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

    Neuronpedia

    INDEX
    Explanations

    words associated with brightness or reflective qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -1.00
    PathVariable
    -0.82
     idéia
    -0.76
    NegativeButton
    -0.76
     AppBundle
    -0.74
    Rptr
    -0.73
     Gentry
    -0.73
    ltk
    -0.72
    StreetMap
    -0.72
    endphp
    -0.71
    POSITIVE LOGITS
     shine
    2.66
     shines
    2.34
     shining
    2.30
     Shine
    2.28
    shine
    2.20
    Shine
    2.18
     shone
    2.06
     Shining
    2.03
    Shining
    1.95
    shining
    1.87
    Act Density 0.078%

    No Known Activations