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

    Neuronpedia

    INDEX
    Explanations

    instances of examples and references to comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vl
    -0.14
    urt
    -0.14
    ãĥ³ãĤ¸
    -0.14
    ãĥ¼ãĥ
    -0.14
    tim
    -0.14
    uh
    -0.14
    Æ¡
    -0.13
    amil
    -0.13
    .ByteArray
    -0.13
    amel
    -0.13
    POSITIVE LOGITS
    ampo
    0.17
    .struts
    0.15
    agements
    0.14
    Ú¯ÛĮرÛĮ
    0.14
    KeyDown
    0.14
     اÙĦÙĨÙĩ
    0.14
    å³°
    0.14
    biased
    0.14
    imon
    0.13
    ampoo
    0.13
    Act Density 0.019%

    No Known Activations