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

    Neuronpedia

    INDEX
    Explanations

    references to messaging and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilians
    -0.15
    \/
    -0.15
     дог
    -0.14
    ekim
    -0.14
    arga
    -0.14
    ople
    -0.14
     hired
    -0.14
    annie
    -0.14
    444
    -0.14
    ieve
    -0.14
    POSITIVE LOGITS
    avad
    0.18
    tps
    0.14
    ucher
    0.14
    è¯
    0.14
     Kens
    0.14
    okes
    0.14
    ãĤ¡
    0.14
     griev
    0.14
    RTL
    0.14
     com
    0.13
    Act Density 0.014%

    No Known Activations