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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or terms related to a particular language or culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Citadel
    -0.16
    fds
    -0.16
    andra
    -0.15
    pis
    -0.15
    fold
    -0.15
    ault
    -0.15
    uye
    -0.14
    enberg
    -0.14
    âl
    -0.14
    ikel
    -0.14
    POSITIVE LOGITS
    å§ĵ
    0.20
    usercontent
    0.17
    /Dk
    0.17
    UrlParser
    0.15
    è£ķ
    0.15
    izador
    0.15
    cket
    0.15
    $LANG
    0.14
    ows
    0.13
     fu
    0.13
    Act Density 0.050%

    No Known Activations