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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "home"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "home."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    milo
    -0.70
     Tokens
    -0.67
    Iterator
    -0.63
     Apostles
    -0.63
    illusion
    -0.60
    agree
    -0.60
    worms
    -0.59
     Apostle
    -0.59
    wu
    -0.58
    TED
    -0.58
    POSITIVE LOGITS
     home
    3.74
    home
    2.81
    Home
    2.57
     Home
    2.50
     HOME
    2.49
     homes
    2.19
     house
    1.59
    HOME
    1.54
     Homes
    1.51
     homers
    1.49
    Act Density 0.038%

    No Known Activations