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

    Neuronpedia

    INDEX
    Explanations

    references to corruption and political scandals involving individuals in power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     benefic
    -0.44
     PMI
    -0.41
     kron
    -0.39
     GAD
    -0.39
     Raoul
    -0.38
    ThroughAttribute
    -0.37
    ziasztok
    -0.36
    PMI
    -0.36
     desglose
    -0.36
     suff
    -0.36
    POSITIVE LOGITS
    ̈́
    0.49
    fjspx
    0.47
     contextLoads
    0.46
     llorando
    0.45
    BeginInit
    0.45
     sidang
    0.45
     sayang
    0.44
     HttpNotFound
    0.44
    Legături
    0.43
     otomatig
    0.43
    Act Density 0.412%

    No Known Activations