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

    Neuronpedia

    INDEX
    Explanations

    references to data organization and statistical analysis in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
                                   
    -1.20
    -1.11
    -1.07
    …………………………………………
    -1.07
    -1.07
    -1.05
    -1.05
    -1.04
    -1.04
    -1.04
    POSITIVE LOGITS
    ....
    0.46
        
    0.43
    ..
    0.42
     prohibido
    0.42
    .....
    0.41
     noqa
    0.40
    lepaskan
    0.40
    setUse
    0.39
    ...
    0.39
         
    0.39
    Act Density 0.391%

    No Known Activations