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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accessibility and inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orman
    -0.21
    allen
    -0.15
    adt
    -0.15
    iko
    -0.14
    _CID
    -0.14
    oyal
    -0.14
    embedded
    -0.13
    pio
    -0.13
    ibs
    -0.13
    ibe
    -0.13
    POSITIVE LOGITS
    миÑĤ
    0.18
    azon
    0.16
    ľ
    0.15
     valid
    0.14
    @brief
    0.14
     Dün
    0.14
     Král
    0.14
    alytics
    0.14
    yro
    0.14
     Morr
    0.14
    Act Density 0.076%

    No Known Activations