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

    Neuronpedia

    INDEX
    Explanations

    references to non-linear concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gram
    -0.17
    onis
    -0.16
    UNCTION
    -0.14
     Gram
    -0.14
    reff
    -0.14
    ãĥ¼ãĥģ
    -0.14
    ì¦Į
    -0.14
    ecute
    -0.14
    _ACL
    -0.14
    plier
    -0.13
    POSITIVE LOGITS
    ÑĢави
    0.16
    för
    0.16
     lẽ
    0.16
    onymous
    0.15
    ationToken
    0.14
    .RemoveAll
    0.14
    ymous
    0.14
    ô
    0.14
    ındaki
    0.14
    rej
    0.14
    Act Density 0.027%

    No Known Activations