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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Like" as a common phrase or reference throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vla
    -0.15
    ãĤ¤ãĤ¯
    -0.14
    ula
    -0.14
    ï
    -0.14
     oo
    -0.14
    noc
    -0.14
    uD
    -0.14
    tera
    -0.13
    nten
    -0.13
    oras
    -0.13
    POSITIVE LOGITS
     Jae
    0.17
    sterdam
    0.15
    chwitz
    0.15
    729
    0.15
     Harden
    0.14
    \admin
    0.14
     unto
    0.14
    ÏģÏĮ
    0.14
    .bi
    0.14
    ë°ĺ
    0.13
    Act Density 0.020%

    No Known Activations