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

    Neuronpedia

    INDEX
    Explanations

    references to Greek letter organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to Greek letters and fraternities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.91
    puter
    -0.87
    ibrary
    -0.85
    */(
    -0.80
    iflower
    -0.79
    iage
    -0.79
    lessly
    -0.75
    aiman
    -0.74
    standing
    -0.70
    taboola
    -0.70
    POSITIVE LOGITS
     Centauri
    1.43
     Phi
    1.11
     Kappa
    1.00
     Tau
    0.93
     Quad
    0.92
     Eps
    0.91
     Gamma
    0.89
     Chi
    0.88
     Sigma
    0.88
    Wing
    0.85
    Act Density 0.062%

    No Known Activations