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

    Neuronpedia

    INDEX
    Explanations

    phrases related to participation and learning experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stranger
    -0.15
    书记
    -0.14
     bytesRead
    -0.13
    raman
    -0.13
    oubted
    -0.13
    ereotype
    -0.13
    (Link
    -0.13
    plural
    -0.13
    .Ed
    -0.13
    DES
    -0.13
    POSITIVE LOGITS
    æĹı
    0.16
     Thornton
    0.15
    ulet
    0.15
    çİĩ
    0.14
    ï¸
    0.14
    ìį¨
    0.14
    epad
    0.14
    907
    0.14
    ãĤ
    0.14
    úsqueda
    0.14
    Act Density 0.052%

    No Known Activations