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

    Neuronpedia

    INDEX
    Explanations

    references to groups and experimental conditions in a research context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     turístico
    -0.70
     sû
    -0.65
     gordo
    -0.62
    adaptiveStyles
    -0.56
     nød
    -0.56
     jurídica
    -0.56
     reaſon
    -0.56
     geox
    -0.56
     dwar
    -0.56
     sects
    -0.55
    POSITIVE LOGITS
    IsContent
    0.74
     isInitialized
    0.65
    twimg
    0.60
    >--}}
    0.60
    AndEndTag
    0.58
    ,‎
    0.56
    ريف
    0.56
     الحره
    0.56
     skor
    0.54
    '...
    0.53
    Act Density 0.045%

    No Known Activations