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

    Neuronpedia

    INDEX
    Explanations

    references to studies or documents related to peace and security issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     //!<
    -0.16
    аÑĢам
    -0.15
     programmes
    -0.14
    PIX
    -0.14
    bew
    -0.14
    hue
    -0.14
     silhouette
    -0.13
     programs
    -0.13
     rotations
    -0.13
    ARSER
    -0.13
    POSITIVE LOGITS
     report
    0.24
     released
    0.20
    released
    0.19
     release
    0.18
     Released
    0.18
    Released
    0.17
    report
    0.17
    æĬ¥åijĬ
    0.17
     Report
    0.17
     paper
    0.17
    Act Density 0.120%

    No Known Activations