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

    Neuronpedia

    INDEX
    Explanations

    references to activities or items related to being at home

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "home" or related places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratulations
    -0.62
    zhen
    -0.58
    sylv
    -0.58
     choir
    -0.57
     Peb
    -0.57
     Patriarch
    -0.56
     Duff
    -0.56
    anson
    -0.55
     spores
    -0.54
    ERY
    -0.54
    POSITIVE LOGITS
     behest
    0.99
     glance
    0.89
     expense
    0.87
     discretion
    0.84
     disposal
    0.83
    Footnote
    0.79
     helm
    0.76
     intersections
    0.74
     apiece
    0.71
     outset
    0.69
    Act Density 0.212%

    No Known Activations