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

    Neuronpedia

    INDEX
    Explanations

    terms related to inclusivity and representation in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ByUrl
    -0.16
    ded
    -0.14
    let
    -0.14
    rough
    -0.14
    èĸĦ
    -0.14
    ÑĢоÑī
    -0.14
     BaseEntity
    -0.14
    лиз
    -0.14
    à¸Ľà¸£à¸°à¸Īำ
    -0.14
    isas
    -0.13
    POSITIVE LOGITS
     terms
    0.23
    Terms
    0.22
    .term
    0.21
     term
    0.20
    Term
    0.18
     usage
    0.18
     terme
    0.17
    /terms
    0.17
    TERM
    0.17
    _term
    0.16
    Act Density 0.125%

    No Known Activations