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

    Neuronpedia

    INDEX
    Explanations

    phrases related to awareness and knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bcryptjs
    -0.70
    posób
    -0.67
    anadium
    -0.66
     Pickering
    -0.65
    mpg
    -0.65
    войства
    -0.64
     Quig
    -0.63
    IndentedString
    -0.63
    </tbody>
    -0.62
     roost
    -0.62
    POSITIVE LOGITS
     awareness
    1.49
     Aware
    1.46
     aware
    1.44
    awareness
    1.37
     Awareness
    1.37
    aware
    1.36
    Awareness
    1.35
    Aware
    1.14
    wareness
    1.07
     Conscious
    0.96
    Act Density 0.040%

    No Known Activations