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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to conspiracy and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampilan
    -0.44
     obowią
    -0.43
     OMITBAD
    -0.42
    diğimiz
    -0.39
    ziehen
    -0.38
     défend
    -0.37
     behandel
    -0.36
    zieht
    -0.36
     bomberos
    -0.36
    Leistung
    -0.36
    POSITIVE LOGITS
     plot
    1.47
     conspiracy
    1.40
     plots
    1.37
     plotting
    1.37
     conspira
    1.30
     plotted
    1.29
     conspir
    1.29
     Plot
    1.21
    plot
    1.17
     Conspiracy
    1.16
    Act Density 0.775%

    No Known Activations