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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship or source attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enberg
    -0.15
    æ³Ĭ
    -0.15
    aler
    -0.15
    oler
    -0.15
    /*č↵
    -0.14
    nip
    -0.14
    ÙħÙĨد
    -0.14
    .setAction
    -0.14
    noon
    -0.13
    γκα
    -0.13
    POSITIVE LOGITS
     bol
    0.15
     ...
    0.15
    ãĥ³ãĥIJ
    0.15
    ãĤ·ãĥ¼
    0.14
    cura
    0.14
     swo
    0.14
    0.13
    fol
    0.13
     rit
    0.13
    .ones
    0.13
    Act Density 0.213%

    No Known Activations