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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to optics and data analysis in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.91
    %")
    -0.89
     Савезне
    -0.89
     myſelf
    -0.87
     ―――――
    -0.86
    )».
    -0.85
     виправивши
    -0.82
    }")
    -0.82
    %");
    -0.81
    sizeCache
    -0.81
    POSITIVE LOGITS
     is
    0.74
    ...
    0.73
     =
    0.73
     
    0.69
     ...
    0.68
     in
    0.67
    的
    0.65
     also
    0.65
     stesso
    0.65
     stessa
    0.64
    Act Density 14.284%

    No Known Activations