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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing size

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing size or scale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vironment
    -0.81
    actionDate
    -0.80
    manship
    -0.78
    anship
    -0.77
    RP
    -0.76
    proven
    -0.73
    alysis
    -0.73
    termination
    -0.73
    âĸ¬
    -0.72
     Assass
    -0.72
    POSITIVE LOGITS
     intestine
    1.15
     sized
    1.09
     rectangular
    1.05
     bulky
    1.00
     chunks
    1.00
     cyl
    0.91
     stature
    0.91
     diameter
    0.90
     chunk
    0.89
     oversized
    0.88
    Act Density 0.107%

    No Known Activations