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

    Neuronpedia

    INDEX
    Explanations

    mentions of future-related concepts or predictions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to future developments and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyal
    -0.76
    Avg
    -0.69
    pton
    -0.69
    houn
    -0.67
    nick
    -0.66
    reau
    -0.64
    itte
    -0.63
    hoe
    -0.63
    iasco
    -0.62
    Hour
    -0.61
    POSITIVE LOGITS
     Future
    0.70
    livion
    0.68
     Starg
    0.68
     Rapt
    0.67
     Krypt
    0.66
     2021
    0.64
     Computing
    0.64
    uploads
    0.63
     reckoning
    0.62
     amen
    0.61
    Act Density 0.270%

    No Known Activations