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

    Neuronpedia

    INDEX
    Explanations

    notations or elements that signify cultural or systemic hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ofire
    -0.16
    ignum
    -0.16
    alian
    -0.15
    vox
    -0.14
    ullet
    -0.14
    _lite
    -0.14
     ÐĵÐŀ
    -0.14
    formance
    -0.14
    ndern
    -0.14
    lst
    -0.14
    POSITIVE LOGITS
     pair
    0.27
     Pair
    0.23
     fra
    0.23
     richt
    0.23
     efter
    0.23
     wi
    0.21
    ither
    0.21
    Pair
    0.20
    pair
    0.20
     slic
    0.20
    Act Density 0.001%

    No Known Activations