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

    Neuronpedia

    INDEX
    Explanations

    references to specific organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Malk
    -0.15
    ecute
    -0.15
    ymi
    -0.14
    Ñıж
    -0.14
     _↵↵
    -0.14
    478
    -0.14
    nes
    -0.13
    rames
    -0.13
    .Messaging
    -0.13
     vô
    -0.13
    POSITIVE LOGITS
    ody
    0.15
     rend
    0.15
    arius
    0.14
    Fallback
    0.14
     meg
    0.13
    dio
    0.13
     HID
    0.13
    ium
    0.13
     Franco
    0.13
    ı
    0.13
    Act Density 0.501%

    No Known Activations