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

    Neuronpedia

    INDEX
    Explanations

    phrases related to building and maintaining physical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ТÐŀ
    -0.15
    hello
    -0.14
    [email
    -0.14
    oyo
    -0.14
    endor
    -0.14
    eking
    -0.14
    adv
    -0.14
    verty
    -0.14
    lius
    -0.14
     Hello
    -0.13
    POSITIVE LOGITS
    isser
    0.15
     cade
    0.14
     lòng
    0.14
    erken
    0.14
    edd
    0.14
     cán
    0.14
    569
    0.13
     CommandType
    0.13
    ABCDEFGHIJKLMNOP
    0.13
    íĦ¸
    0.13
    Act Density 0.455%

    No Known Activations