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

    Neuronpedia

    INDEX
    Explanations

    words related to houses or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "House" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iation
    -0.73
    ISO
    -0.69
    aneously
    -0.67
    oshop
    -0.66
    istical
    -0.66
    onal
    -0.65
     DPR
    -0.65
    ï¸ı
    -0.65
     Alonso
    -0.64
     clipboard
    -0.63
    POSITIVE LOGITS
    wives
    1.43
    wife
    1.31
    keeping
    1.09
    holders
    0.97
    hold
    0.94
    holder
    0.91
    warming
    0.90
    acles
    0.87
    plant
    0.86
    cle
    0.86
    Act Density 0.022%

    No Known Activations