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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aight
    -0.17
    .scalablytyped
    -0.16
    ilter
    -0.15
    ennen
    -0.14
    رÙĪد
    -0.14
    lili
    -0.13
     Heller
    -0.13
    ¯¼
    -0.13
    ulis
    -0.13
    ConverterFactory
    -0.13
    POSITIVE LOGITS
    rites
    0.18
    ercul
    0.17
    TR
    0.16
     scrub
    0.15
    inos
    0.15
    祥
    0.15
    uns
    0.15
     bro
    0.15
     SCR
    0.15
    sworth
    0.14
    Act Density 0.001%

    No Known Activations