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

    Neuronpedia

    INDEX
    Explanations

    phrases related to storage spaces, particularly closets and drawers

    oai_token-act-pair · gpt-3.5-turbo

    references to storage spaces like closets and drawers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vati
    -0.64
     Ol
    -0.64
    aceous
    -0.63
     luck
    -0.62
    Interstitial
    -0.60
     Riding
    -0.59
    Rich
    -0.59
    ACA
    -0.59
    uana
    -0.58
     administering
    -0.58
    POSITIVE LOGITS
     closet
    1.33
    pedia
    0.79
    rities
    0.78
    ysis
    0.73
     cabinet
    0.72
    soDeliveryDate
    0.72
    glers
    0.70
    bledon
    0.70
    flame
    0.70
    liga
    0.69
    Act Density 0.005%

    No Known Activations