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

    Neuronpedia

    INDEX
    Explanations

    references to a variety of items or categories that are part of a collection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atorium
    -0.16
    Ñĵ
    -0.15
    oster
    -0.15
    ç¾
    -0.14
    åı¦å¤ĸ
    -0.13
    asin
    -0.13
    ãĥķãĥĪ
    -0.13
    acos
    -0.13
    á»IJ
    -0.13
    ault
    -0.13
    POSITIVE LOGITS
     simple
    0.19
     to
    0.17
    ihad
    0.15
    enger
    0.14
    ToFile
    0.14
    ect
    0.14
    ä¿
    0.14
    simple
    0.14
    ToArray
    0.14
    ebek
    0.14
    Act Density 0.020%

    No Known Activations