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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms related to societal issues and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.64
     alguno
    -0.63
     sufficiente
    -0.60
     tiennent
    -0.58
     alemanes
    -0.58
     algum
    -0.58
     importantly
    -0.57
     esetén
    -0.56
    tahankan
    -0.56
     interessanti
    -0.53
    POSITIVE LOGITS
     nature
    1.39
    nature
    1.08
     confines
    1.05
     presence
    0.96
     majority
    0.92
     intricacies
    0.88
     NATURE
    0.85
     absence
    0.85
     workings
    0.85
     extent
    0.84
    Act Density 0.558%

    No Known Activations