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

    Neuronpedia

    INDEX
    Explanations

    patterns related to regex and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aul
    -0.17
    adla
    -0.17
    oter
    -0.16
    erra
    -0.16
    oland
    -0.15
    ample
    -0.14
    ]^
    -0.14
    ravel
    -0.14
    è¾ŀ
    -0.14
    ilk
    -0.14
    POSITIVE LOGITS
    +
    0.19
    +↵
    0.16
    {
    0.16
    (æ°´
    0.15
    ãĥĬãĥ«
    0.15
    +↵↵
    0.14
    +:
    0.14
    eros
    0.14
    |\
    0.14
     wig
    0.14
    Act Density 0.036%

    No Known Activations