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

    Neuronpedia

    INDEX
    Explanations

    key terms related to reform and oversight in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emark
    -0.15
    æk
    -0.15
    _DISABLE
    -0.14
    unma
    -0.14
    unky
    -0.14
    emez
    -0.14
     NGX
    -0.14
    ή
    -0.14
    empo
    -0.14
    ellig
    -0.13
    POSITIVE LOGITS
     overdue
    0.40
     long
    0.31
     sore
    0.26
     LONG
    0.24
    long
    0.22
     badly
    0.22
    urg
    0.21
     warranted
    0.21
    .long
    0.20
    (long
    0.20
    Act Density 0.082%

    No Known Activations