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

    Neuronpedia

    INDEX
    Explanations

    terms related to political topics or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndInit
    -0.52
    ochim
    -0.49
    lem
    -0.49
    cchi
    -0.48
    kende
    -0.48
    cers
    -0.47
    zkopf
    -0.47
    SEGUIR
    -0.47
    chloric
    -0.46
    ölker
    -0.45
    POSITIVE LOGITS
     AssemblyCompany
    0.48
    zzleHttp
    0.46
     correctness
    0.43
    Życiorys
    0.39
    Party
    0.39
     Party
    0.38
     Parties
    0.38
     PARTY
    0.37
    astify
    0.37
     UIColor
    0.36
    Act Density 0.089%

    No Known Activations