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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aho
    -0.18
    ucht
    -0.17
    rouch
    -0.16
    cdb
    -0.15
    ppers
    -0.15
    pei
    -0.15
    proc
    -0.15
    duct
    -0.15
    Contours
    -0.14
    sei
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĥijãĥ¼
    0.15
    514
    0.14
    wat
    0.14
     Sporting
    0.14
    dorf
    0.13
     Kerr
    0.13
    оÑģÑĤ
    0.13
    tsky
    0.13
     shim
    0.13
     detr
    0.13
    Act Density 0.019%

    No Known Activations