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

    Neuronpedia

    INDEX
    Explanations

    references to chapters and their titles or sections in written works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enberg
    -0.17
    755
    -0.17
    ye
    -0.17
    .Parcelable
    -0.16
    yo
    -0.16
    gid
    -0.15
    ÄĽti
    -0.15
    754
    -0.14
    out
    -0.14
     ucwords
    -0.14
    POSITIVE LOGITS
    sterol
    0.19
    IZE
    0.17
    iston
    0.16
    ître
    0.16
    ize
    0.16
    MBOL
    0.15
    ÅĦ
    0.14
    lain
    0.14
    kowski
    0.14
    ãĥ¬ãĥĥãĥĪ
    0.14
    Act Density 0.015%

    No Known Activations