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

    Neuronpedia

    INDEX
    Explanations

    discussions around mistakes and moral complexity in human behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bubble
    -0.18
     Bubble
    -0.18
    bubble
    -0.17
    ÏħÏĩ
    -0.17
    upa
    -0.17
    íİ
    -0.16
     bubbles
    -0.16
     bubble
    -0.15
    arma
    -0.14
    aben
    -0.14
    POSITIVE LOGITS
     nuts
    0.16
    erten
    0.15
    ogue
    0.15
    Ñıж
    0.14
    ãĥ©ãĥ³ãĤ¹
    0.14
     perfection
    0.14
    á»ķi
    0.14
    Vault
    0.13
     fre
    0.13
    Spo
    0.13
    Act Density 0.294%

    No Known Activations