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

    Neuronpedia

    INDEX
    Explanations

    phrases related to awareness and consciousness regarding facts or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mu
    -0.66
     Biggs
    -0.66
    IndentedString
    -0.65
    yong
    -0.65
    ://
    -0.63
    din
    -0.60
     Schultz
    -0.60
    walde
    -0.59
    Mu
    -0.59
    QUADS
    -0.59
    POSITIVE LOGITS
     aware
    2.21
     Aware
    2.09
     awareness
    2.05
    awareness
    1.93
    aware
    1.93
     Awareness
    1.86
    Awareness
    1.82
    Aware
    1.58
     unaware
    1.45
     consciente
    1.34
    Act Density 0.062%

    No Known Activations