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

    Neuronpedia

    INDEX
    Explanations

    phrases related to knowledge or awareness

    oai_token-act-pair · gpt-3.5-turbo

    the word "aware" and related phrases indicating knowledge or consciousness of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.76
    itent
    -0.72
    hement
    -0.66
    uld
    -0.65
     cess
    -0.65
    uably
    -0.63
    nets
    -0.62
    estyles
    -0.60
    ocate
    -0.60
    aints
    -0.60
    POSITIVE LOGITS
     what
    0.92
     how
    0.87
     course
    0.83
     sorts
    0.75
     anything
    0.74
     wrongdoing
    0.71
     whats
    0.71
     HOW
    0.69
     everything
    0.67
     impending
    0.67
    Act Density 0.082%

    No Known Activations