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

    Neuronpedia

    INDEX
    Explanations

    instances where the concept of being "aware" is mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "aware."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     retri
    -0.57
     reunion
    -0.56
     reun
    -0.55
    cific
    -0.55
    entry
    -0.54
    cell
    -0.53
    irrel
    -0.53
    emetery
    -0.53
    bard
    -0.52
     coord
    -0.51
    POSITIVE LOGITS
    ledged
    1.17
    ledge
    0.97
     thereof
    0.95
     of
    0.93
    clinton
    0.79
    Of
    0.79
    ial
    0.77
    of
    0.73
     OF
    0.71
    aking
    0.71
    Act Density 0.048%

    No Known Activations