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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing quantity or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    868
    -0.17
    oko
    -0.15
     enqu
    -0.15
     Starr
    -0.15
    ãĤ¤ãĤ¯
    -0.15
    /UIKit
    -0.14
    سÛĮÙĨ
    -0.14
     Rogers
    -0.13
    weed
    -0.13
    agine
    -0.13
    POSITIVE LOGITS
    leton
    0.17
    Than
    0.17
    -than
    0.16
    strup
    0.15
    _than
    0.14
    roit
    0.14
    IMAL
    0.14
     Race
    0.14
     than
    0.14
    izyon
    0.14
    Act Density 0.101%

    No Known Activations