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

    Neuronpedia

    INDEX
    Explanations

    terms associated with manipulation and self-interest in social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CppCodeGen
    -0.38
     BoxDecoration
    -0.38
    onames
    -0.37
     cazul
    -0.36
     diagnostica
    -0.36
     AssemblyTitle
    -0.35
     InputDecoration
    -0.35
    denn
    -0.34
     bezig
    -0.34
    ocino
    -0.34
    POSITIVE LOGITS
     subserv
    1.47
     obedience
    1.42
     obedient
    1.40
     submission
    1.36
     submissive
    1.30
     Obedience
    1.20
     obe
    1.18
     obed
    1.18
     obey
    1.16
     Submission
    1.16
    Act Density 0.738%

    No Known Activations