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

    Neuronpedia

    INDEX
    Explanations

    concepts related to crime, law, and societal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.59
     ***!
    -0.57
    oneofs
    -0.57
     smtplib
    -0.56
     nonUne
    -0.56
     Defects
    -0.54
    adpleegd
    -0.52
    __*/
    -0.52
    AnimationsModule
    -0.52
     дописавши
    -0.51
    POSITIVE LOGITS
     interactions
    0.57
     relationships
    0.55
     influencing
    0.54
     interaction
    0.53
     interact
    0.53
     influences
    0.51
     people
    0.48
     influence
    0.47
     social
    0.47
     determining
    0.46
    Act Density 0.387%

    No Known Activations