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

    Neuronpedia

    INDEX
    Explanations

    words related to statistics and analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical methods and analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -1.06
    eem
    -0.94
    aline
    -0.79
    nen
    -0.78
    shire
    -0.78
    ktop
    -0.75
    ding
    -0.74
    pires
    -0.74
    ijing
    -0.72
    gro
    -0.72
    POSITIVE LOGITS
    istically
    1.22
    istical
    1.10
     significance
    0.92
     anomalies
    0.89
     anomaly
    0.87
     impossibility
    0.84
     probability
    0.81
     statistical
    0.80
    istics
    0.77
     coefficient
    0.76
    Act Density 0.014%

    No Known Activations