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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iture
    -0.16
    vers
    -0.15
    opsis
    -0.14
     attention
    -0.14
    ahan
    -0.14
    gan
    -0.13
    versation
    -0.13
    azzi
    -0.13
    ToInt
    -0.13
    ove
    -0.13
    POSITIVE LOGITS
    ythe
    0.15
    ικα
    0.14
    StringUtil
    0.14
    Ấ
    0.14
    UILDER
    0.14
     bằng
    0.13
    нÑıÑĤи
    0.13
    IBUT
    0.13
     SPDX
    0.13
    é®®
    0.13
    Act Density 0.054%

    No Known Activations