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

    Neuronpedia

    INDEX
    Explanations

    phrases related to roofs

    oai_token-act-pair · gpt-3.5-turbo

    references to roofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avez
    -0.87
     MacArthur
    -0.80
    Americans
    -0.68
    csv
    -0.66
    å¦
    -0.64
    Associated
    -0.63
    Clar
    -0.63
    Pacific
    -0.63
    gotten
    -0.63
     Sacrament
    -0.63
    POSITIVE LOGITS
     roof
    1.10
     roofs
    0.89
     loft
    0.84
    deck
    0.81
     alley
    0.81
    ilion
    0.81
    loo
    0.77
     Roof
    0.76
     cleaners
    0.75
     terr
    0.75
    Act Density 0.006%

    No Known Activations