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

    Neuronpedia

    INDEX
    Explanations

    references to curtains and their various states or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etically
    -0.90
    lihood
    -0.81
    nesota
    -0.81
    livious
    -0.73
    ciating
    -0.70
    orically
    -0.70
    iewicz
    -0.69
     Galile
    -0.69
    itude
    -0.68
    ese
    -0.68
    POSITIVE LOGITS
     curtains
    1.29
     curtain
    1.22
    glass
    0.98
     canopy
    0.81
     veil
    0.80
     Veil
    0.79
     ceiling
    0.77
    atcher
    0.77
     walls
    0.76
     shroud
    0.75
    Act Density 0.005%

    No Known Activations