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

    Neuronpedia

    INDEX
    Explanations

    phrases related to absence or lack of something

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "nothing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assis
    -0.72
    asio
    -0.71
    grad
    -0.68
    CVE
    -0.68
    NAS
    -0.65
     srf
    -0.63
    ilt
    -0.63
    onduct
    -0.62
    osen
    -0.61
     anonymity
    -0.61
    POSITIVE LOGITS
     else
    1.30
    Else
    1.13
     whatsoever
    0.90
     Else
    0.89
     imaginable
    0.79
     remotely
    0.78
     happens
    0.75
     happened
    0.73
    ness
    0.71
     except
    0.71
    Act Density 0.037%

    No Known Activations