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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to statistical likelihood and inference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    likelihood ratio and function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ernie
    -0.46
    Sri
    -0.46
     Ru
    -0.44
    ]=>
    -0.44
     bü
    -0.44
     Sar
    -0.43
    SAV
    -0.43
     Pab
    -0.42
    amzn
    -0.42
     p
    -0.42
    POSITIVE LOGITS
     likelihood
    1.80
     Likelihood
    1.75
    Likelihood
    1.66
    likelihood
    1.66
    lihood
    0.94
     miniaturka
    0.72
     LIK
    0.71
     probabilidad
    0.68
     вероят
    0.68
     likely
    0.65
    Act Density 0.006%

    No Known Activations