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

    Neuronpedia

    INDEX
    Explanations

    certain words related to recognition, respect, and acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    words and variations related to recognition and awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sapphire
    -0.67
     Spur
    -0.66
     Gaul
    -0.66
    BACK
    -0.63
     DRAG
    -0.63
     setbacks
    -0.61
     blindly
    -0.60
     Dollar
    -0.60
     Boko
    -0.60
     Stard
    -0.59
    POSITIVE LOGITS
    izable
    1.58
    ition
    1.42
    ises
    1.41
    isable
    1.39
    isance
    1.37
    ising
    1.32
    izers
    1.31
    izing
    1.27
    izer
    1.27
    ize
    1.24
    Act Density 0.100%

    No Known Activations