations