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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and proportions in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -0.86
     houſe
    -0.86
     ſtate
    -0.85
     ſeveral
    -0.83
     Anſ
    -0.82
     purpoſe
    -0.81
     leſs
    -0.81
     Efq
    -0.80
     myſelf
    -0.79
     themſelves
    -0.79
    POSITIVE LOGITS
    TestingModule
    0.57
    .
    0.52
     -->
    0.45
     D
    0.44
    ...
    0.43
     ...
    0.43
     --
    0.42
     
    0.42
     battu
    0.40
    --
    0.39
    Act Density 0.059%

    No Known Activations