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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate illumination or enlightenment, often in a metaphorical sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollectionView
    -0.57
    SourceChecksum
    -0.54
     getItemCount
    -0.53
    writeFieldEnd
    -0.51
     FormData
    -0.50
     estekak
    -0.50
    oneofs
    -0.49
     يتيمه
    -0.48
    formik
    -0.46
     referrerpolicy
    -0.45
    POSITIVE LOGITS
     light
    3.48
    light
    3.05
     Light
    2.98
    Light
    2.95
     LIGHT
    2.91
     lights
    2.88
    LIGHT
    2.64
     lighting
    2.64
    lights
    2.58
     Lights
    2.52
    Act Density 0.811%

    No Known Activations