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

    Neuronpedia

    INDEX
    Explanations

    legal terms and references to court cases and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cases
    -0.17
     Cases
    -0.17
    ilim
    -0.16
    ãĥIJãĤ¹
    -0.15
    ieber
    -0.15
    Cases
    -0.15
    à¥Ģम
    -0.14
    ãĥ¡ãĥ©
    -0.14
     even
    -0.13
    FRING
    -0.13
    POSITIVE LOGITS
    ä¹Ļ
    0.16
    UIT
    0.16
     Relevant
    0.15
    olean
    0.15
    ÅĻÃŃm
    0.15
    uitar
    0.14
     Rally
    0.14
    ucker
    0.14
     alleged
    0.14
     Lovely
    0.14
    Act Density 0.227%

    No Known Activations