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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve formatting or concatenation in strings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄĻp
    -0.18
    ders
    -0.15
    ÏĥÏīÏĢ
    -0.14
    æĤŁ
    -0.14
    ãĥªãĥ³ãĤ°
    -0.14
    horn
    -0.14
    hani
    -0.14
    ê¶Į
    -0.14
     christ
    -0.13
    leston
    -0.13
    POSITIVE LOGITS
    angu
    0.16
    rve
    0.15
    achen
    0.14
    ayet
    0.14
    .Mutable
    0.14
    .nr
    0.14
     Snyder
    0.14
    oire
    0.14
    udas
    0.14
    artment
    0.14
    Act Density 0.165%

    No Known Activations