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

    Neuronpedia

    INDEX
    Explanations

    capital letters and/or initials in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Sdk
    -0.20
    shima
    -0.16
    usch
    -0.16
    ÑĪ
    -0.16
    sh
    -0.15
    sher
    -0.15
     ash
    -0.15
    ire
    -0.15
    Å¡
    -0.15
    ãĥĴ
    -0.15
    POSITIVE LOGITS
    ycz
    0.15
     Budd
    0.15
    pais
    0.15
    vine
    0.15
    nop
    0.15
    adele
    0.14
    flat
    0.14
    -flat
    0.14
    ¼åIJĪ
    0.14
    ÑĢов
    0.14
    Act Density 0.051%

    No Known Activations