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

    Neuronpedia

    INDEX
    Explanations

    specific characters and symbols often related to technical or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    аÑĢÑĩ
    -0.16
     оÑĤп
    -0.14
    ocio
    -0.14
    GN
    -0.14
    anding
    -0.14
    asing
    -0.14
    rasing
    -0.14
    levard
    -0.13
    loan
    -0.13
    claimer
    -0.13
    POSITIVE LOGITS
     giving
    0.29
     give
    0.27
     gives
    0.25
     gave
    0.25
     Give
    0.24
     Giving
    0.24
    give
    0.23
    Give
    0.23
     given
    0.23
    ç»Ļ
    0.23
    Act Density 0.008%

    No Known Activations