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

    Neuronpedia

    INDEX
    Explanations

    Choices and preferences regarding relationships and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldo
    -0.19
    ç¿Ķ
    -0.16
    cht
    -0.15
    ãĥ¼ãĥį
    -0.15
    ember
    -0.15
    prite
    -0.15
    reso
    -0.14
    PFN
    -0.14
    eldo
    -0.14
    ÑĢон
    -0.14
    POSITIVE LOGITS
     instead
    0.19
    instead
    0.19
    Instead
    0.17
     Instead
    0.17
    thon
    0.15
    gua
    0.15
    лами
    0.14
     mil
    0.14
    MBED
    0.14
     mont
    0.14
    Act Density 0.721%

    No Known Activations