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

    Neuronpedia

    INDEX
    Explanations

    references to educational and informational resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acons
    -0.15
     borr
    -0.15
    ноÑģÑĤи
    -0.15
    idding
    -0.15
    ditor
    -0.14
    ãĥ¼ãĥĢ
    -0.14
     advertisement
    -0.14
    ppo
    -0.14
    manship
    -0.14
    Advertisement
    -0.13
    POSITIVE LOGITS
     press
    0.33
     embargo
    0.27
     PR
    0.27
     media
    0.26
     journalists
    0.25
     Press
    0.25
    press
    0.25
    PR
    0.24
     MEDIA
    0.23
    Press
    0.23
    Act Density 0.064%

    No Known Activations