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

    Neuronpedia

    INDEX
    Explanations

    structured formats and placeholders commonly used in forms or surveys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auce
    -0.15
    aname
    -0.15
    -0.15
    ardo
    -0.14
    azel
    -0.14
    ewis
    -0.14
    argon
    -0.14
    endregion
    -0.14
     Sas
    -0.14
     milfs
    -0.13
    POSITIVE LOGITS
    alog
    0.17
    ait
    0.16
    ../../
    0.16
    .........
    0.16
    LayoutConstraint
    0.15
    .......
    0.15
    237
    0.15
    ¾
    0.14
    ......
    0.14
    orno
    0.14
    Act Density 0.003%

    No Known Activations