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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pitié
    -0.81
     ainfi
    -0.76
     Lightboxes
    -0.76
     uſed
    -0.75
     Teut
    -0.73
     незавершена
    -0.73
    OGND
    -0.73
     Decent
    -0.72
     Venise
    -0.72
     avoient
    -0.72
    POSITIVE LOGITS
    にとって
    0.60
    にとっては
    0.60
    来说
    0.54
    來說
    0.53
    而言
    0.51
     számára
    0.47
    来讲
    0.47
     cas
    0.46
     
    0.44
     StatelessWidget
    0.43
    Act Density 0.199%

    No Known Activations