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

    Neuronpedia

    INDEX
    Explanations

    references to humans or human beings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.78
    oriasis
    -0.66
    enderror
    -0.63
     Persons
    -0.62
     perſon
    -0.62
     Laufe
    -0.59
    Persons
    -0.59
    copg
    -0.59
    Становништво
    -0.59
     persons
    -0.59
    POSITIVE LOGITS
     humanity
    1.21
     humans
    1.17
     Humans
    1.05
    Humans
    1.03
     Humanity
    1.00
     humanos
    0.89
     mankind
    0.88
     manusia
    0.87
    humans
    0.86
     umani
    0.85
    Act Density 0.090%

    No Known Activations