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

    Neuronpedia

    INDEX
    Explanations

    references to floors and levels in buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.51
     transfieras
    -0.51
    VolleyError
    -0.47
     Başkanı
    -0.47
     hObject
    -0.46
    경
    -0.46
     الاطلاع
    -0.46
    Guard
    -0.45
    безпе
    -0.43
    chieben
    -0.43
    POSITIVE LOGITS
     upstairs
    1.27
    Upstairs
    1.17
    stairs
    1.09
     rooftop
    1.04
     attic
    1.03
     stairs
    0.90
     downstairs
    0.89
     penthouse
    0.88
     roof
    0.87
     étage
    0.87
    Act Density 0.111%

    No Known Activations