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

    Neuronpedia

    INDEX
    Explanations

    references to homes or residential locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLU
    -0.16
     Buildings
    -0.15
    uno
    -0.15
    алÑĭ
    -0.15
     etiqu
    -0.15
    ridor
    -0.15
    oeff
    -0.14
     attr
    -0.14
    ardi
    -0.14
     corridor
    -0.14
    POSITIVE LOGITS
     quarters
    0.22
     studio
    0.21
     digs
    0.21
     headquarters
    0.21
     home
    0.20
     pad
    0.20
     HQ
    0.20
    HQ
    0.19
     hide
    0.19
     pent
    0.19
    Act Density 0.149%

    No Known Activations