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

    Neuronpedia

    INDEX
    Explanations

    words related to surprise or sudden revelation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of shock or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amins
    -0.89
    ciplinary
    -0.79
    resources
    -0.74
    ouf
    -0.72
    ept
    -0.72
    pmwiki
    -0.71
    ajo
    -0.69
    iosyncr
    -0.69
    inth
    -0.69
    effic
    -0.67
    POSITIVE LOGITS
     stunned
    1.15
     shocked
    1.12
     aback
    1.01
     horrified
    0.92
     incred
    0.83
     onlook
    0.82
     surprised
    0.81
     astonished
    0.81
     bystanders
    0.81
     startled
    0.79
    Act Density 0.012%

    No Known Activations