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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating societal issues or political dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sort
    -0.17
    ãģªãģĮãĤī
    -0.15
    ãģĭãģ®
    -0.14
    ÅĻaz
    -0.13
    ãģ¨ãģ¯
    -0.13
     Solve
    -0.13
    们
    -0.13
     alike
    -0.13
    (ConfigurationManager
    -0.13
    ï¼Į以åıĬ
    -0.12
    POSITIVE LOGITS
     which
    1.16
    which
    1.00
     Which
    0.83
     WHICH
    0.81
    Which
    0.78
     wich
    0.68
    .which
    0.62
     który
    0.61
     коÑĤоÑĢÑĭй
    0.60
     коÑĤоÑĢаÑı
    0.59
    Act Density 1.541%

    No Known Activations