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

    Neuronpedia

    INDEX
    Explanations

    references to random variables and processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     propOrder
    -0.94
    -0.88
    Portale
    -0.85
     Wicidata
    -0.83
    zzleHttp
    -0.81
    دانشنامهٔ
    -0.80
    numerusform
    -0.76
    Erfolge
    -0.75
     yyr
    -0.74
    帖最后由
    -0.74
    POSITIVE LOGITS
    ‗
    0.63
    mund
    0.60
     mund
    0.57
     Sea
    0.56
    mun
    0.54
    BAN
    0.54
    ifdef
    0.53
    ban
    0.53
    Run
    0.52
     Gef
    0.52
    Act Density 0.013%

    No Known Activations