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

    Neuronpedia

    INDEX
    Explanations

    references to values and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     #__
    -0.17
    лаж
    -0.16
    itude
    -0.15
    itag
    -0.15
    orsi
    -0.15
    /tiny
    -0.15
    /DD
    -0.15
    azzi
    -0.15
    unge
    -0.14
    idal
    -0.14
    POSITIVE LOGITS
    /values
    0.19
    å¥
    0.15
     values
    0.15
    hift
    0.15
    -Christian
    0.15
    0.14
    .scalablytyped
    0.14
     Values
    0.14
     Hue
    0.14
    rnd
    0.13
    Act Density 0.053%

    No Known Activations