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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of 'nothing'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "nothing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grad
    -0.71
     anonymity
    -0.66
    assis
    -0.65
    asio
    -0.64
    ilt
    -0.64
    ocard
    -0.62
    nee
    -0.62
    CVE
    -0.62
     Appeal
    -0.61
    onym
    -0.61
    POSITIVE LOGITS
     else
    1.34
    Else
    1.12
     whatsoever
    0.94
     Else
    0.87
     remotely
    0.80
     resembling
    0.79
     imaginable
    0.77
     Flask
    0.77
     happened
    0.77
     happens
    0.76
    Act Density 0.037%

    No Known Activations