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

    Neuronpedia

    INDEX
    Explanations

    references to individual characters and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sobie
    -0.17
    δη
    -0.17
    ards
    -0.15
    quier
    -0.15
    ानत
    -0.15
     завиÑģим
    -0.14
     ÑģобÑĸ
    -0.14
    ÃŁen
    -0.14
     having
    -0.14
     Having
    -0.14
    POSITIVE LOGITS
     Ñĥдал
    0.17
    Ñĥжд
    0.16
    permit
    0.16
     hroz
    0.16
     umož
    0.16
    .scalablytyped
    0.15
     ulaÅŁ
    0.15
    elo
    0.15
    umen
    0.15
    _Framework
    0.15
    Act Density 0.023%

    No Known Activations