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

    Neuronpedia

    INDEX
    Explanations

    exclamations expressing surprise or astonishment

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory expressions of surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.75
    20439
    -0.72
     concess
    -0.69
     interchange
    -0.68
    oided
    -0.67
    isSpecialOrderable
    -0.67
    adle
    -0.65
    Rated
    -0.65
    entary
    -0.64
    ilater
    -0.63
    POSITIVE LOGITS
    Wow
    1.14
     Wow
    1.09
     wow
    1.07
    Holy
    1.06
     Damn
    1.05
    Damn
    1.03
     OMG
    1.03
     THIS
    0.99
     WHAT
    0.97
    wow
    0.96
    Act Density 0.219%

    No Known Activations