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

    Neuronpedia

    INDEX
    Explanations

    phrases related to human well-being or safety

    oai_token-act-pair · gpt-3.5-turbo

    references to the importance of lives and safety in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.71
    NetMessage
    -0.67
    roo
    -0.66
    shall
    -0.66
    ãĥķãĤ©
    -0.65
    MpServer
    -0.65
    é¾
    -0.64
    INO
    -0.63
    ICO
    -0.62
    asketball
    -0.62
    POSITIVE LOGITS
    ourge
    0.76
    iest
    0.76
     of
    0.65
    ghai
    0.64
     worn
    0.63
     portion
    0.60
    liest
    0.59
    hirt
    0.59
    fulness
    0.59
     gap
    0.58
    Act Density 0.384%

    No Known Activations