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

    Neuronpedia

    INDEX
    Explanations

    terms related to innovation and legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doctrine
    -0.73
     Faw
    -0.68
    WAYS
    -0.65
    ness
    -0.64
     Roads
    -0.63
     Origin
    -0.62
     Thrones
    -0.61
     Europa
    -0.61
     LORD
    -0.60
     Worlds
    -0.59
    POSITIVE LOGITS
    ated
    1.91
    ating
    1.90
    ators
    1.65
    ator
    1.64
    atively
    1.58
    ations
    1.55
    ates
    1.52
    ational
    1.51
    atory
    1.44
    ative
    1.40
    Act Density 0.016%

    No Known Activations