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

    Neuronpedia

    INDEX
    Explanations

    references to the societal impact and implications of artificial intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ryan
    -0.16
    lew
    -0.16
    aco
    -0.15
    ritz
    -0.14
    enant
    -0.14
     di
    -0.14
    andi
    -0.14
    дÑĢом
    -0.14
    pez
    -0.14
    Contr
    -0.14
    POSITIVE LOGITS
    icker
    0.16
     future
    0.16
    shade
    0.16
     Eth
    0.15
     fut
    0.15
     potential
    0.14
     concerned
    0.14
     entr
    0.14
     privacy
    0.14
     Chatt
    0.14
    Act Density 0.167%

    No Known Activations