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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of buildings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "houses."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clipboard
    -0.67
    ovic
    -0.66
    sson
    -0.65
    ibe
    -0.65
     trending
    -0.65
    ookie
    -0.64
    enza
    -0.63
    role
    -0.62
    icht
    -0.61
    error
    -0.59
    POSITIVE LOGITS
     houses
    3.97
     Houses
    2.79
    houses
    2.33
     house
    2.25
     homes
    2.22
     dwellings
    2.04
     residences
    1.95
     buildings
    1.80
     apartments
    1.69
     rooms
    1.63
    Act Density 0.014%

    No Known Activations