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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures related to statistics and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.66
    hett
    -0.66
    assies
    -0.65
    aud
    -0.65
    IDENT
    -0.61
    icans
    -0.60
     Commun
    -0.59
    ophers
    -0.58
    henko
    -0.57
    aria
    -0.57
    POSITIVE LOGITS
     exceeding
    1.17
     ranging
    1.07
     averaging
    0.96
     comparable
    0.96
     whopping
    0.93
     approx
    0.89
     estimated
    0.89
     âī¥
    0.88
     unimaginable
    0.87
     equal
    0.85
    Act Density 0.116%

    No Known Activations