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

    Neuronpedia

    INDEX
    Explanations

    assertions and references to understanding or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antaranya
    -0.77
     bordada
    -0.73
    tvguidetime
    -0.71
     AssemblyCulture
    -0.67
     voidaan
    -0.67
     adicionales
    -0.66
     restantes
    -0.64
     lisäksi
    -0.62
     supplémentaire
    -0.62
     aportes
    -0.60
    POSITIVE LOGITS
     humans
    0.90
     people
    0.83
     Americans
    0.79
     women
    0.75
     everyone
    0.72
    Humans
    0.70
     modern
    0.70
     日本の
    0.70
     capitalism
    0.70
     everybody
    0.69
    Act Density 0.527%

    No Known Activations