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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to legal or political entities

    oai_token-act-pair · gpt-3.5-turbo

    the letter "A" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     optics
    -0.66
    enegger
    -0.66
    reports
    -0.63
     Indigo
    -0.61
    falls
    -0.59
     upstairs
    -0.58
     Emanuel
    -0.56
    ]}
    -0.55
     Alph
    -0.55
    faces
    -0.55
    POSITIVE LOGITS
    ussie
    1.28
    cknowled
    1.18
    cknow
    1.17
    verages
    1.15
    uctions
    1.07
    BILITIES
    1.05
    perture
    1.04
    UG
    1.03
    lyss
    1.00
    HAHA
    0.99
    Act Density 0.089%

    No Known Activations