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

    Neuronpedia

    INDEX
    Explanations

    attribute-value pairs in HTML or XML code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intr
    -0.15
     Williamson
    -0.15
    intr
    -0.15
    rale
    -0.14
    emem
    -0.14
    awy
    -0.13
    berapa
    -0.13
    ÑĸйÑģ
    -0.13
    423
    -0.13
    rama
    -0.13
    POSITIVE LOGITS
    UPPORTED
    0.16
    uch
    0.15
    auen
    0.15
     ruce
    0.14
    UCH
    0.14
    ajor
    0.14
    olars
    0.13
    quoi
    0.13
    asant
    0.13
    s
    0.13
    Act Density 0.001%

    No Known Activations