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

    Neuronpedia

    INDEX
    Explanations

    references to storage spaces such as 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
    -0.68
    odic
    -0.68
    iva
    -0.66
    uana
    -0.65
    Downloadha
    -0.62
     Rounds
    -0.61
    aceous
    -0.61
    Interstitial
    -0.60
    onso
    -0.60
    awar
    -0.59
    POSITIVE LOGITS
     closet
    1.21
    pedia
    0.84
     shelves
    0.80
    bryce
    0.79
    stairs
    0.75
     drawer
    0.74
     attic
    0.72
    rities
    0.72
     doors
    0.72
     fireplace
    0.71
    Act Density 0.007%

    No Known Activations