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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to specific parts or locations.

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or geographical areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.79
    maid
    -0.77
    arten
    -0.70
    wash
    -0.68
    uci
    -0.68
     Akin
    -0.66
    arians
    -0.65
    puff
    -0.65
    owicz
    -0.63
     alone
    -0.63
    POSITIVE LOGITS
     equation
    1.06
     country
    0.92
     spectrum
    0.89
     same
    0.86
     world
    0.84
     globe
    0.82
     universe
    0.82
     continuum
    0.80
     city
    0.79
     smallest
    0.79
    Act Density 0.254%

    No Known Activations