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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference groups of people or collective identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.52
    LikeLike
    -0.48
     Mec
    -0.48
     frage
    -0.46
    opensource
    -0.46
    Nå
    -0.45
    mány
    -0.44
    dotta
    -0.44
    Köszönöm
    -0.44
     two
    -0.44
    POSITIVE LOGITS
     którzy
    0.80
     quienes
    0.80
     coloro
    0.78
     Others
    0.71
    Others
    0.71
    setVerticalGroup
    0.70
     others
    0.67
    osoever
    0.66
    คนที่
    0.66
     ktorí
    0.66
    Act Density 0.112%

    No Known Activations