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

    Neuronpedia

    INDEX
    Explanations

    references to international relations and political implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    аÑĢÑĤ
    -0.16
     Åŀirket
    -0.16
    æĿ
    -0.15
    _Struct
    -0.15
    adius
    -0.14
    levator
    -0.14
    ica
    -0.14
    animations
    -0.14
    uko
    -0.14
     "[%
    -0.14
    POSITIVE LOGITS
     handjob
    0.17
     ref
    0.16
    anoi
    0.16
     neutrality
    0.16
    971
    0.16
     unp
    0.15
    ref
    0.15
    aran
    0.15
    ãģĩ
    0.15
     cooperate
    0.15
    Act Density 0.278%

    No Known Activations