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

    Neuronpedia

    INDEX
    Explanations

    terms related to manipulation and deception in social or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.54
    rungsseite
    -0.44
    MessageTagHelper
    -0.44
    thusi
    -0.43
    IntoConstraints
    -0.41
    seamnă
    -0.41
     resourceCulture
    -0.40
     przypad
    -0.40
    NewUrlParser
    -0.40
     dormitórios
    -0.40
    POSITIVE LOGITS
     trick
    2.16
     tricks
    2.03
     Trick
    1.62
    trick
    1.62
     Tricks
    1.55
    tricks
    1.53
     cunning
    1.47
    Trick
    1.45
     trucos
    1.35
     tactics
    1.31
    Act Density 0.643%

    No Known Activations