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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inclusivity and diversity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inclusivity and acceptance within society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.72
    CLASSIFIED
    -0.69
    acca
    -0.66
     proc
    -0.64
     Kham
    -0.64
     rpm
    -0.64
    sonian
    -0.61
    hiba
    -0.61
     caches
    -0.59
     nib
    -0.59
    POSITIVE LOGITS
     inclusive
    0.88
    iveness
    0.87
    ethnic
    0.86
    ivism
    0.85
    gender
    0.84
    galitarian
    0.83
    clus
    0.82
     spaces
    0.82
     society
    0.82
    ivist
    0.81
    Act Density 0.102%

    No Known Activations