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

    Neuronpedia

    INDEX
    Explanations

    terms related to human rights

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦
    -0.68
    INO
    -0.67
    onne
    -0.66
     wink
    -0.65
    rypt
    -0.65
     Rowling
    -0.64
    REAM
    -0.63
    uries
    -0.63
     Gunn
    -0.63
    arella
    -0.63
    POSITIVE LOGITS
    itarian
    1.30
    itary
    1.13
    itar
    1.02
     Rights
    0.96
    istic
    0.82
    izen
    0.79
     Traff
    0.78
    izational
    0.78
    itaire
    0.78
    ité
    0.78
    Act Density 0.014%

    No Known Activations